From 30a8d55fd0680c03c0935cf2b6f6c342de1c3858 Mon Sep 17 00:00:00 2001 From: Carson Date: Fri, 7 Aug 2026 16:49:03 -0500 Subject: [PATCH 01/14] feat(anthropic): resolve web_fetch citations to source URLs Anthropic's web_fetch tool results carry a document_index that citations reference, but chatlas surfaced that raw index instead of resolving it to the fetched page's URL, leaving citations from web_fetch un-attributable. --- chatlas/_provider_anthropic.py | 48 +++++++- tests/test_provider_anthropic.py | 181 +++++++++++++++++++++++++++++++ 2 files changed, 223 insertions(+), 6 deletions(-) diff --git a/chatlas/_provider_anthropic.py b/chatlas/_provider_anthropic.py index 1749a7d6..6e1a4b0f 100644 --- a/chatlas/_provider_anthropic.py +++ b/chatlas/_provider_anthropic.py @@ -70,6 +70,7 @@ from typing import IO from anthropic.types import ( + ContentBlock, Message, MessageParam, RawMessageStreamEvent, @@ -615,7 +616,12 @@ def stream_content(self, chunk, completion) -> list[Content]: block = completion.content[chunk.index] if block.type == "text": # list() widens list[ContentCitation] to the list[Content] return - return list(anthropic_citations(block)) + return list( + anthropic_citations( + block, + fetch_sources=anthropic_fetch_sources(completion.content), + ) + ) if block.type == "server_tool_use": request = anthropic_server_tool_request(block) return [request] if request is not None else [] @@ -1042,6 +1048,7 @@ def _as_turn(self, completion: Message, has_data_model=False) -> AssistantTurn: check_finish_reason(finish_reason, "error") contents = [] + fetch_sources = anthropic_fetch_sources(completion.content) # Detect which structured output approach was used: # - Old approach: has a _structured_tool_call tool_use block @@ -1058,7 +1065,7 @@ def _as_turn(self, completion: Message, has_data_model=False) -> AssistantTurn: contents.append(ContentJson(value=orjson.loads(content.text))) else: contents.append(ContentText(text=content.text)) - contents.extend(anthropic_citations(content)) + contents.extend(anthropic_citations(content, fetch_sources)) elif content.type == "tool_use": if uses_old_tool_approach and content.name == "_structured_tool_call": if not isinstance(content.input, dict): @@ -1544,18 +1551,33 @@ def list_models(self): return res -def anthropic_citations(block: "TextBlock") -> list[ContentCitation]: +def anthropic_citations( + block: "TextBlock", + fetch_sources: Sequence[WebSource] = (), +) -> list[ContentCitation]: """ContentCitations for one fully-accumulated text block.""" out: list[ContentCitation] = [] for c in block.citations or []: # `url`/`title` only exist on the web-search/search-result members of the # TextCitation union (document citations carry `document_title` instead). url = getattr(c, "url", None) + source = None + if url: + source = WebSource(url=url, title=getattr(c, "title", None)) + else: + document_index = getattr(c, "document_index", None) + if ( + isinstance(document_index, int) + and not isinstance(document_index, bool) + and 0 <= document_index < len(fetch_sources) + ): + source = WebSource( + url=fetch_sources[document_index].url, + title=getattr(c, "document_title", None), + ) out.append( ContentCitation( - source=WebSource(url=url, title=getattr(c, "title", None)) - if url - else None, + source=source, # Anthropic scopes a citation to the text block it arrived on. grounded_span=block.text, cited_quote=c.cited_text, @@ -1565,6 +1587,20 @@ def anthropic_citations(block: "TextBlock") -> list[ContentCitation]: return out +def anthropic_fetch_sources(contents: Sequence["ContentBlock"]) -> list[WebSource]: + """Successful web-fetch sources in the order citations reference them.""" + from anthropic.types import WebFetchBlock + + out: list[WebSource] = [] + for block in contents: + if block.type != "web_fetch_tool_result": + continue + content = block.content + if isinstance(content, WebFetchBlock): + out.append(WebSource(url=content.url, title=content.content.title)) + return out + + def anthropic_server_tool_request( block: "ServerToolUseBlock", ) -> Optional[ContentToolRequestSearch | ContentToolRequestFetch]: diff --git a/tests/test_provider_anthropic.py b/tests/test_provider_anthropic.py index 8c601b7b..626d6099 100644 --- a/tests/test_provider_anthropic.py +++ b/tests/test_provider_anthropic.py @@ -3,8 +3,10 @@ import httpx import pytest from anthropic.types import ( + CitationCharLocation, CitationsDelta, CitationsWebSearchResultLocation, + DocumentBlock, Message, RawContentBlockDeltaEvent, RawContentBlockStartEvent, @@ -13,6 +15,8 @@ TextBlock, TextDelta, Usage, + WebFetchBlock, + WebFetchToolResultBlock, ) from chatlas import ( AssistantTurn, @@ -236,6 +240,183 @@ def test_anthropic_web_search_citations(): assert c.extra is not None # raw payload retained +def test_anthropic_web_fetch_citation_uses_document_index_for_source(): + provider = AnthropicProvider( + model="claude-sonnet-4-5", api_key="dummy", kwargs=None + ) + completion = Message( + id="msg", + type="message", + role="assistant", + model="claude-sonnet-4-5", + content=[ + web_fetch_result("https://first.example", "First document"), + web_fetch_result("https://second.example", "Second document"), + TextBlock( + type="text", + text="Grounded answer", + citations=[ + CitationCharLocation( + type="char_location", + cited_text="second source evidence", + document_index=1, + document_title="Second document", + start_char_index=0, + end_char_index=22, + ) + ], + ), + ], + stop_reason="end_turn", + stop_sequence=None, + usage=Usage(input_tokens=1, output_tokens=1), + ) + + turn = provider._as_turn(completion) + citation = next(c for c in turn.contents if isinstance(c, ContentCitation)) + + assert citation.source is not None + assert citation.source.url == "https://second.example" + assert citation.source.title == "Second document" + + +def test_anthropic_web_fetch_citation_stream_uses_document_index_for_source(): + provider = AnthropicProvider( + model="claude-sonnet-4-5", api_key="dummy", kwargs=None + ) + completion = Message( + id="msg", + type="message", + role="assistant", + model="claude-sonnet-4-5", + content=[ + web_fetch_result("https://first.example", "First document"), + web_fetch_result("https://second.example", "Second document"), + TextBlock( + type="text", + text="Grounded answer", + citations=[ + CitationCharLocation( + type="char_location", + cited_text="second source evidence", + document_index=1, + document_title="Second document", + start_char_index=0, + end_char_index=22, + ) + ], + ), + ], + stop_reason="end_turn", + stop_sequence=None, + usage=Usage(input_tokens=1, output_tokens=1), + ) + + contents = provider.stream_content( + RawContentBlockStopEvent(type="content_block_stop", index=2), + completion, + ) + citation = next(c for c in contents if isinstance(c, ContentCitation)) + + assert citation.source is not None + assert citation.source.url == "https://second.example" + assert citation.source.title == "Second document" + + +def test_anthropic_citation_with_url_keeps_its_own_source(): + provider = AnthropicProvider( + model="claude-sonnet-4-5", api_key="dummy", kwargs=None + ) + completion = Message( + id="msg", + type="message", + role="assistant", + model="claude-sonnet-4-5", + content=[ + TextBlock( + type="text", + text="Grounded answer", + citations=[ + CitationsWebSearchResultLocation( + type="web_search_result_location", + cited_text="search evidence", + encrypted_index="x", + title="Search result", + url="https://search.example", + ) + ], + ) + ], + stop_reason="end_turn", + stop_sequence=None, + usage=Usage(input_tokens=1, output_tokens=1), + ) + + turn = provider._as_turn(completion) + citation = next(c for c in turn.contents if isinstance(c, ContentCitation)) + + assert citation.source is not None + assert citation.source.url == "https://search.example" + assert citation.source.title == "Search result" + + +def test_anthropic_web_fetch_citation_with_invalid_document_index_has_no_source(): + provider = AnthropicProvider( + model="claude-sonnet-4-5", api_key="dummy", kwargs=None + ) + completion = Message( + id="msg", + type="message", + role="assistant", + model="claude-sonnet-4-5", + content=[ + web_fetch_result("https://first.example", "First document"), + TextBlock( + type="text", + text="Grounded answer", + citations=[ + CitationCharLocation( + type="char_location", + cited_text="missing source evidence", + document_index=1, + document_title="Missing document", + start_char_index=0, + end_char_index=23, + ) + ], + ), + ], + stop_reason="end_turn", + stop_sequence=None, + usage=Usage(input_tokens=1, output_tokens=1), + ) + + turn = provider._as_turn(completion) + citation = next(c for c in turn.contents if isinstance(c, ContentCitation)) + + assert citation.source is None + + +def web_fetch_result(url: str, title: str) -> WebFetchToolResultBlock: + return WebFetchToolResultBlock( + type="web_fetch_tool_result", + tool_use_id=f"fetch-{url}", + content=WebFetchBlock( + type="web_fetch_result", + url=url, + content=DocumentBlock( + type="document", + title=title, + source={ + "type": "text", + "media_type": "text/plain", + "data": "", + }, + ), + ), + ) + + def test_anthropic_concurrent_streams_dont_share_state(): """Two streams on one provider must not cross-contaminate citations. From e1ce04b6a900ed96af83272096b416ed54235c48 Mon Sep 17 00:00:00 2001 From: Carson Date: Fri, 7 Aug 2026 16:50:14 -0500 Subject: [PATCH 02/14] feat(provider): thread turns through stream_content/stream_turn/value_turn --- chatlas/_provider.py | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/chatlas/_provider.py b/chatlas/_provider.py index d662c7d9..d0f248a5 100644 --- a/chatlas/_provider.py +++ b/chatlas/_provider.py @@ -279,6 +279,7 @@ def stream_content( self, chunk: ChatCompletionChunkT, completion: Optional[ChatCompletionDictT], + turns: Sequence[Turn] = (), ) -> "Sequence[Content]": """ Content to yield for `chunk`. @@ -289,6 +290,12 @@ def stream_content( single provider instance is shared across forked chats (`Chat.__deepcopy__` keeps `provider` by reference), so several streams can be in flight at once. + + `turns` is the full request history (prior turns plus the newest user + turn) that produced this stream, for providers that need to resolve + content referencing something outside `completion` itself (e.g. + Anthropic's `document_index` citations, which can reference a document + from an earlier turn). Defaults to `()` for callers that don't have it. """ ... @@ -304,6 +311,7 @@ def stream_turn( self, completion: ChatCompletionDictT, has_data_model: bool, + turns: Sequence[Turn] = (), ) -> AssistantTurn[ChatCompletionT]: ... @abstractmethod @@ -311,6 +319,7 @@ def value_turn( self, completion: ChatCompletionT, has_data_model: bool, + turns: Sequence[Turn] = (), ) -> AssistantTurn[ChatCompletionT]: ... @abstractmethod From 9f7ee681fd8a6642f7c137d62506bd34afee4c4f Mon Sep 17 00:00:00 2001 From: Carson Date: Fri, 7 Aug 2026 16:53:18 -0500 Subject: [PATCH 03/14] chore(providers): accept (and ignore) turns in stream_content/stream_turn/value_turn --- chatlas/_provider_google.py | 6 +++--- chatlas/_provider_openai.py | 6 +++--- chatlas/_provider_openai_completions.py | 6 +++--- 3 files changed, 9 insertions(+), 9 deletions(-) diff --git a/chatlas/_provider_google.py b/chatlas/_provider_google.py index 91bbf31d..0984a934 100644 --- a/chatlas/_provider_google.py +++ b/chatlas/_provider_google.py @@ -475,7 +475,7 @@ def _chat_perform_args( return kwargs_full - def stream_content(self, chunk, completion) -> list[Content]: + def stream_content(self, chunk, completion, turns=()) -> list[Content]: candidates = getattr(chunk, "candidates", None) if not candidates: return [] @@ -516,13 +516,13 @@ def stream_merge_chunks(self, completion, chunk): merge_dicts(completion, chunkd), # type: ignore ) - def stream_turn(self, completion, has_data_model): + def stream_turn(self, completion, has_data_model, turns=()): return self._as_turn( completion, has_data_model, ) - def value_turn(self, completion, has_data_model): + def value_turn(self, completion, has_data_model, turns=()): completion = cast("GenerateContentResponseDict", completion.model_dump()) return self._as_turn(completion, has_data_model) diff --git a/chatlas/_provider_openai.py b/chatlas/_provider_openai.py index b3f72564..62973278 100644 --- a/chatlas/_provider_openai.py +++ b/chatlas/_provider_openai.py @@ -381,7 +381,7 @@ def _token_count_args( args_to_keep = ["input", "model", "tools", "text", "tool_choice", "reasoning"] return {arg: kwargs[arg] for arg in args_to_keep if arg in kwargs} - def stream_content(self, chunk, completion) -> list[Content]: + def stream_content(self, chunk, completion, turns=()) -> list[Content]: if chunk.type == "response.output_text.delta": # https://platform.openai.com/docs/api-reference/responses-streaming/response/output_text/delta return [ContentText.model_construct(text=chunk.delta)] @@ -425,10 +425,10 @@ def stream_merge_chunks(self, completion, chunk): return completion - def stream_turn(self, completion, has_data_model): + def stream_turn(self, completion, has_data_model, turns=()): return self._response_as_turn(completion, has_data_model) - def value_turn(self, completion, has_data_model): + def value_turn(self, completion, has_data_model, turns=()): return self._response_as_turn(completion, has_data_model) def value_tokens(self, completion): diff --git a/chatlas/_provider_openai_completions.py b/chatlas/_provider_openai_completions.py index 6da2273f..764207b4 100644 --- a/chatlas/_provider_openai_completions.py +++ b/chatlas/_provider_openai_completions.py @@ -278,7 +278,7 @@ def _chat_perform_args( return kwargs_full - def stream_content(self, chunk, completion) -> list[Content]: + def stream_content(self, chunk, completion, turns=()) -> list[Content]: if not chunk.choices: return [] delta = chunk.choices[0].delta @@ -302,13 +302,13 @@ def stream_merge_chunks(self, completion, chunk): return chunkd return merge_dicts(completion, chunkd) - def stream_turn(self, completion, has_data_model): + def stream_turn(self, completion, has_data_model, turns=()): delta = completion["choices"][0].pop("delta") completion["choices"][0]["message"] = delta completion = ChatCompletion.construct(**completion) return self._response_as_turn(completion, has_data_model) - def value_turn(self, completion, has_data_model): + def value_turn(self, completion, has_data_model, turns=()): return self._response_as_turn(completion, has_data_model) def value_tokens(self, completion): From 035bb42490f921d32e0e2812d02a1855624c9869 Mon Sep 17 00:00:00 2001 From: Carson Date: Fri, 7 Aug 2026 16:57:07 -0500 Subject: [PATCH 04/14] test(anthropic): add failing cross-turn document_index regression test --- tests/test_provider_anthropic.py | 61 ++++++++++++++++++++++++++++++++ 1 file changed, 61 insertions(+) diff --git a/tests/test_provider_anthropic.py b/tests/test_provider_anthropic.py index 626d6099..1e35e64b 100644 --- a/tests/test_provider_anthropic.py +++ b/tests/test_provider_anthropic.py @@ -35,6 +35,7 @@ from chatlas._provider_anthropic import ( _ANTHROPIC_FINISH_REASON_MAP, AnthropicProvider, + anthropic_fetch_result, serving_model, ) from chatlas._provider_anthropic import ( @@ -397,6 +398,66 @@ def test_anthropic_web_fetch_citation_with_invalid_document_index_has_no_source( assert citation.source is None +def test_anthropic_web_fetch_citation_resolves_across_turns(): + provider = AnthropicProvider( + model="claude-sonnet-4-5", api_key="dummy", kwargs=None + ) + + turn_1_fetch = web_fetch_result("https://a.example", "First document") + prior_turns = [ + UserTurn("Look at https://a.example"), + AssistantTurn( + [ + anthropic_fetch_result(turn_1_fetch), + ], + finish_reason="stop", + ), + ] + + completion = Message( + id="msg", + type="message", + role="assistant", + model="claude-sonnet-4-5", + content=[ + web_fetch_result("https://b.example", "Second document"), + TextBlock( + type="text", + text="Comparing both pages", + citations=[ + CitationCharLocation( + type="char_location", + cited_text="claim about the first page", + document_index=0, + document_title="First document", + start_char_index=0, + end_char_index=27, + ), + CitationCharLocation( + type="char_location", + cited_text="claim about the second page", + document_index=1, + document_title="Second document", + start_char_index=28, + end_char_index=56, + ), + ], + ), + ], + stop_reason="end_turn", + stop_sequence=None, + usage=Usage(input_tokens=1, output_tokens=1), + ) + + turn = provider._as_turn(completion, turns=prior_turns) + citations = [c for c in turn.contents if isinstance(c, ContentCitation)] + + assert citations[0].source is not None + assert citations[0].source.url == "https://a.example" + assert citations[1].source is not None + assert citations[1].source.url == "https://b.example" + + def web_fetch_result(url: str, title: str) -> WebFetchToolResultBlock: return WebFetchToolResultBlock( type="web_fetch_tool_result", From 3bccdb65390ac1d3b09ab6eaca2cecdddffc69ea Mon Sep 17 00:00:00 2001 From: Carson Date: Fri, 7 Aug 2026 17:01:13 -0500 Subject: [PATCH 05/14] fix(anthropic): resolve document_index citations across the whole request --- chatlas/_provider_anthropic.py | 76 +++++++++++++++++++++++++--------- 1 file changed, 56 insertions(+), 20 deletions(-) diff --git a/chatlas/_provider_anthropic.py b/chatlas/_provider_anthropic.py index 6e1a4b0f..33b71e50 100644 --- a/chatlas/_provider_anthropic.py +++ b/chatlas/_provider_anthropic.py @@ -593,7 +593,7 @@ def _structured_tool_call(**kwargs: Any): return data_model_tool - def stream_content(self, chunk, completion) -> list[Content]: + def stream_content(self, chunk, completion, turns=()) -> list[Content]: if chunk.type == "content_block_delta": if chunk.delta.type == "text_delta": return [ContentText.model_construct(text=chunk.delta.text)] @@ -619,7 +619,9 @@ def stream_content(self, chunk, completion) -> list[Content]: return list( anthropic_citations( block, - fetch_sources=anthropic_fetch_sources(completion.content), + fetch_sources=anthropic_document_sources( + turns, completion.content + ), ) ) if block.type == "server_tool_use": @@ -679,11 +681,11 @@ def stream_merge_chunks(self, completion, chunk): return completion - def stream_turn(self, completion, has_data_model): - return self._as_turn(completion, has_data_model) + def stream_turn(self, completion, has_data_model, turns=()): + return self._as_turn(completion, has_data_model, turns) - def value_turn(self, completion, has_data_model): - return self._as_turn(completion, has_data_model) + def value_turn(self, completion, has_data_model, turns=()): + return self._as_turn(completion, has_data_model, turns) def value_tokens(self, completion): usage = completion.usage @@ -1041,14 +1043,19 @@ def _anthropic_tool_schema(self, tool: "Tool | ToolBuiltIn") -> "ToolUnionParam" return res - def _as_turn(self, completion: Message, has_data_model=False) -> AssistantTurn: + def _as_turn( + self, + completion: Message, + has_data_model=False, + turns: Sequence[Turn] = (), + ) -> AssistantTurn: finish_reason = normalize_finish_reason(completion.stop_reason) if has_data_model: # Must precede the JSON parse below; see check_finish_reason(). check_finish_reason(finish_reason, "error") contents = [] - fetch_sources = anthropic_fetch_sources(completion.content) + fetch_sources = anthropic_document_sources(turns, completion.content) # Detect which structured output approach was used: # - Old approach: has a _structured_tool_call tool_use block @@ -1553,7 +1560,7 @@ def list_models(self): def anthropic_citations( block: "TextBlock", - fetch_sources: Sequence[WebSource] = (), + fetch_sources: Sequence[Optional[WebSource]] = (), ) -> list[ContentCitation]: """ContentCitations for one fully-accumulated text block.""" out: list[ContentCitation] = [] @@ -1571,10 +1578,12 @@ def anthropic_citations( and not isinstance(document_index, bool) and 0 <= document_index < len(fetch_sources) ): - source = WebSource( - url=fetch_sources[document_index].url, - title=getattr(c, "document_title", None), - ) + resolved = fetch_sources[document_index] + if resolved is not None: + source = WebSource( + url=resolved.url, + title=getattr(c, "document_title", None), + ) out.append( ContentCitation( source=source, @@ -1587,18 +1596,45 @@ def anthropic_citations( return out -def anthropic_fetch_sources(contents: Sequence["ContentBlock"]) -> list[WebSource]: - """Successful web-fetch sources in the order citations reference them.""" +def anthropic_document_sources( + turns: Sequence[Turn], contents: Sequence["ContentBlock"] +) -> list[Optional[WebSource]]: + """Ordered document slots for `document_index` citations in `contents`. + + Anthropic's `document_index` counts every document-shaped content block + across the *whole* request (spanning prior turns), not just this + completion's own fetches -- a `web_fetch_tool_result`'s embedded document + and a user-attached PDF/text document share one index space. `turns` (the + prior history plus the newest user turn) supplies everything that + precedes this completion in that space; `contents` supplies this + completion's own new fetches, appended last. A slot with no representable + URL (e.g. an uploaded PDF) stays `None` so later slots still land on the + right index -- it never fabricates a source. + """ from anthropic.types import WebFetchBlock - out: list[WebSource] = [] + sources: list[Optional[WebSource]] = [] + for turn in turns: + if isinstance(turn, SystemTurn): + continue + for content in turn.contents: + if isinstance(content, ContentToolResponseFetch): + if content.status == "success" and anthropic_replayable(content): + sources.append(WebSource(url=content.url)) + elif isinstance(content, (ContentPDF, ContentDocument)): + sources.append(WebSource(url=content.url) if content.url else None) + elif isinstance(content, ContentUploaded): + if not content.mime_type.startswith("image/"): + sources.append(None) + for block in contents: if block.type != "web_fetch_tool_result": continue - content = block.content - if isinstance(content, WebFetchBlock): - out.append(WebSource(url=content.url, title=content.content.title)) - return out + result = block.content + if isinstance(result, WebFetchBlock): + sources.append(WebSource(url=result.url)) + + return sources def anthropic_server_tool_request( From 8380393e9b8063c3fdb3cf83a2bc25048e120097 Mon Sep 17 00:00:00 2001 From: Carson Date: Fri, 7 Aug 2026 17:07:49 -0500 Subject: [PATCH 06/14] test(anthropic): cover same-turn document-attachment document_index cases --- tests/test_provider_anthropic.py | 109 +++++++++++++++++++++++++++++++ 1 file changed, 109 insertions(+) diff --git a/tests/test_provider_anthropic.py b/tests/test_provider_anthropic.py index 1e35e64b..058ed8f3 100644 --- a/tests/test_provider_anthropic.py +++ b/tests/test_provider_anthropic.py @@ -458,6 +458,115 @@ def test_anthropic_web_fetch_citation_resolves_across_turns(): assert citations[1].source.url == "https://b.example" +def test_anthropic_web_fetch_citation_accounts_for_attached_document(): + provider = AnthropicProvider( + model="claude-sonnet-4-5", api_key="dummy", kwargs=None + ) + + prior_turns = [ + UserTurn( + [ + ContentPDF(data=b"%PDF-1.4 fake", filename="report.pdf"), + "Compare this report with https://site.example", + ] + ), + ] + + completion = Message( + id="msg", + type="message", + role="assistant", + model="claude-sonnet-4-5", + content=[ + web_fetch_result("https://site.example", "Site page"), + TextBlock( + type="text", + text="The report and the site disagree", + citations=[ + CitationCharLocation( + type="char_location", + cited_text="claim from the PDF", + document_index=0, + document_title="report.pdf", + start_char_index=0, + end_char_index=19, + ), + CitationCharLocation( + type="char_location", + cited_text="claim from the site", + document_index=1, + document_title="Site page", + start_char_index=20, + end_char_index=40, + ), + ], + ), + ], + stop_reason="end_turn", + stop_sequence=None, + usage=Usage(input_tokens=1, output_tokens=1), + ) + + turn = provider._as_turn(completion, turns=prior_turns) + citations = [c for c in turn.contents if isinstance(c, ContentCitation)] + + # The PDF has no URL to attribute -- must stay unresolved, not + # borrow the fetched page's URL. + assert citations[0].source is None + # The fetch keeps its own, correctly-offset URL. + assert citations[1].source is not None + assert citations[1].source.url == "https://site.example" + + +def test_anthropic_web_fetch_citation_uses_pdf_url_when_present(): + provider = AnthropicProvider( + model="claude-sonnet-4-5", api_key="dummy", kwargs=None + ) + + prior_turns = [ + UserTurn( + [ + ContentPDF( + url="https://docs.example/report.pdf", filename="report.pdf" + ), + "Summarize this report.", + ] + ), + ] + + completion = Message( + id="msg", + type="message", + role="assistant", + model="claude-sonnet-4-5", + content=[ + TextBlock( + type="text", + text="The report says X", + citations=[ + CitationCharLocation( + type="char_location", + cited_text="claim from the PDF", + document_index=0, + document_title="report.pdf", + start_char_index=0, + end_char_index=18, + ), + ], + ), + ], + stop_reason="end_turn", + stop_sequence=None, + usage=Usage(input_tokens=1, output_tokens=1), + ) + + turn = provider._as_turn(completion, turns=prior_turns) + citation = next(c for c in turn.contents if isinstance(c, ContentCitation)) + + assert citation.source is not None + assert citation.source.url == "https://docs.example/report.pdf" + + def web_fetch_result(url: str, title: str) -> WebFetchToolResultBlock: return WebFetchToolResultBlock( type="web_fetch_tool_result", From 68381ab0a8e23bf77d93348419d29baa9f6be066 Mon Sep 17 00:00:00 2001 From: Carson Date: Fri, 7 Aug 2026 17:11:16 -0500 Subject: [PATCH 07/14] fix(chat): pass request turns into provider turn/content resolution --- chatlas/_chat.py | 18 ++++++++++++++---- 1 file changed, 14 insertions(+), 4 deletions(-) diff --git a/chatlas/_chat.py b/chatlas/_chat.py index 0a664143..c8b87ecd 100644 --- a/chatlas/_chat.py +++ b/chatlas/_chat.py @@ -2926,7 +2926,9 @@ def emit(x: str | Content): if controller.cancelled: break result = self.provider.stream_merge_chunks(result, chunk) - for content in self.provider.stream_content(chunk, result): + for content in self.provider.stream_content( + chunk, result, turns=[*self._turns, user_turn] + ): yield from acc.process_content( content, display_text(content), content_mode, emit ) @@ -2937,6 +2939,7 @@ def emit(x: str | Content): turn = self.provider.stream_turn( result, has_data_model=data_model is not None, + turns=[*self._turns, user_turn], ) emit_image_contents(turn, emit) if echo == "all": @@ -2959,7 +2962,9 @@ def emit(x: str | Content): ) turn = self.provider.value_turn( - response, has_data_model=data_model is not None + response, + has_data_model=data_model is not None, + turns=[*self._turns, user_turn], ) emit_thinking_contents(turn, emit) emit_web_contents(turn, emit) @@ -3079,7 +3084,9 @@ def emit(x: str | Content): if controller.cancelled: break result = self.provider.stream_merge_chunks(result, chunk) - for content in self.provider.stream_content(chunk, result): + for content in self.provider.stream_content( + chunk, result, turns=[*self._turns, user_turn] + ): for item in acc.process_content( content, display_text(content), content_mode, emit ): @@ -3092,6 +3099,7 @@ def emit(x: str | Content): turn = self.provider.stream_turn( result, has_data_model=data_model is not None, + turns=[*self._turns, user_turn], ) emit_image_contents(turn, emit) if echo == "all": @@ -3114,7 +3122,9 @@ def emit(x: str | Content): ) turn = self.provider.value_turn( - response, has_data_model=data_model is not None + response, + has_data_model=data_model is not None, + turns=[*self._turns, user_turn], ) emit_thinking_contents(turn, emit) emit_web_contents(turn, emit) From 8b687214b6dd86bc1737d8326fce7a489aff3ea7 Mon Sep 17 00:00:00 2001 From: Carson Date: Fri, 7 Aug 2026 17:45:52 -0500 Subject: [PATCH 08/14] chore(providers): accept (and ignore) turns in bedrock/snowflake stream_content/stream_turn/value_turn --- chatlas/_provider_bedrock_converse.py | 3 +++ chatlas/_provider_snowflake.py | 6 +++--- 2 files changed, 6 insertions(+), 3 deletions(-) diff --git a/chatlas/_provider_bedrock_converse.py b/chatlas/_provider_bedrock_converse.py index 11a8f6fe..844295c0 100644 --- a/chatlas/_provider_bedrock_converse.py +++ b/chatlas/_provider_bedrock_converse.py @@ -548,6 +548,7 @@ def stream_content( self, chunk: dict, completion: Optional[ConverseAccumulator], + turns: Sequence[Turn] = (), ) -> Sequence[Content]: delta_event = chunk.get("contentBlockDelta") if delta_event is None: @@ -621,6 +622,7 @@ def stream_turn( self, completion: ConverseAccumulator, has_data_model: bool, + turns: Sequence[Turn] = (), ) -> AssistantTurn[ConverseResponseTypeDef]: # Reassemble into a ConverseResponseTypeDef shape so this can share # `_as_turn` with `value_turn` -- matching the pattern @@ -683,6 +685,7 @@ def value_turn( self, completion: ConverseResponseTypeDef, has_data_model: bool, + turns: Sequence[Turn] = (), ) -> AssistantTurn[ConverseResponseTypeDef]: return self._as_turn(completion, has_data_model) diff --git a/chatlas/_provider_snowflake.py b/chatlas/_provider_snowflake.py index 05806234..21f9bc33 100644 --- a/chatlas/_provider_snowflake.py +++ b/chatlas/_provider_snowflake.py @@ -356,7 +356,7 @@ def _complete_request( return req - def stream_content(self, chunk, completion) -> list[Content]: + def stream_content(self, chunk, completion, turns=()) -> list[Content]: if not chunk.choices: return [] delta = chunk.choices[0].delta @@ -437,7 +437,7 @@ def stream_merge_chunks(self, completion, chunk): return completion - def stream_turn(self, completion, has_data_model): + def stream_turn(self, completion, has_data_model, turns=()): import snowflake.core.cortex.inference_service._generated.models as models completion_dict = completion.model_dump() @@ -448,7 +448,7 @@ def stream_turn(self, completion, has_data_model): ) return self._as_turn(completion, has_data_model) - def value_turn(self, completion, has_data_model): + def value_turn(self, completion, has_data_model, turns=()): return self._as_turn(completion, has_data_model) def value_tokens(self, completion): From b84b157627dbc18791617151be7390f729382880 Mon Sep 17 00:00:00 2001 From: Carson Date: Fri, 7 Aug 2026 18:49:21 -0500 Subject: [PATCH 09/14] fix(chat): preserve request turns during streaming --- chatlas/_chat.py | 30 ++++++++++++-------------- tests/test_echo_display.py | 10 ++++----- tests/test_otel.py | 12 +++++++---- tests/test_provider_stream_contract.py | 30 ++++++++++++++++++++++---- tests/test_stream_thinking.py | 6 +++--- 5 files changed, 56 insertions(+), 32 deletions(-) diff --git a/chatlas/_chat.py b/chatlas/_chat.py index c8b87ecd..fb56cd6c 100644 --- a/chatlas/_chat.py +++ b/chatlas/_chat.py @@ -2868,9 +2868,8 @@ def _submit_turns( if any(isinstance(x, Tool) and x._is_async for x in self._tools.values()): raise ValueError("Cannot use async tools in a synchronous chat") - chat_span = start_chat_span( - self.provider, [*self._turns, user_turn], _otel_parent - ) + request_turns = [*self._turns, user_turn] + chat_span = start_chat_span(self.provider, request_turns, _otel_parent) try: def emit(x: str | Content): @@ -2905,7 +2904,7 @@ def emit(x: str | Content): with activate_span(chat_span): response = self.provider.chat_perform( stream=True, - turns=[*self._turns, user_turn], + turns=request_turns, tools=self._tools, data_model=data_model, kwargs=all_kwargs, @@ -2927,7 +2926,7 @@ def emit(x: str | Content): break result = self.provider.stream_merge_chunks(result, chunk) for content in self.provider.stream_content( - chunk, result, turns=[*self._turns, user_turn] + chunk, result, turns=request_turns ): yield from acc.process_content( content, display_text(content), content_mode, emit @@ -2939,7 +2938,7 @@ def emit(x: str | Content): turn = self.provider.stream_turn( result, has_data_model=data_model is not None, - turns=[*self._turns, user_turn], + turns=request_turns, ) emit_image_contents(turn, emit) if echo == "all": @@ -2955,7 +2954,7 @@ def emit(x: str | Content): with activate_span(chat_span): response = self.provider.chat_perform( stream=False, - turns=[*self._turns, user_turn], + turns=request_turns, tools=self._tools, data_model=data_model, kwargs=all_kwargs, @@ -2964,7 +2963,7 @@ def emit(x: str | Content): turn = self.provider.value_turn( response, has_data_model=data_model is not None, - turns=[*self._turns, user_turn], + turns=request_turns, ) emit_thinking_contents(turn, emit) emit_web_contents(turn, emit) @@ -3026,9 +3025,8 @@ async def _submit_turns_async( *, controller: StreamController, ) -> AsyncGenerator[str | Content, None]: - chat_span = start_chat_span( - self.provider, [*self._turns, user_turn], _otel_parent - ) + request_turns = [*self._turns, user_turn] + chat_span = start_chat_span(self.provider, request_turns, _otel_parent) try: def emit(x: str | Content): @@ -3063,7 +3061,7 @@ def emit(x: str | Content): with activate_span(chat_span): response = await self.provider.chat_perform_async( stream=True, - turns=[*self._turns, user_turn], + turns=request_turns, tools=self._tools, data_model=data_model, kwargs=all_kwargs, @@ -3085,7 +3083,7 @@ def emit(x: str | Content): break result = self.provider.stream_merge_chunks(result, chunk) for content in self.provider.stream_content( - chunk, result, turns=[*self._turns, user_turn] + chunk, result, turns=request_turns ): for item in acc.process_content( content, display_text(content), content_mode, emit @@ -3099,7 +3097,7 @@ def emit(x: str | Content): turn = self.provider.stream_turn( result, has_data_model=data_model is not None, - turns=[*self._turns, user_turn], + turns=request_turns, ) emit_image_contents(turn, emit) if echo == "all": @@ -3115,7 +3113,7 @@ def emit(x: str | Content): with activate_span(chat_span): response = await self.provider.chat_perform_async( stream=False, - turns=[*self._turns, user_turn], + turns=request_turns, tools=self._tools, data_model=data_model, kwargs=all_kwargs, @@ -3124,7 +3122,7 @@ def emit(x: str | Content): turn = self.provider.value_turn( response, has_data_model=data_model is not None, - turns=[*self._turns, user_turn], + turns=request_turns, ) emit_thinking_contents(turn, emit) emit_web_contents(turn, emit) diff --git a/tests/test_echo_display.py b/tests/test_echo_display.py index 3c48f93c..5d4c0b57 100644 --- a/tests/test_echo_display.py +++ b/tests/test_echo_display.py @@ -1512,16 +1512,16 @@ async def gen(): return gen() return EchoCompletion(contents) - def stream_content(self, chunk: FakeChunk, completion) -> list[Content]: + def stream_content(self, chunk: FakeChunk, completion, turns=()) -> list[Content]: return [chunk.content] if chunk.content is not None else [] def stream_merge_chunks(self, completion, chunk): return completion or {} - def stream_turn(self, completion, has_data_model): + def stream_turn(self, completion, has_data_model, turns=()): return self._turn_from_current() - def value_turn(self, completion, has_data_model): + def value_turn(self, completion, has_data_model, turns=()): return self._turn_from_current() def _turn_from_current(self) -> AssistantTurn: @@ -1578,11 +1578,11 @@ class RaisingProvider(EchoProvider): _calls = 0 - def stream_content(self, chunk: FakeChunk, completion) -> list[Content]: + def stream_content(self, chunk: FakeChunk, completion, turns=()) -> list[Content]: self._calls += 1 if self._calls > 1: raise RuntimeError("provider blew up mid-stream") - return super().stream_content(chunk, completion) + return super().stream_content(chunk, completion, turns) def make_chat( diff --git a/tests/test_otel.py b/tests/test_otel.py index 5aa3c17b..fa3f4656 100644 --- a/tests/test_otel.py +++ b/tests/test_otel.py @@ -415,12 +415,14 @@ def gen(): return gen() chat.provider.chat_perform = streaming_perform # type: ignore[method-assign] - chat.provider.stream_content = lambda chunk, completion: [ContentText(text="hi")] # type: ignore[method-assign] + chat.provider.stream_content = lambda chunk, completion, turns=(): [ + ContentText(text="hi") + ] # type: ignore[method-assign] chat.provider.stream_merge_chunks = ( # type: ignore[method-assign] lambda result, chunk: chunk ) chat.provider.stream_turn = ( # type: ignore[method-assign] - lambda completion, has_data_model: AssistantTurn("hi") + lambda completion, has_data_model, turns=(): AssistantTurn("hi") ) list(chat.stream("Say hello.")) @@ -448,12 +450,14 @@ async def gen(): return gen() chat.provider.chat_perform_async = streaming_perform_async # type: ignore[method-assign] - chat.provider.stream_content = lambda chunk, completion: [ContentText(text="hi")] # type: ignore[method-assign] + chat.provider.stream_content = lambda chunk, completion, turns=(): [ + ContentText(text="hi") + ] # type: ignore[method-assign] chat.provider.stream_merge_chunks = ( # type: ignore[method-assign] lambda result, chunk: chunk ) chat.provider.stream_turn = ( # type: ignore[method-assign] - lambda completion, has_data_model: AssistantTurn("hi") + lambda completion, has_data_model, turns=(): AssistantTurn("hi") ) chunks = [] diff --git a/tests/test_provider_stream_contract.py b/tests/test_provider_stream_contract.py index 1039c2e2..83058ddf 100644 --- a/tests/test_provider_stream_contract.py +++ b/tests/test_provider_stream_contract.py @@ -37,14 +37,16 @@ def __init__(self, chunks: list[Chunk]): super().__init__(name="fake", model="fake-model") self._chunks = chunks self.seen_completions: list[Optional[dict]] = [] + self.seen_turns: list[list[tuple[str, str]]] = [] def stream_merge_chunks(self, completion, chunk) -> dict: merged = dict(completion or {"text": ""}) merged["text"] += chunk.text return merged - def stream_content(self, chunk, completion) -> list[Content]: + def stream_content(self, chunk, completion, turns=()) -> list[Content]: self.seen_completions.append(completion) + self.seen_turns.append([(turn.role, turn.text) for turn in turns]) out: list[Content] = [] if chunk.text: out.append(ContentText.model_construct(text=chunk.text)) @@ -68,7 +70,8 @@ async def gen(): return gen() raise NotImplementedError - def stream_turn(self, completion, has_data_model): + def stream_turn(self, completion, has_data_model, turns=()): + self.seen_turns.append([(turn.role, turn.text) for turn in turns]) return AssistantTurn( contents=[ContentText.model_construct(text=completion["text"])], tokens=None, @@ -78,7 +81,7 @@ def stream_turn(self, completion, has_data_model): def list_models(self): return [] - def value_turn(self, completion, has_data_model): + def value_turn(self, completion, has_data_model, turns=()): raise NotImplementedError def value_tokens(self, completion): @@ -130,11 +133,19 @@ def test_stream_content_sees_completion_including_current_chunk(): assert [c["text"] for c in provider.seen_completions if c] == ["a", "ab", "abc"] +def test_stream_content_receives_exact_request_turns(): + provider = AccumulatingProvider([Chunk("a"), Chunk("b")]) + chat = Chat(provider=provider) + + assert "".join(chat.stream("hi")) == "ab" + assert provider.seen_turns == [[("user", "hi")]] * 3 + + def test_multiple_contents_from_one_chunk_are_all_processed(): provider = AccumulatingProvider([]) chat = Chat(provider=provider) # Bypass chat_perform so this test owns the chunk -> content mapping - provider.stream_content = lambda chunk, completion: [ # type: ignore[method-assign] + provider.stream_content = lambda chunk, completion, turns=(): [ # type: ignore[method-assign] ContentThinkingDelta(thinking="why"), ContentText.model_construct(text="what"), ] @@ -156,3 +167,14 @@ async def test_stream_content_sees_completion_including_current_chunk_async(): assert "".join(out) == "ab" assert [c["text"] for c in provider.seen_completions if c] == ["a", "ab"] + + +@pytest.mark.asyncio +async def test_stream_content_receives_exact_request_turns_async(): + provider = AccumulatingProvider([Chunk("a"), Chunk("b")]) + chat = Chat(provider=provider) + + out = [x async for x in await chat.stream_async("hi")] + + assert "".join(out) == "ab" + assert provider.seen_turns == [[("user", "hi")]] * 3 diff --git a/tests/test_stream_thinking.py b/tests/test_stream_thinking.py index 64fcaee2..95a0eafd 100644 --- a/tests/test_stream_thinking.py +++ b/tests/test_stream_thinking.py @@ -42,20 +42,20 @@ async def _gen(): return _gen() raise NotImplementedError - def stream_content(self, chunk, completion) -> list[Content]: + def stream_content(self, chunk, completion, turns=()) -> list[Content]: return [chunk.content] if chunk.content is not None else [] def stream_merge_chunks(self, completion, chunk): return completion or {} - def stream_turn(self, completion, has_data_model): + def stream_turn(self, completion, has_data_model, turns=()): return AssistantTurn( contents=[ContentText.model_construct(text="response")], tokens=None, completion=None, ) - def value_turn(self, completion, has_data_model): + def value_turn(self, completion, has_data_model, turns=()): raise NotImplementedError def value_tokens(self, completion): From 23221b356bcde3ee8cfe99f783e7da3b50fdeb6b Mon Sep 17 00:00:00 2001 From: "github-actions[bot]" Date: Sat, 8 Aug 2026 00:04:17 +0000 Subject: [PATCH 10/14] chore: update provider types and pricing data --- chatlas/data/prices.json | 19153 ++++++++++++++------------- chatlas/types/anthropic/_submit.py | 2 - 2 files changed, 9579 insertions(+), 9576 deletions(-) diff --git a/chatlas/data/prices.json b/chatlas/data/prices.json index 1d263a28..dc5f0b89 100644 --- a/chatlas/data/prices.json +++ b/chatlas/data/prices.json @@ -1,9574 +1,9579 @@ -[ - { - "provider": "AWS/Bedrock", - "model": "ai21.j2-mid-v1", - "variant": "", - "input": 12.5, - "output": 12.5 - }, - { - "provider": "AWS/Bedrock", - "model": "ai21.j2-ultra-v1", - "variant": "", - "input": 18.8, - "output": 18.8 - }, - { - "provider": "AWS/Bedrock", - "model": "ai21.jamba-1-5-large-v1:0", - "variant": "", - "input": 2, - "output": 8 - }, - { - "provider": "AWS/Bedrock", - "model": "ai21.jamba-1-5-mini-v1:0", - "variant": "", - "input": 0.2, - "output": 0.4 - }, - { - "provider": "AWS/Bedrock", - "model": "ai21.jamba-instruct-v1:0", - "variant": "", - "input": 0.5, - "output": 0.7 - }, - { - "provider": "AWS/Bedrock", - "model": "amazon.nova-2-lite-v1:0", - "variant": "", - "input": 0.3, - "output": 2.5, - "cached_input": 0.075 - }, - { - "provider": "AWS/Bedrock", - "model": "amazon.nova-2-multimodal-embeddings-v1:0", - "variant": "", - "input": 0.135, - "output": 0 - }, - { - "provider": "AWS/Bedrock", - "model": "amazon.nova-2-pro-preview-20251202-v1:0", - "variant": "", - "input": 2.1875, - "output": 17.5, - "cached_input": 0.5469 - }, - { - "provider": "AWS/Bedrock", - "model": "amazon.nova-lite-v1:0", - "variant": "", - "input": 0.06, - "output": 0.24 - }, - { - "provider": "AWS/Bedrock", - "model": "amazon.nova-micro-v1:0", - "variant": "", - "input": 0.035, - "output": 0.14 - }, - { - "provider": "AWS/Bedrock", - "model": "amazon.nova-pro-v1:0", - "variant": "", - "input": 0.8, - "output": 3.2 - }, - { - "provider": "AWS/Bedrock", - "model": "amazon.titan-embed-g1-text-02", - "variant": "", - "input": 0.1, - "output": 0 - }, - { - "provider": "AWS/Bedrock", - "model": "amazon.titan-embed-image-v1", - "variant": "", - "input": 0.8, - "output": 0 - }, - { - "provider": "AWS/Bedrock", - "model": "amazon.titan-embed-text-v1", - "variant": "", - "input": 0.1, - "output": 0 - }, - { - "provider": "AWS/Bedrock", - "model": "amazon.titan-embed-text-v2:0", - "variant": "", - "input": 0.02, - "output": 0 - }, - { - "provider": "AWS/Bedrock", - "model": "amazon.titan-text-express-v1", - "variant": "", - "input": 1.3, - "output": 1.7 - }, - { - "provider": "AWS/Bedrock", - "model": "amazon.titan-text-lite-v1", - "variant": "", - "input": 0.3, - "output": 0.4 - }, - { - "provider": "AWS/Bedrock", - "model": "amazon.titan-text-premier-v1:0", - "variant": "", - "input": 0.5, - "output": 1.5 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-3-5-haiku-20241022-v1:0", - "variant": "", - "input": 0.8, - "output": 4, - "cached_input": 0.08 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-3-5-sonnet-20240620-v1:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-3-5-sonnet-20240620-v1:0", - "variant": "above_200k_tokens", - "input": 6, - "output": 30, - "cached_input": 0.6 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-3-5-sonnet-20241022-v2:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-3-5-sonnet-20241022-v2:0", - "variant": "above_200k_tokens", - "input": 6, - "output": 30, - "cached_input": 0.6 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-3-7-sonnet-20240620-v1:0", - "variant": "", - "input": 3.6, - "output": 18, - "cached_input": 0.36 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-3-7-sonnet-20250219-v1:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-3-haiku-20240307-v1:0", - "variant": "", - "input": 0.25, - "output": 1.25, - "cached_input": 0.025 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-3-opus-20240229-v1:0", - "variant": "", - "input": 15, - "output": 75, - "cached_input": 1.5 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-3-sonnet-20240229-v1:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-fable-5", - "variant": "", - "input": 10, - "output": 50, - "cached_input": 1 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-haiku-4-5-20251001-v1:0", - "variant": "", - "input": 1, - "output": 5, - "cached_input": 0.1 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-haiku-4-5@20251001", - "variant": "", - "input": 1, - "output": 5, - "cached_input": 0.1 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-instant-v1", - "variant": "", - "input": 0.8, - "output": 2.4 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-opus-4-1-20250805-v1:0", - "variant": "", - "input": 15, - "output": 75, - "cached_input": 1.5 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-opus-4-20250514-v1:0", - "variant": "", - "input": 15, - "output": 75, - "cached_input": 1.5 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-opus-4-5-20251101-v1:0", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-opus-4-6-v1", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-opus-4-7", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-opus-4-8", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-opus-5", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-sonnet-4-20250514-v1:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-sonnet-4-20250514-v1:0", - "variant": "above_200k_tokens", - "input": 6, - "output": 22.5, - "cached_input": 0.6 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", - "variant": "above_200k_tokens", - "input": 6, - "output": 22.5, - "cached_input": 0.6 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-sonnet-4-6", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-sonnet-5", - "variant": "", - "input": 2, - "output": 10, - "cached_input": 0.2 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-v1", - "variant": "", - "input": 8, - "output": 24 - }, - { - "provider": "AWS/Bedrock", - "model": "anthropic.claude-v2:1", - "variant": "", - "input": 8, - "output": 24 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-northeast-1/anthropic.claude-instant-v1", - "variant": "", - "input": 2.23, - "output": 7.55 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-northeast-1/anthropic.claude-v1", - "variant": "", - "input": 8, - "output": 24 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-northeast-1/anthropic.claude-v2:1", - "variant": "", - "input": 8, - "output": 24 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-northeast-1/deepseek.v3.2", - "variant": "", - "input": 0.74, - "output": 2.22 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-northeast-1/minimax.minimax-m2.1", - "variant": "", - "input": 0.36, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-northeast-1/minimax.minimax-m2.5", - "variant": "", - "input": 0.36, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-northeast-1/moonshotai.kimi-k2-thinking", - "variant": "", - "input": 0.73, - "output": 3.03 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-northeast-1/moonshotai.kimi-k2.5", - "variant": "", - "input": 0.72, - "output": 3.6 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-northeast-1/qwen.qwen3-coder-next", - "variant": "", - "input": 0.6, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-south-1/deepseek.v3.2", - "variant": "", - "input": 0.74, - "output": 2.22 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-south-1/meta.llama3-70b-instruct-v1:0", - "variant": "", - "input": 3.18, - "output": 4.2 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-south-1/meta.llama3-8b-instruct-v1:0", - "variant": "", - "input": 0.36, - "output": 0.72 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-south-1/minimax.minimax-m2.1", - "variant": "", - "input": 0.36, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-south-1/minimax.minimax-m2.5", - "variant": "", - "input": 0.36, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-south-1/moonshotai.kimi-k2-thinking", - "variant": "", - "input": 0.71, - "output": 2.94 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-south-1/moonshotai.kimi-k2.5", - "variant": "", - "input": 0.72, - "output": 3.6 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-south-1/qwen.qwen3-coder-next", - "variant": "", - "input": 0.6, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-southeast-2/minimax.minimax-m2.5", - "variant": "", - "input": 0.309, - "output": 1.236 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-southeast-3/deepseek.v3.2", - "variant": "", - "input": 0.74, - "output": 2.22 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-southeast-3/minimax.minimax-m2.1", - "variant": "", - "input": 0.36, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-southeast-3/minimax.minimax-m2.5", - "variant": "", - "input": 0.36, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-southeast-3/moonshotai.kimi-k2.5", - "variant": "", - "input": 0.72, - "output": 3.6 - }, - { - "provider": "AWS/Bedrock", - "model": "ap-southeast-3/qwen.qwen3-coder-next", - "variant": "", - "input": 0.6, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "apac.amazon.nova-2-lite-v1:0", - "variant": "", - "input": 0.33, - "output": 2.75, - "cached_input": 0.0825 - }, - { - "provider": "AWS/Bedrock", - "model": "apac.amazon.nova-2-pro-preview-20251202-v1:0", - "variant": "", - "input": 2.1875, - "output": 17.5, - "cached_input": 0.5469 - }, - { - "provider": "AWS/Bedrock", - "model": "apac.amazon.nova-lite-v1:0", - "variant": "", - "input": 0.063, - "output": 0.252 - }, - { - "provider": "AWS/Bedrock", - "model": "apac.amazon.nova-micro-v1:0", - "variant": "", - "input": 0.037, - "output": 0.148 - }, - { - "provider": "AWS/Bedrock", - "model": "apac.amazon.nova-pro-v1:0", - "variant": "", - "input": 0.84, - "output": 3.36 - }, - { - "provider": "AWS/Bedrock", - "model": "apac.anthropic.claude-3-5-sonnet-20240620-v1:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "apac.anthropic.claude-3-5-sonnet-20241022-v2:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "apac.anthropic.claude-3-haiku-20240307-v1:0", - "variant": "", - "input": 0.25, - "output": 1.25, - "cached_input": 0.025 - }, - { - "provider": "AWS/Bedrock", - "model": "apac.anthropic.claude-3-sonnet-20240229-v1:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "apac.anthropic.claude-haiku-4-5-20251001-v1:0", - "variant": "", - "input": 1.1, - "output": 5.5, - "cached_input": 0.11 - }, - { - "provider": "AWS/Bedrock", - "model": "apac.anthropic.claude-sonnet-4-20250514-v1:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "apac.anthropic.claude-sonnet-4-20250514-v1:0", - "variant": "above_200k_tokens", - "input": 6, - "output": 22.5, - "cached_input": 0.6 - }, - { - "provider": "AWS/Bedrock", - "model": "au.anthropic.claude-haiku-4-5-20251001-v1:0", - "variant": "", - "input": 1.1, - "output": 5.5, - "cached_input": 0.11 - }, - { - "provider": "AWS/Bedrock", - "model": "au.anthropic.claude-opus-4-6-v1", - "variant": "", - "input": 5.5, - "output": 27.5, - "cached_input": 0.55 - }, - { - "provider": "AWS/Bedrock", - "model": "au.anthropic.claude-opus-4-7", - "variant": "", - "input": 5.5, - "output": 27.5, - "cached_input": 0.55 - }, - { - "provider": "AWS/Bedrock", - "model": "au.anthropic.claude-opus-4-8", - "variant": "", - "input": 5.5, - "output": 27.5, - "cached_input": 0.55 - }, - { - "provider": "AWS/Bedrock", - "model": "au.anthropic.claude-opus-5", - "variant": "", - "input": 5.5, - "output": 27.5, - "cached_input": 0.55 - }, - { - "provider": "AWS/Bedrock", - "model": "au.anthropic.claude-sonnet-4-5-20250929-v1:0", - "variant": "", - "input": 3.3, - "output": 16.5, - "cached_input": 0.33 - }, - { - "provider": "AWS/Bedrock", - "model": "au.anthropic.claude-sonnet-4-5-20250929-v1:0", - "variant": "above_200k_tokens", - "input": 6.6, - "output": 24.75, - "cached_input": 0.66 - }, - { - "provider": "AWS/Bedrock", - "model": "au.anthropic.claude-sonnet-4-6", - "variant": "", - "input": 3.3, - "output": 16.5, - "cached_input": 0.33 - }, - { - "provider": "AWS/Bedrock", - "model": "au.anthropic.claude-sonnet-5", - "variant": "", - "input": 2.2, - "output": 11, - "cached_input": 0.22 - }, - { - "provider": "AWS/Bedrock", - "model": "ca-central-1/meta.llama3-70b-instruct-v1:0", - "variant": "", - "input": 3.05, - "output": 4.03 - }, - { - "provider": "AWS/Bedrock", - "model": "ca-central-1/meta.llama3-8b-instruct-v1:0", - "variant": "", - "input": 0.35, - "output": 0.69 - }, - { - "provider": "AWS/Bedrock", - "model": "claude-sonnet-4-5-20250929-v1:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "claude-sonnet-4-5-20250929-v1:0", - "variant": "above_200k_tokens", - "input": 6, - "output": 22.5, - "cached_input": 0.6 - }, - { - "provider": "AWS/Bedrock", - "model": "cohere.command-light-text-v14", - "variant": "", - "input": 0.3, - "output": 0.6 - }, - { - "provider": "AWS/Bedrock", - "model": "cohere.command-r-plus-v1:0", - "variant": "", - "input": 3, - "output": 15 - }, - { - "provider": "AWS/Bedrock", - "model": "cohere.command-r-v1:0", - "variant": "", - "input": 0.5, - "output": 1.5 - }, - { - "provider": "AWS/Bedrock", - "model": "cohere.command-text-v14", - "variant": "", - "input": 1.5, - "output": 2 - }, - { - "provider": "AWS/Bedrock", - "model": "cohere.embed-english-v3", - "variant": "", - "input": 0.1, - "output": 0 - }, - { - "provider": "AWS/Bedrock", - "model": "cohere.embed-multilingual-v3", - "variant": "", - "input": 0.1, - "output": 0 - }, - { - "provider": "AWS/Bedrock", - "model": "cohere.embed-v4:0", - "variant": "", - "input": 0.12, - "output": 0 - }, - { - "provider": "AWS/Bedrock", - "model": "deepseek.v3-v1:0", - "variant": "", - "input": 0.58, - "output": 1.68 - }, - { - "provider": "AWS/Bedrock", - "model": "deepseek.v3.2", - "variant": "", - "input": 0.62, - "output": 1.85 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-central-1/anthropic.claude-instant-v1", - "variant": "", - "input": 2.48, - "output": 8.38 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-central-1/anthropic.claude-v1", - "variant": "", - "input": 8, - "output": 24 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-central-1/anthropic.claude-v2:1", - "variant": "", - "input": 8, - "output": 24 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-central-1/minimax.minimax-m2.1", - "variant": "", - "input": 0.36, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-central-1/minimax.minimax-m2.5", - "variant": "", - "input": 0.36, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-central-1/qwen.qwen3-coder-next", - "variant": "", - "input": 0.6, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-north-1/deepseek.v3.2", - "variant": "", - "input": 0.74, - "output": 2.22 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-north-1/minimax.minimax-m2.1", - "variant": "", - "input": 0.36, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-north-1/minimax.minimax-m2.5", - "variant": "", - "input": 0.36, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-north-1/moonshotai.kimi-k2.5", - "variant": "", - "input": 0.72, - "output": 3.6 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-south-1/minimax.minimax-m2.1", - "variant": "", - "input": 0.36, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-south-1/minimax.minimax-m2.5", - "variant": "", - "input": 0.36, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-south-1/qwen.qwen3-coder-next", - "variant": "", - "input": 0.6, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-west-1/meta.llama3-70b-instruct-v1:0", - "variant": "", - "input": 2.86, - "output": 3.78 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-west-1/meta.llama3-8b-instruct-v1:0", - "variant": "", - "input": 0.32, - "output": 0.65 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-west-1/minimax.minimax-m2.1", - "variant": "", - "input": 0.36, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-west-1/minimax.minimax-m2.5", - "variant": "", - "input": 0.36, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-west-1/qwen.qwen3-coder-next", - "variant": "", - "input": 0.6, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-west-2/meta.llama3-70b-instruct-v1:0", - "variant": "", - "input": 3.45, - "output": 4.55 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-west-2/meta.llama3-8b-instruct-v1:0", - "variant": "", - "input": 0.39, - "output": 0.78 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-west-2/minimax.minimax-m2.1", - "variant": "", - "input": 0.47, - "output": 1.86 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-west-2/minimax.minimax-m2.5", - "variant": "", - "input": 0.47, - "output": 1.86 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-west-2/qwen.qwen3-coder-next", - "variant": "", - "input": 0.78, - "output": 1.86 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-west-3/mistral.mistral-7b-instruct-v0:2", - "variant": "", - "input": 0.2, - "output": 0.26 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-west-3/mistral.mistral-large-2402-v1:0", - "variant": "", - "input": 10.4, - "output": 31.2 - }, - { - "provider": "AWS/Bedrock", - "model": "eu-west-3/mistral.mixtral-8x7b-instruct-v0:1", - "variant": "", - "input": 0.59, - "output": 0.91 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.amazon.nova-2-lite-v1:0", - "variant": "", - "input": 0.33, - "output": 2.75, - "cached_input": 0.0825 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.amazon.nova-2-pro-preview-20251202-v1:0", - "variant": "", - "input": 2.1875, - "output": 17.5, - "cached_input": 0.5469 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.amazon.nova-lite-v1:0", - "variant": "", - "input": 0.078, - "output": 0.312 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.amazon.nova-micro-v1:0", - "variant": "", - "input": 0.046, - "output": 0.184 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.amazon.nova-pro-v1:0", - "variant": "", - "input": 1.05, - "output": 4.2 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-3-5-haiku-20241022-v1:0", - "variant": "", - "input": 0.25, - "output": 1.25, - "cached_input": 0.025 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-3-5-sonnet-20240620-v1:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-3-5-sonnet-20241022-v2:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-3-7-sonnet-20250219-v1:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-3-haiku-20240307-v1:0", - "variant": "", - "input": 0.25, - "output": 1.25, - "cached_input": 0.025 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-3-opus-20240229-v1:0", - "variant": "", - "input": 15, - "output": 75, - "cached_input": 1.5 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-3-sonnet-20240229-v1:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-fable-5", - "variant": "", - "input": 11, - "output": 55, - "cached_input": 1.1 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-haiku-4-5-20251001-v1:0", - "variant": "", - "input": 1.1, - "output": 5.5, - "cached_input": 0.11 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-opus-4-1-20250805-v1:0", - "variant": "", - "input": 15, - "output": 75, - "cached_input": 1.5 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-opus-4-20250514-v1:0", - "variant": "", - "input": 15, - "output": 75, - "cached_input": 1.5 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-opus-4-5-20251101-v1:0", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-opus-4-6-v1", - "variant": "", - "input": 5.5, - "output": 27.5, - "cached_input": 0.55 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-opus-4-7", - "variant": "", - "input": 5.5, - "output": 27.5, - "cached_input": 0.55 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-opus-4-8", - "variant": "", - "input": 5.5, - "output": 27.5, - "cached_input": 0.55 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-opus-5", - "variant": "", - "input": 5.5, - "output": 27.5, - "cached_input": 0.55 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-sonnet-4-20250514-v1:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-sonnet-4-20250514-v1:0", - "variant": "above_200k_tokens", - "input": 6, - "output": 22.5, - "cached_input": 0.6 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0", - "variant": "", - "input": 3.3, - "output": 16.5, - "cached_input": 0.33 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0", - "variant": "above_200k_tokens", - "input": 6.6, - "output": 24.75, - "cached_input": 0.66 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-sonnet-4-6", - "variant": "", - "input": 3.3, - "output": 16.5, - "cached_input": 0.33 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.anthropic.claude-sonnet-5", - "variant": "", - "input": 2.2, - "output": 11, - "cached_input": 0.22 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.deepseek.v3.2", - "variant": "", - "input": 0.74, - "output": 2.22 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.meta.llama3-2-1b-instruct-v1:0", - "variant": "", - "input": 0.13, - "output": 0.13 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.meta.llama3-2-3b-instruct-v1:0", - "variant": "", - "input": 0.19, - "output": 0.19 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.mistral.pixtral-large-2502-v1:0", - "variant": "", - "input": 2, - "output": 6 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.twelvelabs.marengo-embed-2-7-v1:0", - "variant": "", - "input": 70, - "output": 0 - }, - { - "provider": "AWS/Bedrock", - "model": "eu.twelvelabs.pegasus-1-2-v1:0", - "variant": "", - "output": 7.5 - }, - { - "provider": "AWS/Bedrock", - "model": "global.amazon.nova-2-lite-v1:0", - "variant": "", - "input": 0.3, - "output": 2.5, - "cached_input": 0.075 - }, - { - "provider": "AWS/Bedrock", - "model": "global.anthropic.claude-fable-5", - "variant": "", - "input": 10, - "output": 50, - "cached_input": 1 - }, - { - "provider": "AWS/Bedrock", - "model": "global.anthropic.claude-haiku-4-5-20251001-v1:0", - "variant": "", - "input": 1, - "output": 5, - "cached_input": 0.1 - }, - { - "provider": "AWS/Bedrock", - "model": "global.anthropic.claude-opus-4-5-20251101-v1:0", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "AWS/Bedrock", - "model": "global.anthropic.claude-opus-4-6-v1", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "AWS/Bedrock", - "model": "global.anthropic.claude-opus-4-7", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "AWS/Bedrock", - "model": "global.anthropic.claude-opus-4-8", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "AWS/Bedrock", - "model": "global.anthropic.claude-opus-5", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "AWS/Bedrock", - "model": "global.anthropic.claude-sonnet-4-20250514-v1:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "global.anthropic.claude-sonnet-4-20250514-v1:0", - "variant": "above_200k_tokens", - "input": 6, - "output": 22.5, - "cached_input": 0.6 - }, - { - "provider": "AWS/Bedrock", - "model": "global.anthropic.claude-sonnet-4-5-20250929-v1:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "global.anthropic.claude-sonnet-4-5-20250929-v1:0", - "variant": "above_200k_tokens", - "input": 6, - "output": 22.5, - "cached_input": 0.6 - }, - { - "provider": "AWS/Bedrock", - "model": "global.anthropic.claude-sonnet-4-6", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "global.anthropic.claude-sonnet-5", - "variant": "", - "input": 2, - "output": 10, - "cached_input": 0.2 - }, - { - "provider": "AWS/Bedrock", - "model": "google.gemma-3-12b-it", - "variant": "", - "input": 0.09, - "output": 0.29 - }, - { - "provider": "AWS/Bedrock", - "model": "google.gemma-3-27b-it", - "variant": "", - "input": 0.23, - "output": 0.38 - }, - { - "provider": "AWS/Bedrock", - "model": "google.gemma-3-4b-it", - "variant": "", - "input": 0.04, - "output": 0.08 - }, - { - "provider": "AWS/Bedrock", - "model": "google.gemma-4-26b-a4b", - "variant": "", - "input": 0.13, - "output": 0.4 - }, - { - "provider": "AWS/Bedrock", - "model": "google.gemma-4-31b", - "variant": "", - "input": 0.14, - "output": 0.4 - }, - { - "provider": "AWS/Bedrock", - "model": "google.gemma-4-e2b", - "variant": "", - "input": 0.04, - "output": 0.08 - }, - { - "provider": "AWS/Bedrock", - "model": "invoke/anthropic.claude-3-5-sonnet-20240620-v1:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "jp.anthropic.claude-haiku-4-5-20251001-v1:0", - "variant": "", - "input": 1.1, - "output": 5.5, - "cached_input": 0.11 - }, - { - "provider": "AWS/Bedrock", - "model": "jp.anthropic.claude-opus-4-7", - "variant": "", - "input": 5.5, - "output": 27.5, - "cached_input": 0.55 - }, - { - "provider": "AWS/Bedrock", - "model": "jp.anthropic.claude-opus-4-8", - "variant": "", - "input": 5.5, - "output": 27.5, - "cached_input": 0.55 - }, - { - "provider": "AWS/Bedrock", - "model": "jp.anthropic.claude-opus-5", - "variant": "", - "input": 5.5, - "output": 27.5, - "cached_input": 0.55 - }, - { - "provider": "AWS/Bedrock", - "model": "jp.anthropic.claude-sonnet-4-5-20250929-v1:0", - "variant": "", - "input": 3.3, - "output": 16.5, - "cached_input": 0.33 - }, - { - "provider": "AWS/Bedrock", - "model": "jp.anthropic.claude-sonnet-4-5-20250929-v1:0", - "variant": "above_200k_tokens", - "input": 6.6, - "output": 24.75, - "cached_input": 0.66 - }, - { - "provider": "AWS/Bedrock", - "model": "jp.anthropic.claude-sonnet-4-6", - "variant": "", - "input": 3.3, - "output": 16.5, - "cached_input": 0.33 - }, - { - "provider": "AWS/Bedrock", - "model": "jp.anthropic.claude-sonnet-5", - "variant": "", - "input": 2.2, - "output": 11, - "cached_input": 0.22 - }, - { - "provider": "AWS/Bedrock", - "model": "meta.llama2-13b-chat-v1", - "variant": "", - "input": 0.75, - "output": 1 - }, - { - "provider": "AWS/Bedrock", - "model": "meta.llama2-70b-chat-v1", - "variant": "", - "input": 1.95, - "output": 2.56 - }, - { - "provider": "AWS/Bedrock", - "model": "meta.llama3-1-405b-instruct-v1:0", - "variant": "", - "input": 5.32, - "output": 16 - }, - { - "provider": "AWS/Bedrock", - "model": "meta.llama3-1-70b-instruct-v1:0", - "variant": "", - "input": 0.99, - "output": 0.99 - }, - { - "provider": "AWS/Bedrock", - "model": "meta.llama3-1-8b-instruct-v1:0", - "variant": "", - "input": 0.22, - "output": 0.22 - }, - { - "provider": "AWS/Bedrock", - "model": "meta.llama3-2-11b-instruct-v1:0", - "variant": "", - "input": 0.35, - "output": 0.35 - }, - { - "provider": "AWS/Bedrock", - "model": "meta.llama3-2-1b-instruct-v1:0", - "variant": "", - "input": 0.1, - "output": 0.1 - }, - { - "provider": "AWS/Bedrock", - "model": "meta.llama3-2-3b-instruct-v1:0", - "variant": "", - "input": 0.15, - "output": 0.15 - }, - { - "provider": "AWS/Bedrock", - "model": "meta.llama3-2-90b-instruct-v1:0", - "variant": "", - "input": 2, - "output": 2 - }, - { - "provider": "AWS/Bedrock", - "model": "meta.llama3-3-70b-instruct-v1:0", - "variant": "", - "input": 0.72, - "output": 0.72 - }, - { - "provider": "AWS/Bedrock", - "model": "meta.llama3-70b-instruct-v1:0", - "variant": "", - "input": 2.65, - "output": 3.5 - }, - { - "provider": "AWS/Bedrock", - "model": "meta.llama3-8b-instruct-v1:0", - "variant": "", - "input": 0.3, - "output": 0.6 - }, - { - "provider": "AWS/Bedrock", - "model": "meta.llama4-maverick-17b-instruct-v1:0", - "variant": "", - "input": 0.24, - "output": 0.97 - }, - { - "provider": "AWS/Bedrock", - "model": "meta.llama4-maverick-17b-instruct-v1:0", - "variant": "batches", - "input": 0.12, - "output": 0.485 - }, - { - "provider": "AWS/Bedrock", - "model": "meta.llama4-scout-17b-instruct-v1:0", - "variant": "", - "input": 0.17, - "output": 0.66 - }, - { - "provider": "AWS/Bedrock", - "model": "meta.llama4-scout-17b-instruct-v1:0", - "variant": "batches", - "input": 0.085, - "output": 0.33 - }, - { - "provider": "AWS/Bedrock", - "model": "minimax.minimax-m2", - "variant": "", - "input": 0.3, - "output": 1.2 - }, - { - "provider": "AWS/Bedrock", - "model": "minimax.minimax-m2.1", - "variant": "", - "input": 0.3, - "output": 1.2 - }, - { - "provider": "AWS/Bedrock", - "model": "minimax.minimax-m2.5", - "variant": "", - "input": 0.3, - "output": 1.2 - }, - { - "provider": "AWS/Bedrock", - "model": "mistral.devstral-2-123b", - "variant": "", - "input": 0.4, - "output": 2 - }, - { - "provider": "AWS/Bedrock", - "model": "mistral.magistral-small-2509", - "variant": "", - "input": 0.5, - "output": 1.5 - }, - { - "provider": "AWS/Bedrock", - "model": "mistral.ministral-3-14b-instruct", - "variant": "", - "input": 0.2, - "output": 0.2 - }, - { - "provider": "AWS/Bedrock", - "model": "mistral.ministral-3-3b-instruct", - "variant": "", - "input": 0.1, - "output": 0.1 - }, - { - "provider": "AWS/Bedrock", - "model": "mistral.ministral-3-8b-instruct", - "variant": "", - "input": 0.15, - "output": 0.15 - }, - { - "provider": "AWS/Bedrock", - "model": "mistral.mistral-7b-instruct-v0:2", - "variant": "", - "input": 0.15, - "output": 0.2 - }, - { - "provider": "AWS/Bedrock", - "model": "mistral.mistral-large-2402-v1:0", - "variant": "", - "input": 8, - "output": 24 - }, - { - "provider": "AWS/Bedrock", - "model": "mistral.mistral-large-2407-v1:0", - "variant": "", - "input": 3, - "output": 9 - }, - { - "provider": "AWS/Bedrock", - "model": "mistral.mistral-large-3-675b-instruct", - "variant": "", - "input": 0.5, - "output": 1.5 - }, - { - "provider": "AWS/Bedrock", - "model": "mistral.mistral-small-2402-v1:0", - "variant": "", - "input": 1, - "output": 3 - }, - { - "provider": "AWS/Bedrock", - "model": "mistral.mixtral-8x7b-instruct-v0:1", - "variant": "", - "input": 0.45, - "output": 0.7 - }, - { - "provider": "AWS/Bedrock", - "model": "mistral.voxtral-mini-3b-2507", - "variant": "", - "input": 0.04, - "output": 0.04 - }, - { - "provider": "AWS/Bedrock", - "model": "mistral.voxtral-small-24b-2507", - "variant": "", - "input": 0.1, - "output": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "moonshot.kimi-k2-thinking", - "variant": "", - "input": 0.6, - "output": 2.5 - }, - { - "provider": "AWS/Bedrock", - "model": "moonshotai.kimi-k2-thinking", - "variant": "", - "input": 0.73, - "output": 3.03 - }, - { - "provider": "AWS/Bedrock", - "model": "moonshotai.kimi-k2.5", - "variant": "", - "input": 0.6, - "output": 3.03 - }, - { - "provider": "AWS/Bedrock", - "model": "nvidia.nemotron-nano-12b-v2", - "variant": "", - "input": 0.2, - "output": 0.6 - }, - { - "provider": "AWS/Bedrock", - "model": "nvidia.nemotron-nano-3-30b", - "variant": "", - "input": 0.06, - "output": 0.24 - }, - { - "provider": "AWS/Bedrock", - "model": "nvidia.nemotron-nano-9b-v2", - "variant": "", - "input": 0.06, - "output": 0.23 - }, - { - "provider": "AWS/Bedrock", - "model": "nvidia.nemotron-super-3-120b", - "variant": "", - "input": 0.15, - "output": 0.65 - }, - { - "provider": "AWS/Bedrock", - "model": "openai.gpt-5.4", - "variant": "", - "input": 2.75, - "output": 16.5, - "cached_input": 0.275 - }, - { - "provider": "AWS/Bedrock", - "model": "openai.gpt-5.5", - "variant": "", - "input": 5.5, - "output": 33, - "cached_input": 0.55 - }, - { - "provider": "AWS/Bedrock", - "model": "openai.gpt-5.6-luna", - "variant": "", - "input": 0.22, - "output": 1.32, - "cached_input": 0.022 - }, - { - "provider": "AWS/Bedrock", - "model": "openai.gpt-5.6-sol", - "variant": "", - "input": 5.5, - "output": 33, - "cached_input": 0.55 - }, - { - "provider": "AWS/Bedrock", - "model": "openai.gpt-5.6-terra", - "variant": "", - "input": 2.2, - "output": 13.2, - "cached_input": 0.22 - }, - { - "provider": "AWS/Bedrock", - "model": "openai.gpt-oss-120b", - "variant": "", - "input": 0.15, - "output": 0.6 - }, - { - "provider": "AWS/Bedrock", - "model": "openai.gpt-oss-120b-1:0", - "variant": "", - "input": 0.15, - "output": 0.6 - }, - { - "provider": "AWS/Bedrock", - "model": "openai.gpt-oss-20b", - "variant": "", - "input": 0.075, - "output": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "openai.gpt-oss-20b-1:0", - "variant": "", - "input": 0.07, - "output": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "openai.gpt-oss-safeguard-120b", - "variant": "", - "input": 0.15, - "output": 0.6 - }, - { - "provider": "AWS/Bedrock", - "model": "openai.gpt-oss-safeguard-20b", - "variant": "", - "input": 0.07, - "output": 0.2 - }, - { - "provider": "AWS/Bedrock", - "model": "qwen.qwen3-235b-a22b-2507-v1:0", - "variant": "", - "input": 0.22, - "output": 0.88 - }, - { - "provider": "AWS/Bedrock", - "model": "qwen.qwen3-32b-v1:0", - "variant": "", - "input": 0.15, - "output": 0.6 - }, - { - "provider": "AWS/Bedrock", - "model": "qwen.qwen3-coder-30b-a3b-v1:0", - "variant": "", - "input": 0.15, - "output": 0.6 - }, - { - "provider": "AWS/Bedrock", - "model": "qwen.qwen3-coder-480b-a35b-v1:0", - "variant": "", - "input": 0.22, - "output": 1.8 - }, - { - "provider": "AWS/Bedrock", - "model": "qwen.qwen3-coder-next", - "variant": "", - "input": 0.5, - "output": 1.2 - }, - { - "provider": "AWS/Bedrock", - "model": "qwen.qwen3-next-80b-a3b", - "variant": "", - "input": 0.15, - "output": 1.2 - }, - { - "provider": "AWS/Bedrock", - "model": "qwen.qwen3-vl-235b-a22b", - "variant": "", - "input": 0.53, - "output": 2.66 - }, - { - "provider": "AWS/Bedrock", - "model": "sa-east-1/deepseek.v3.2", - "variant": "", - "input": 0.74, - "output": 2.22 - }, - { - "provider": "AWS/Bedrock", - "model": "sa-east-1/meta.llama3-70b-instruct-v1:0", - "variant": "", - "input": 4.45, - "output": 5.88 - }, - { - "provider": "AWS/Bedrock", - "model": "sa-east-1/meta.llama3-8b-instruct-v1:0", - "variant": "", - "input": 0.5, - "output": 1.01 - }, - { - "provider": "AWS/Bedrock", - "model": "sa-east-1/minimax.minimax-m2.1", - "variant": "", - "input": 0.36, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "sa-east-1/minimax.minimax-m2.5", - "variant": "", - "input": 0.36, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "sa-east-1/moonshotai.kimi-k2-thinking", - "variant": "", - "input": 0.73, - "output": 3.03 - }, - { - "provider": "AWS/Bedrock", - "model": "sa-east-1/moonshotai.kimi-k2.5", - "variant": "", - "input": 0.72, - "output": 3.6 - }, - { - "provider": "AWS/Bedrock", - "model": "sa-east-1/qwen.qwen3-coder-next", - "variant": "", - "input": 0.6, - "output": 1.44 - }, - { - "provider": "AWS/Bedrock", - "model": "twelvelabs.marengo-embed-2-7-v1:0", - "variant": "", - "input": 70, - "output": 0 - }, - { - "provider": "AWS/Bedrock", - "model": "twelvelabs.pegasus-1-2-v1:0", - "variant": "", - "output": 7.5 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-1/anthropic.claude-instant-v1", - "variant": "", - "input": 0.8, - "output": 2.4 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-1/anthropic.claude-v1", - "variant": "", - "input": 8, - "output": 24 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-1/anthropic.claude-v2:1", - "variant": "", - "input": 8, - "output": 24 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-1/deepseek.v3.2", - "variant": "", - "input": 0.62, - "output": 1.85 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-1/meta.llama3-70b-instruct-v1:0", - "variant": "", - "input": 2.65, - "output": 3.5 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-1/meta.llama3-8b-instruct-v1:0", - "variant": "", - "input": 0.3, - "output": 0.6 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-1/minimax.minimax-m2.1", - "variant": "", - "input": 0.3, - "output": 1.2 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-1/minimax.minimax-m2.5", - "variant": "", - "input": 0.3, - "output": 1.2 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-1/mistral.mistral-7b-instruct-v0:2", - "variant": "", - "input": 0.15, - "output": 0.2 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-1/mistral.mistral-large-2402-v1:0", - "variant": "", - "input": 8, - "output": 24 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-1/mistral.mixtral-8x7b-instruct-v0:1", - "variant": "", - "input": 0.45, - "output": 0.7 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-1/moonshotai.kimi-k2-thinking", - "variant": "", - "input": 0.6, - "output": 2.5 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-1/moonshotai.kimi-k2.5", - "variant": "", - "input": 0.6, - "output": 3 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-1/qwen.qwen3-coder-next", - "variant": "", - "input": 0.5, - "output": 1.2 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-1/zai.glm-5", - "variant": "", - "input": 1, - "output": 3.2 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-2/deepseek.v3.2", - "variant": "", - "input": 0.62, - "output": 1.85 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-2/minimax.minimax-m2.1", - "variant": "", - "input": 0.3, - "output": 1.2 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-2/minimax.minimax-m2.5", - "variant": "", - "input": 0.3, - "output": 1.2 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-2/moonshotai.kimi-k2-thinking", - "variant": "", - "input": 0.6, - "output": 2.5 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-2/moonshotai.kimi-k2.5", - "variant": "", - "input": 0.6, - "output": 3 - }, - { - "provider": "AWS/Bedrock", - "model": "us-east-2/qwen.qwen3-coder-next", - "variant": "", - "input": 0.5, - "output": 1.2 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-east-1/amazon.nova-pro-v1:0", - "variant": "", - "input": 0.96, - "output": 3.84 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-east-1/amazon.titan-embed-text-v1", - "variant": "", - "input": 0.1, - "output": 0 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-east-1/amazon.titan-embed-text-v2:0", - "variant": "", - "input": 0.2, - "output": 0 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-east-1/amazon.titan-text-express-v1", - "variant": "", - "input": 1.3, - "output": 1.7 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-east-1/amazon.titan-text-lite-v1", - "variant": "", - "input": 0.3, - "output": 0.4 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-east-1/amazon.titan-text-premier-v1:0", - "variant": "", - "input": 0.5, - "output": 1.5 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0", - "variant": "", - "input": 3.6, - "output": 18, - "cached_input": 0.36 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0", - "variant": "", - "input": 0.3, - "output": 1.5, - "cached_input": 0.03 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0", - "variant": "", - "input": 1.2, - "output": 6, - "cached_input": 0.12 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-east-1/anthropic.claude-sonnet-4-5-20250929-v1:0", - "variant": "", - "input": 3.6, - "output": 18, - "cached_input": 0.36 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-east-1/claude-sonnet-4-5-20250929-v1:0", - "variant": "", - "input": 3.6, - "output": 18, - "cached_input": 0.36 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-east-1/meta.llama3-70b-instruct-v1:0", - "variant": "", - "input": 2.65, - "output": 3.5 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-east-1/meta.llama3-8b-instruct-v1:0", - "variant": "", - "input": 0.3, - "output": 2.65 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-west-1/amazon.nova-pro-v1:0", - "variant": "", - "input": 0.96, - "output": 3.84 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-west-1/amazon.titan-embed-text-v1", - "variant": "", - "input": 0.1, - "output": 0 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-west-1/amazon.titan-embed-text-v2:0", - "variant": "", - "input": 0.2, - "output": 0 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-west-1/amazon.titan-text-express-v1", - "variant": "", - "input": 1.3, - "output": 1.7 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-west-1/amazon.titan-text-lite-v1", - "variant": "", - "input": 0.3, - "output": 0.4 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-west-1/amazon.titan-text-premier-v1:0", - "variant": "", - "input": 0.5, - "output": 1.5 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0", - "variant": "", - "input": 3.6, - "output": 18, - "cached_input": 0.36 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0", - "variant": "", - "input": 3.6, - "output": 18, - "cached_input": 0.36 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0", - "variant": "", - "input": 0.3, - "output": 1.5, - "cached_input": 0.03 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0", - "variant": "", - "input": 1.2, - "output": 6, - "cached_input": 0.12 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-west-1/anthropic.claude-sonnet-4-5-20250929-v1:0", - "variant": "", - "input": 3.6, - "output": 18, - "cached_input": 0.36 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-west-1/claude-sonnet-4-5-20250929-v1:0", - "variant": "", - "input": 3.6, - "output": 18, - "cached_input": 0.36 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-west-1/meta.llama3-70b-instruct-v1:0", - "variant": "", - "input": 2.65, - "output": 3.5 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov-west-1/meta.llama3-8b-instruct-v1:0", - "variant": "", - "input": 0.3, - "output": 2.65 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0", - "variant": "", - "input": 3.6, - "output": 18, - "cached_input": 0.36 - }, - { - "provider": "AWS/Bedrock", - "model": "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0", - "variant": "above_200k_tokens", - "input": 7.2, - "output": 27, - "cached_input": 0.72 - }, - { - "provider": "AWS/Bedrock", - "model": "us-west-1/meta.llama3-70b-instruct-v1:0", - "variant": "", - "input": 2.65, - "output": 3.5 - }, - { - "provider": "AWS/Bedrock", - "model": "us-west-1/meta.llama3-8b-instruct-v1:0", - "variant": "", - "input": 0.3, - "output": 0.6 - }, - { - "provider": "AWS/Bedrock", - "model": "us-west-2/anthropic.claude-instant-v1", - "variant": "", - "input": 0.8, - "output": 2.4 - }, - { - "provider": "AWS/Bedrock", - "model": "us-west-2/anthropic.claude-v1", - "variant": "", - "input": 8, - "output": 24 - }, - { - "provider": "AWS/Bedrock", - "model": "us-west-2/anthropic.claude-v2:1", - "variant": "", - "input": 8, - "output": 24 - }, - { - "provider": "AWS/Bedrock", - "model": "us-west-2/deepseek.v3.2", - "variant": "", - "input": 0.62, - "output": 1.85 - }, - { - "provider": "AWS/Bedrock", - "model": "us-west-2/minimax.minimax-m2.1", - "variant": "", - "input": 0.3, - "output": 1.2 - }, - { - "provider": "AWS/Bedrock", - "model": "us-west-2/minimax.minimax-m2.5", - "variant": "", - "input": 0.3, - "output": 1.2 - }, - { - "provider": "AWS/Bedrock", - "model": "us-west-2/mistral.mistral-7b-instruct-v0:2", - "variant": "", - "input": 0.15, - "output": 0.2 - }, - { - "provider": "AWS/Bedrock", - "model": "us-west-2/mistral.mistral-large-2402-v1:0", - "variant": "", - "input": 8, - "output": 24 - }, - { - "provider": "AWS/Bedrock", - "model": "us-west-2/mistral.mixtral-8x7b-instruct-v0:1", - "variant": "", - "input": 0.45, - "output": 0.7 - }, - { - "provider": "AWS/Bedrock", - "model": "us-west-2/moonshotai.kimi-k2-thinking", - "variant": "", - "input": 0.6, - "output": 2.5 - }, - { - "provider": "AWS/Bedrock", - "model": "us-west-2/moonshotai.kimi-k2.5", - "variant": "", - "input": 0.6, - "output": 3 - }, - { - "provider": "AWS/Bedrock", - "model": "us-west-2/qwen.qwen3-coder-next", - "variant": "", - "input": 0.5, - "output": 1.2 - }, - { - "provider": "AWS/Bedrock", - "model": "us-west-2/zai.glm-5", - "variant": "", - "input": 1, - "output": 3.2 - }, - { - "provider": "AWS/Bedrock", - "model": "us.amazon.nova-2-lite-v1:0", - "variant": "", - "input": 0.33, - "output": 2.75, - "cached_input": 0.0825 - }, - { - "provider": "AWS/Bedrock", - "model": "us.amazon.nova-2-pro-preview-20251202-v1:0", - "variant": "", - "input": 2.1875, - "output": 17.5, - "cached_input": 0.5469 - }, - { - "provider": "AWS/Bedrock", - "model": "us.amazon.nova-lite-v1:0", - "variant": "", - "input": 0.06, - "output": 0.24 - }, - { - "provider": "AWS/Bedrock", - "model": "us.amazon.nova-micro-v1:0", - "variant": "", - "input": 0.035, - "output": 0.14 - }, - { - "provider": "AWS/Bedrock", - "model": "us.amazon.nova-premier-v1:0", - "variant": "", - "input": 2.5, - "output": 12.5 - }, - { - "provider": "AWS/Bedrock", - "model": "us.amazon.nova-pro-v1:0", - "variant": "", - "input": 0.8, - "output": 3.2 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-3-5-haiku-20241022-v1:0", - "variant": "", - "input": 0.8, - "output": 4, - "cached_input": 0.08 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-3-5-sonnet-20240620-v1:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-3-5-sonnet-20241022-v2:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-3-7-sonnet-20250219-v1:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-3-haiku-20240307-v1:0", - "variant": "", - "input": 0.25, - "output": 1.25, - "cached_input": 0.025 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-3-opus-20240229-v1:0", - "variant": "", - "input": 15, - "output": 75, - "cached_input": 1.5 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-3-sonnet-20240229-v1:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-fable-5", - "variant": "", - "input": 11, - "output": 55, - "cached_input": 1.1 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-haiku-4-5-20251001-v1:0", - "variant": "", - "input": 1.1, - "output": 5.5, - "cached_input": 0.11 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-opus-4-1-20250805-v1:0", - "variant": "", - "input": 15, - "output": 75, - "cached_input": 1.5 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-opus-4-20250514-v1:0", - "variant": "", - "input": 15, - "output": 75, - "cached_input": 1.5 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-opus-4-5-20251101-v1:0", - "variant": "", - "input": 5.5, - "output": 27.5, - "cached_input": 0.55 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-opus-4-6-v1", - "variant": "", - "input": 5.5, - "output": 27.5, - "cached_input": 0.55 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-opus-4-7", - "variant": "", - "input": 5.5, - "output": 27.5, - "cached_input": 0.55 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-opus-4-8", - "variant": "", - "input": 5.5, - "output": 27.5, - "cached_input": 0.55 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-opus-5", - "variant": "", - "input": 5.5, - "output": 27.5, - "cached_input": 0.55 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-sonnet-4-20250514-v1:0", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-sonnet-4-20250514-v1:0", - "variant": "above_200k_tokens", - "input": 6, - "output": 22.5, - "cached_input": 0.6 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-sonnet-4-5-20250929-v1:0", - "variant": "", - "input": 3.3, - "output": 16.5, - "cached_input": 0.33 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-sonnet-4-5-20250929-v1:0", - "variant": "above_200k_tokens", - "input": 6.6, - "output": 24.75, - "cached_input": 0.66 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-sonnet-4-6", - "variant": "", - "input": 3.3, - "output": 16.5, - "cached_input": 0.33 - }, - { - "provider": "AWS/Bedrock", - "model": "us.anthropic.claude-sonnet-5", - "variant": "", - "input": 2.2, - "output": 11, - "cached_input": 0.22 - }, - { - "provider": "AWS/Bedrock", - "model": "us.deepseek.r1-v1:0", - "variant": "", - "input": 1.35, - "output": 5.4 - }, - { - "provider": "AWS/Bedrock", - "model": "us.deepseek.v3.2", - "variant": "", - "input": 0.62, - "output": 1.85 - }, - { - "provider": "AWS/Bedrock", - "model": "us.meta.llama3-1-405b-instruct-v1:0", - "variant": "", - "input": 5.32, - "output": 16 - }, - { - "provider": "AWS/Bedrock", - "model": "us.meta.llama3-1-70b-instruct-v1:0", - "variant": "", - "input": 0.99, - "output": 0.99 - }, - { - "provider": "AWS/Bedrock", - "model": "us.meta.llama3-1-8b-instruct-v1:0", - "variant": "", - "input": 0.22, - "output": 0.22 - }, - { - "provider": "AWS/Bedrock", - "model": "us.meta.llama3-2-11b-instruct-v1:0", - "variant": "", - "input": 0.35, - "output": 0.35 - }, - { - "provider": "AWS/Bedrock", - "model": "us.meta.llama3-2-1b-instruct-v1:0", - "variant": "", - "input": 0.1, - "output": 0.1 - }, - { - "provider": "AWS/Bedrock", - "model": "us.meta.llama3-2-3b-instruct-v1:0", - "variant": "", - "input": 0.15, - "output": 0.15 - }, - { - "provider": "AWS/Bedrock", - "model": "us.meta.llama3-2-90b-instruct-v1:0", - "variant": "", - "input": 2, - "output": 2 - }, - { - "provider": "AWS/Bedrock", - "model": "us.meta.llama3-3-70b-instruct-v1:0", - "variant": "", - "input": 0.72, - "output": 0.72 - }, - { - "provider": "AWS/Bedrock", - "model": "us.meta.llama4-maverick-17b-instruct-v1:0", - "variant": "", - "input": 0.24, - "output": 0.97 - }, - { - "provider": "AWS/Bedrock", - "model": "us.meta.llama4-maverick-17b-instruct-v1:0", - "variant": "batches", - "input": 0.12, - "output": 0.485 - }, - { - "provider": "AWS/Bedrock", - "model": "us.meta.llama4-scout-17b-instruct-v1:0", - "variant": "", - "input": 0.17, - "output": 0.66 - }, - { - "provider": "AWS/Bedrock", - "model": "us.meta.llama4-scout-17b-instruct-v1:0", - "variant": "batches", - "input": 0.085, - "output": 0.33 - }, - { - "provider": "AWS/Bedrock", - "model": "us.mistral.pixtral-large-2502-v1:0", - "variant": "", - "input": 2, - "output": 6 - }, - { - "provider": "AWS/Bedrock", - "model": "us.twelvelabs.marengo-embed-2-7-v1:0", - "variant": "", - "input": 70, - "output": 0 - }, - { - "provider": "AWS/Bedrock", - "model": "us.twelvelabs.pegasus-1-2-v1:0", - "variant": "", - "output": 7.5 - }, - { - "provider": "AWS/Bedrock", - "model": "us.writer.palmyra-x4-v1:0", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "AWS/Bedrock", - "model": "us.writer.palmyra-x5-v1:0", - "variant": "", - "input": 0.6, - "output": 6 - }, - { - "provider": "AWS/Bedrock", - "model": "writer.palmyra-x4-v1:0", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "AWS/Bedrock", - "model": "writer.palmyra-x5-v1:0", - "variant": "", - "input": 0.6, - "output": 6 - }, - { - "provider": "AWS/Bedrock", - "model": "xai.grok-4.3", - "variant": "", - "input": 1.25, - "output": 2.5, - "cached_input": 0.2 - }, - { - "provider": "AWS/Bedrock", - "model": "zai.glm-4.7", - "variant": "", - "input": 0.6, - "output": 2.2 - }, - { - "provider": "AWS/Bedrock", - "model": "zai.glm-4.7-flash", - "variant": "", - "input": 0.07, - "output": 0.4 - }, - { - "provider": "AWS/Bedrock", - "model": "zai.glm-5", - "variant": "", - "input": 1, - "output": 3.2 - }, - { - "provider": "Anthropic", - "model": "claude-3-7-sonnet-20250219", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "Anthropic", - "model": "claude-3-haiku-20240307", - "variant": "", - "input": 0.25, - "output": 1.25, - "cached_input": 0.03 - }, - { - "provider": "Anthropic", - "model": "claude-3-opus-20240229", - "variant": "", - "input": 15, - "output": 75, - "cached_input": 1.5 - }, - { - "provider": "Anthropic", - "model": "claude-4-opus-20250514", - "variant": "", - "input": 15, - "output": 75, - "cached_input": 1.5 - }, - { - "provider": "Anthropic", - "model": "claude-4-sonnet-20250514", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "Anthropic", - "model": "claude-4-sonnet-20250514", - "variant": "above_200k_tokens", - "input": 6, - "output": 22.5, - "cached_input": 0.6 - }, - { - "provider": "Anthropic", - "model": "claude-fable-5", - "variant": "", - "input": 10, - "output": 50, - "cached_input": 1 - }, - { - "provider": "Anthropic", - "model": "claude-haiku-4-5", - "variant": "", - "input": 1, - "output": 5, - "cached_input": 0.1 - }, - { - "provider": "Anthropic", - "model": "claude-haiku-4-5-20251001", - "variant": "", - "input": 1, - "output": 5, - "cached_input": 0.1 - }, - { - "provider": "Anthropic", - "model": "claude-opus-4-1", - "variant": "", - "input": 15, - "output": 75, - "cached_input": 1.5 - }, - { - "provider": "Anthropic", - "model": "claude-opus-4-1-20250805", - "variant": "", - "input": 15, - "output": 75, - "cached_input": 1.5 - }, - { - "provider": "Anthropic", - "model": "claude-opus-4-20250514", - "variant": "", - "input": 15, - "output": 75, - "cached_input": 1.5 - }, - { - "provider": "Anthropic", - "model": "claude-opus-4-5", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "Anthropic", - "model": "claude-opus-4-5-20251101", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "Anthropic", - "model": "claude-opus-4-6", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "Anthropic", - "model": "claude-opus-4-6-20260205", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "Anthropic", - "model": "claude-opus-4-7", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "Anthropic", - "model": "claude-opus-4-7-20260416", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "Anthropic", - "model": "claude-opus-4-8", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "Anthropic", - "model": "claude-opus-5", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "Anthropic", - "model": "claude-sonnet-4-20250514", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "Anthropic", - "model": "claude-sonnet-4-20250514", - "variant": "above_200k_tokens", - "input": 6, - "output": 22.5, - "cached_input": 0.6 - }, - { - "provider": "Anthropic", - "model": "claude-sonnet-4-5", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "Anthropic", - "model": "claude-sonnet-4-5", - "variant": "above_200k_tokens", - "input": 6, - "output": 22.5, - "cached_input": 0.6 - }, - { - "provider": "Anthropic", - "model": "claude-sonnet-4-5-20250929", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "Anthropic", - "model": "claude-sonnet-4-5-20250929", - "variant": "above_200k_tokens", - "input": 6, - "output": 22.5, - "cached_input": 0.6 - }, - { - "provider": "Anthropic", - "model": "claude-sonnet-4-6", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "Anthropic", - "model": "claude-sonnet-5", - "variant": "", - "input": 2, - "output": 10, - "cached_input": 0.2 - }, - { - "provider": "Azure/OpenAI", - "model": "ada", - "variant": "", - "input": 0.1, - "output": 0 - }, - { - "provider": "Azure/OpenAI", - "model": "codex-mini", - "variant": "", - "input": 1.5, - "output": 6, - "cached_input": 0.375 - }, - { - "provider": "Azure/OpenAI", - "model": "command-r-plus", - "variant": "", - "input": 3, - "output": 15 - }, - { - "provider": "Azure/OpenAI", - "model": "computer-use-preview", - "variant": "", - "input": 3, - "output": 12 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-4o-2024-08-06", - "variant": "", - "input": 2.75, - "output": 11, - "cached_input": 1.375 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-4o-2024-11-20", - "variant": "", - "input": 2.75, - "output": 11 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-4o-mini-2024-07-18", - "variant": "", - "input": 0.165, - "output": 0.66, - "cached_input": 0.083 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-4o-mini-realtime-preview-2024-12-17", - "variant": "", - "input": 0.66, - "output": 2.64, - "cached_input": 0.33 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-4o-realtime-preview-2024-10-01", - "variant": "", - "input": 5.5, - "output": 22, - "cached_input": 2.75 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-4o-realtime-preview-2024-12-17", - "variant": "", - "input": 5.5, - "output": 22, - "cached_input": 2.75 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5-2025-08-07", - "variant": "", - "input": 1.375, - "output": 11, - "cached_input": 0.1375 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5-mini-2025-08-07", - "variant": "", - "input": 0.275, - "output": 2.2, - "cached_input": 0.0275 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5-nano-2025-08-07", - "variant": "", - "input": 0.055, - "output": 0.44, - "cached_input": 0.0055 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.1", - "variant": "", - "input": 1.38, - "output": 11, - "cached_input": 0.14 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.1-chat", - "variant": "", - "input": 1.38, - "output": 11, - "cached_input": 0.14 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.1-codex", - "variant": "", - "input": 1.38, - "output": 11, - "cached_input": 0.14 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.1-codex-mini", - "variant": "", - "input": 0.275, - "output": 2.2, - "cached_input": 0.028 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.4", - "variant": "", - "input": 2.75, - "output": 16.5, - "cached_input": 0.28 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.4", - "variant": "priority", - "input": 5.5, - "output": 33, - "cached_input": 0.55 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.4-2026-03-05", - "variant": "", - "input": 2.75, - "output": 16.5, - "cached_input": 0.28 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.4-2026-03-05", - "variant": "priority", - "input": 5.5, - "output": 33, - "cached_input": 0.55 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.5", - "variant": "", - "input": 5.5, - "output": 33, - "cached_input": 0.55 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.5", - "variant": "above_272k_tokens", - "input": 11, - "output": 49.5, - "cached_input": 1.1 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.5", - "variant": "priority", - "input": 13.75, - "output": 82.5, - "cached_input": 1.38 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.5-2026-04-23", - "variant": "", - "input": 5.5, - "output": 33, - "cached_input": 0.55 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.5-2026-04-23", - "variant": "above_272k_tokens", - "input": 11, - "output": 49.5, - "cached_input": 1.1 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.5-2026-04-23", - "variant": "priority", - "input": 13.75, - "output": 82.5, - "cached_input": 1.38 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.6", - "variant": "", - "input": 5.5, - "output": 33, - "cached_input": 0.55 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.6", - "variant": "above_272k_tokens", - "input": 11, - "output": 49.5, - "cached_input": 1.1 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.6", - "variant": "priority", - "input": 13.75, - "output": 82.5, - "cached_input": 1.375 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.6-luna", - "variant": "", - "input": 1.1, - "output": 6.6, - "cached_input": 0.11 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.6-luna", - "variant": "above_272k_tokens", - "input": 2.2, - "output": 9.9, - "cached_input": 0.22 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.6-luna", - "variant": "priority", - "input": 2.75, - "output": 16.5, - "cached_input": 0.275 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.6-sol", - "variant": "", - "input": 5.5, - "output": 33, - "cached_input": 0.55 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.6-sol", - "variant": "above_272k_tokens", - "input": 11, - "output": 49.5, - "cached_input": 1.1 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.6-sol", - "variant": "priority", - "input": 13.75, - "output": 82.5, - "cached_input": 1.375 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.6-terra", - "variant": "", - "input": 2.75, - "output": 16.5, - "cached_input": 0.275 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.6-terra", - "variant": "above_272k_tokens", - "input": 5.5, - "output": 24.75, - "cached_input": 0.55 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/gpt-5.6-terra", - "variant": "priority", - "input": 6.875, - "output": 41.25, - "cached_input": 0.6875 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/o1-2024-12-17", - "variant": "", - "input": 16.5, - "output": 66, - "cached_input": 8.25 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/o1-mini-2024-09-12", - "variant": "", - "input": 1.21, - "output": 4.84, - "cached_input": 0.605 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/o1-mini-2024-09-12", - "variant": "batches", - "input": 0.605, - "output": 2.42 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/o1-preview-2024-09-12", - "variant": "", - "input": 16.5, - "output": 66, - "cached_input": 8.25 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/o3-mini-2025-01-31", - "variant": "", - "input": 1.21, - "output": 4.84, - "cached_input": 0.605 - }, - { - "provider": "Azure/OpenAI", - "model": "eu/o3-mini-2025-01-31", - "variant": "batches", - "input": 0.605, - "output": 2.42 - }, - { - "provider": "Azure/OpenAI", - "model": "global-standard/gpt-4o-2024-08-06", - "variant": "", - "input": 2.5, - "output": 10, - "cached_input": 1.25 - }, - { - "provider": "Azure/OpenAI", - "model": "global-standard/gpt-4o-2024-11-20", - "variant": "", - "input": 2.5, - "output": 10, - "cached_input": 1.25 - }, - { - "provider": "Azure/OpenAI", - "model": "global-standard/gpt-4o-mini", - "variant": "", - "input": 0.15, - "output": 0.6 - }, - { - "provider": "Azure/OpenAI", - "model": "global/gpt-4o-2024-08-06", - "variant": "", - "input": 2.5, - "output": 10, - "cached_input": 1.25 - }, - { - "provider": "Azure/OpenAI", - "model": "global/gpt-4o-2024-11-20", - "variant": "", - "input": 2.5, - "output": 10, - "cached_input": 1.25 - }, - { - "provider": "Azure/OpenAI", - "model": "global/gpt-5.1", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "Azure/OpenAI", - "model": "global/gpt-5.1-chat", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "Azure/OpenAI", - "model": "global/gpt-5.1-codex", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "Azure/OpenAI", - "model": "global/gpt-5.1-codex-mini", - "variant": "", - "input": 0.25, - "output": 2, - "cached_input": 0.025 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-3.5-turbo", - "variant": "", - "input": 0.5, - "output": 1.5 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-3.5-turbo-0125", - "variant": "", - "input": 0.5, - "output": 1.5 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-35-turbo", - "variant": "", - "input": 0.5, - "output": 1.5 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-35-turbo-0125", - "variant": "", - "input": 0.5, - "output": 1.5 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-35-turbo-1106", - "variant": "", - "input": 1, - "output": 2 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-35-turbo-16k", - "variant": "", - "input": 3, - "output": 4 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-35-turbo-16k-0613", - "variant": "", - "input": 3, - "output": 4 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4", - "variant": "", - "input": 30, - "output": 60 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4-0125-preview", - "variant": "", - "input": 10, - "output": 30 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4-0613", - "variant": "", - "input": 30, - "output": 60 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4-1106-preview", - "variant": "", - "input": 10, - "output": 30 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4-32k", - "variant": "", - "input": 60, - "output": 120 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4-32k-0613", - "variant": "", - "input": 60, - "output": 120 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4-turbo", - "variant": "", - "input": 10, - "output": 30 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4-turbo-2024-04-09", - "variant": "", - "input": 10, - "output": 30 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4-turbo-vision-preview", - "variant": "", - "input": 10, - "output": 30 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4.1", - "variant": "", - "input": 2, - "output": 8, - "cached_input": 0.5 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4.1", - "variant": "batches", - "input": 1, - "output": 4 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4.1-2025-04-14", - "variant": "", - "input": 2, - "output": 8, - "cached_input": 0.5 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4.1-2025-04-14", - "variant": "batches", - "input": 1, - "output": 4 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4.1-mini", - "variant": "", - "input": 0.4, - "output": 1.6, - "cached_input": 0.1 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4.1-mini", - "variant": "batches", - "input": 0.2, - "output": 0.8 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4.1-mini-2025-04-14", - "variant": "", - "input": 0.4, - "output": 1.6, - "cached_input": 0.1 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4.1-mini-2025-04-14", - "variant": "batches", - "input": 0.2, - "output": 0.8 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4.1-nano", - "variant": "", - "input": 0.1, - "output": 0.4, - "cached_input": 0.025 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4.1-nano", - "variant": "batches", - "input": 0.05, - "output": 0.2 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4.1-nano-2025-04-14", - "variant": "", - "input": 0.1, - "output": 0.4, - "cached_input": 0.025 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4.1-nano-2025-04-14", - "variant": "batches", - "input": 0.05, - "output": 0.2 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4.5-preview", - "variant": "", - "input": 75, - "output": 150, - "cached_input": 37.5 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4.5-preview", - "variant": "batches", - "input": 37.5, - "output": 75 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4o", - "variant": "", - "input": 2.5, - "output": 10, - "cached_input": 1.25 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4o-2024-05-13", - "variant": "", - "input": 5, - "output": 15 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4o-2024-08-06", - "variant": "", - "input": 2.5, - "output": 10, - "cached_input": 1.25 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4o-2024-11-20", - "variant": "", - "input": 2.75, - "output": 11, - "cached_input": 1.25 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4o-audio-preview-2024-12-17", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4o-mini", - "variant": "", - "input": 0.165, - "output": 0.66, - "cached_input": 0.075 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4o-mini-2024-07-18", - "variant": "", - "input": 0.165, - "output": 0.66, - "cached_input": 0.075 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4o-mini-audio-preview-2024-12-17", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4o-mini-realtime-preview-2024-12-17", - "variant": "", - "input": 0.6, - "output": 2.4, - "cached_input": 0.3 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4o-mini-transcribe", - "variant": "", - "input": 1.25, - "output": 5 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4o-mini-tts", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4o-realtime-preview-2024-10-01", - "variant": "", - "input": 5, - "output": 20, - "cached_input": 2.5 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4o-realtime-preview-2024-12-17", - "variant": "", - "input": 5, - "output": 20, - "cached_input": 2.5 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4o-transcribe", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-4o-transcribe-diarize", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5-2025-08-07", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5-chat", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5-chat-latest", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5-codex", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5-mini", - "variant": "", - "input": 0.25, - "output": 2, - "cached_input": 0.025 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5-mini-2025-08-07", - "variant": "", - "input": 0.25, - "output": 2, - "cached_input": 0.025 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5-nano", - "variant": "", - "input": 0.05, - "output": 0.4, - "cached_input": 0.005 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5-nano-2025-08-07", - "variant": "", - "input": 0.05, - "output": 0.4, - "cached_input": 0.005 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5-pro", - "variant": "", - "input": 15, - "output": 120 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.1", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.1-2025-11-13", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.1-2025-11-13", - "variant": "priority", - "input": 2.5, - "output": 20, - "cached_input": 0.25 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.1-chat", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.1-chat-2025-11-13", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.1-chat-2025-11-13", - "variant": "priority", - "input": 2.5, - "output": 20, - "cached_input": 0.25 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.1-codex", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.1-codex-2025-11-13", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.1-codex-2025-11-13", - "variant": "priority", - "input": 2.5, - "output": 20, - "cached_input": 0.25 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.1-codex-max", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.1-codex-mini", - "variant": "", - "input": 0.25, - "output": 2, - "cached_input": 0.025 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.1-codex-mini-2025-11-13", - "variant": "", - "input": 0.25, - "output": 2, - "cached_input": 0.025 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.1-codex-mini-2025-11-13", - "variant": "priority", - "input": 0.45, - "output": 3.6, - "cached_input": 0.045 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.2", - "variant": "", - "input": 1.75, - "output": 14, - "cached_input": 0.175 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.2-2025-12-11", - "variant": "", - "input": 1.75, - "output": 14, - "cached_input": 0.175 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.2-2025-12-11", - "variant": "priority", - "input": 3.5, - "output": 28, - "cached_input": 0.35 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.2-chat", - "variant": "", - "input": 1.75, - "output": 14, - "cached_input": 0.175 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.2-chat", - "variant": "priority", - "input": 3.5, - "output": 28, - "cached_input": 0.35 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.2-chat-2025-12-11", - "variant": "", - "input": 1.75, - "output": 14, - "cached_input": 0.175 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.2-chat-2025-12-11", - "variant": "priority", - "input": 3.5, - "output": 28, - "cached_input": 0.35 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.2-codex", - "variant": "", - "input": 1.75, - "output": 14, - "cached_input": 0.175 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.2-pro", - "variant": "", - "input": 21, - "output": 168 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.2-pro-2025-12-11", - "variant": "", - "input": 21, - "output": 168 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.3-chat", - "variant": "", - "input": 1.75, - "output": 14, - "cached_input": 0.175 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.3-chat", - "variant": "priority", - "input": 3.5, - "output": 28, - "cached_input": 0.35 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.3-codex", - "variant": "", - "input": 1.75, - "output": 14, - "cached_input": 0.175 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.4", - "variant": "", - "input": 2.5, - "output": 15, - "cached_input": 0.25 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.4", - "variant": "above_272k_tokens", - "input": 5, - "output": 22.5, - "cached_input": 0.5 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.4", - "variant": "above_272k_tokens_priority", - "input": 10, - "output": 45, - "cached_input": 1 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.4", - "variant": "priority", - "input": 5, - "output": 30, - "cached_input": 0.5 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.4-2026-03-05", - "variant": "", - "input": 2.5, - "output": 15, - "cached_input": 0.25 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.4-2026-03-05", - "variant": "above_272k_tokens", - "input": 5, - "output": 22.5, - "cached_input": 0.5 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.4-2026-03-05", - "variant": "above_272k_tokens_priority", - "input": 10, - "output": 45, - "cached_input": 1 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.4-2026-03-05", - "variant": "priority", - "input": 5, - "output": 30, - "cached_input": 0.5 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.4-mini", - "variant": "", - "input": 0.75, - "output": 4.5, - "cached_input": 0.075 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.4-mini-2026-03-17", - "variant": "", - "input": 0.75, - "output": 4.5, - "cached_input": 0.075 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.4-nano", - "variant": "", - "input": 0.2, - "output": 1.25, - "cached_input": 0.02 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.4-nano-2026-03-17", - "variant": "", - "input": 0.2, - "output": 1.25, - "cached_input": 0.02 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.4-pro", - "variant": "", - "input": 30, - "output": 180, - "cached_input": 3 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.4-pro", - "variant": "above_272k_tokens", - "input": 60, - "output": 270, - "cached_input": 6 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.4-pro-2026-03-05", - "variant": "", - "input": 30, - "output": 180, - "cached_input": 3 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.4-pro-2026-03-05", - "variant": "above_272k_tokens", - "input": 60, - "output": 270, - "cached_input": 6 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.5", - "variant": "", - "input": 5, - "output": 30, - "cached_input": 0.5 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.5", - "variant": "above_272k_tokens", - "input": 10, - "output": 45, - "cached_input": 1 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.5", - "variant": "above_272k_tokens_priority", - "input": 20, - "output": 90, - "cached_input": 2 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.5", - "variant": "priority", - "input": 10, - "output": 60, - "cached_input": 1 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.5-2026-04-23", - "variant": "", - "input": 5, - "output": 30, - "cached_input": 0.5 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.5-2026-04-23", - "variant": "above_272k_tokens", - "input": 10, - "output": 45, - "cached_input": 1 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.5-2026-04-23", - "variant": "above_272k_tokens_priority", - "input": 20, - "output": 90, - "cached_input": 2 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.5-2026-04-23", - "variant": "priority", - "input": 10, - "output": 60, - "cached_input": 1 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.5-pro", - "variant": "", - "input": 30, - "output": 180, - "cached_input": 3 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.5-pro", - "variant": "above_272k_tokens", - "input": 60, - "output": 270, - "cached_input": 6 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.5-pro-2026-04-23", - "variant": "", - "input": 30, - "output": 180, - "cached_input": 3 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.5-pro-2026-04-23", - "variant": "above_272k_tokens", - "input": 60, - "output": 270, - "cached_input": 6 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.6", - "variant": "", - "input": 5, - "output": 30, - "cached_input": 0.5 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.6", - "variant": "above_272k_tokens", - "input": 10, - "output": 45, - "cached_input": 1 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.6", - "variant": "above_272k_tokens_priority", - "input": 20, - "output": 90, - "cached_input": 2 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.6", - "variant": "priority", - "input": 10, - "output": 60, - "cached_input": 1 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.6-luna", - "variant": "", - "input": 1, - "output": 6, - "cached_input": 0.1 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.6-luna", - "variant": "above_272k_tokens", - "input": 2, - "output": 9, - "cached_input": 0.2 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.6-luna", - "variant": "above_272k_tokens_priority", - "input": 4, - "output": 18, - "cached_input": 0.4 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.6-luna", - "variant": "priority", - "input": 2, - "output": 12, - "cached_input": 0.2 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.6-sol", - "variant": "", - "input": 5, - "output": 30, - "cached_input": 0.5 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.6-sol", - "variant": "above_272k_tokens", - "input": 10, - "output": 45, - "cached_input": 1 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.6-sol", - "variant": "above_272k_tokens_priority", - "input": 20, - "output": 90, - "cached_input": 2 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.6-sol", - "variant": "priority", - "input": 10, - "output": 60, - "cached_input": 1 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.6-terra", - "variant": "", - "input": 2.5, - "output": 15, - "cached_input": 0.25 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.6-terra", - "variant": "above_272k_tokens", - "input": 5, - "output": 22.5, - "cached_input": 0.5 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.6-terra", - "variant": "above_272k_tokens_priority", - "input": 10, - "output": 45, - "cached_input": 1 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-5.6-terra", - "variant": "priority", - "input": 5, - "output": 30, - "cached_input": 0.5 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-audio-1.5-2026-02-23", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-audio-2025-08-28", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-audio-mini-2025-10-06", - "variant": "", - "input": 0.6, - "output": 2.4 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-image-1", - "variant": "", - "input": 5, - "cached_input": 1.25 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-image-1-mini", - "variant": "", - "input": 2, - "cached_input": 0.2 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-image-1.5", - "variant": "", - "input": 5, - "cached_input": 1.25 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-image-1.5-2025-12-16", - "variant": "", - "input": 5, - "cached_input": 1.25 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-image-2", - "variant": "", - "input": 5, - "output": 10, - "cached_input": 1.25 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-image-2-2026-04-21", - "variant": "", - "input": 5, - "output": 10, - "cached_input": 1.25 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-realtime-1.5-2026-02-23", - "variant": "", - "input": 4, - "output": 16, - "cached_input": 4 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-realtime-2025-08-28", - "variant": "", - "input": 4, - "output": 16, - "cached_input": 4 - }, - { - "provider": "Azure/OpenAI", - "model": "gpt-realtime-mini-2025-10-06", - "variant": "", - "input": 0.6, - "output": 2.4, - "cached_input": 0.06 - }, - { - "provider": "Azure/OpenAI", - "model": "mistral-large-2402", - "variant": "", - "input": 8, - "output": 24 - }, - { - "provider": "Azure/OpenAI", - "model": "mistral-large-latest", - "variant": "", - "input": 8, - "output": 24 - }, - { - "provider": "Azure/OpenAI", - "model": "o1", - "variant": "", - "input": 15, - "output": 60, - "cached_input": 7.5 - }, - { - "provider": "Azure/OpenAI", - "model": "o1-2024-12-17", - "variant": "", - "input": 15, - "output": 60, - "cached_input": 7.5 - }, - { - "provider": "Azure/OpenAI", - "model": "o1-mini", - "variant": "", - "input": 1.21, - "output": 4.84, - "cached_input": 0.605 - }, - { - "provider": "Azure/OpenAI", - "model": "o1-mini-2024-09-12", - "variant": "", - "input": 1.1, - "output": 4.4, - "cached_input": 0.55 - }, - { - "provider": "Azure/OpenAI", - "model": "o1-preview", - "variant": "", - "input": 15, - "output": 60, - "cached_input": 7.5 - }, - { - "provider": "Azure/OpenAI", - "model": "o1-preview-2024-09-12", - "variant": "", - "input": 15, - "output": 60, - "cached_input": 7.5 - }, - { - "provider": "Azure/OpenAI", - "model": "o3", - "variant": "", - "input": 2, - "output": 8, - "cached_input": 0.5 - }, - { - "provider": "Azure/OpenAI", - "model": "o3-2025-04-16", - "variant": "", - "input": 2, - "output": 8, - "cached_input": 0.5 - }, - { - "provider": "Azure/OpenAI", - "model": "o3-deep-research", - "variant": "", - "input": 10, - "output": 40, - "cached_input": 2.5 - }, - { - "provider": "Azure/OpenAI", - "model": "o3-mini", - "variant": "", - "input": 1.1, - "output": 4.4, - "cached_input": 0.55 - }, - { - "provider": "Azure/OpenAI", - "model": "o3-mini-2025-01-31", - "variant": "", - "input": 1.1, - "output": 4.4, - "cached_input": 0.55 - }, - { - "provider": "Azure/OpenAI", - "model": "o3-pro", - "variant": "", - "input": 20, - "output": 80 - }, - { - "provider": "Azure/OpenAI", - "model": "o3-pro", - "variant": "batches", - "input": 10, - "output": 40 - }, - { - "provider": "Azure/OpenAI", - "model": "o3-pro-2025-06-10", - "variant": "", - "input": 20, - "output": 80 - }, - { - "provider": "Azure/OpenAI", - "model": "o3-pro-2025-06-10", - "variant": "batches", - "input": 10, - "output": 40 - }, - { - "provider": "Azure/OpenAI", - "model": "o4-mini", - "variant": "", - "input": 1.1, - "output": 4.4, - "cached_input": 0.275 - }, - { - "provider": "Azure/OpenAI", - "model": "o4-mini-2025-04-16", - "variant": "", - "input": 1.1, - "output": 4.4, - "cached_input": 0.275 - }, - { - "provider": "Azure/OpenAI", - "model": "text-embedding-3-large", - "variant": "", - "input": 0.13, - "output": 0 - }, - { - "provider": "Azure/OpenAI", - "model": "text-embedding-3-small", - "variant": "", - "input": 0.02, - "output": 0 - }, - { - "provider": "Azure/OpenAI", - "model": "text-embedding-ada-002", - "variant": "", - "input": 0.1, - "output": 0 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-4.1-2025-04-14", - "variant": "", - "input": 2.2, - "output": 8.8, - "cached_input": 0.55 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-4.1-2025-04-14", - "variant": "batches", - "input": 1.1, - "output": 4.4 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-4.1-mini-2025-04-14", - "variant": "", - "input": 0.44, - "output": 1.76, - "cached_input": 0.11 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-4.1-mini-2025-04-14", - "variant": "batches", - "input": 0.22, - "output": 0.88 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-4.1-nano-2025-04-14", - "variant": "", - "input": 0.11, - "output": 0.44, - "cached_input": 0.025 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-4.1-nano-2025-04-14", - "variant": "batches", - "input": 0.06, - "output": 0.22 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-4o-2024-08-06", - "variant": "", - "input": 2.75, - "output": 11, - "cached_input": 1.375 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-4o-2024-11-20", - "variant": "", - "input": 2.75, - "output": 11 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-4o-mini-2024-07-18", - "variant": "", - "input": 0.165, - "output": 0.66, - "cached_input": 0.083 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-4o-mini-realtime-preview-2024-12-17", - "variant": "", - "input": 0.66, - "output": 2.64, - "cached_input": 0.33 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-4o-realtime-preview-2024-10-01", - "variant": "", - "input": 5.5, - "output": 22, - "cached_input": 2.75 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-4o-realtime-preview-2024-12-17", - "variant": "", - "input": 5.5, - "output": 22, - "cached_input": 2.75 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5-2025-08-07", - "variant": "", - "input": 1.375, - "output": 11, - "cached_input": 0.1375 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5-mini-2025-08-07", - "variant": "", - "input": 0.275, - "output": 2.2, - "cached_input": 0.0275 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5-nano-2025-08-07", - "variant": "", - "input": 0.055, - "output": 0.44, - "cached_input": 0.0055 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.1", - "variant": "", - "input": 1.38, - "output": 11, - "cached_input": 0.14 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.1-chat", - "variant": "", - "input": 1.38, - "output": 11, - "cached_input": 0.14 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.1-codex", - "variant": "", - "input": 1.38, - "output": 11, - "cached_input": 0.14 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.1-codex-mini", - "variant": "", - "input": 0.275, - "output": 2.2, - "cached_input": 0.028 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.4", - "variant": "", - "input": 2.75, - "output": 16.5, - "cached_input": 0.28 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.4", - "variant": "priority", - "input": 5.5, - "output": 33, - "cached_input": 0.55 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.4-2026-03-05", - "variant": "", - "input": 2.75, - "output": 16.5, - "cached_input": 0.28 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.4-2026-03-05", - "variant": "priority", - "input": 5.5, - "output": 33, - "cached_input": 0.55 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.5", - "variant": "", - "input": 5.5, - "output": 33, - "cached_input": 0.55 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.5", - "variant": "above_272k_tokens", - "input": 11, - "output": 49.5, - "cached_input": 1.1 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.5", - "variant": "priority", - "input": 13.75, - "output": 82.5, - "cached_input": 1.38 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.5-2026-04-23", - "variant": "", - "input": 5.5, - "output": 33, - "cached_input": 0.55 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.5-2026-04-23", - "variant": "above_272k_tokens", - "input": 11, - "output": 49.5, - "cached_input": 1.1 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.5-2026-04-23", - "variant": "priority", - "input": 13.75, - "output": 82.5, - "cached_input": 1.38 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.6", - "variant": "", - "input": 5.5, - "output": 33, - "cached_input": 0.55 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.6", - "variant": "above_272k_tokens", - "input": 11, - "output": 49.5, - "cached_input": 1.1 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.6", - "variant": "priority", - "input": 13.75, - "output": 82.5, - "cached_input": 1.375 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.6-luna", - "variant": "", - "input": 1.1, - "output": 6.6, - "cached_input": 0.11 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.6-luna", - "variant": "above_272k_tokens", - "input": 2.2, - "output": 9.9, - "cached_input": 0.22 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.6-luna", - "variant": "priority", - "input": 2.75, - "output": 16.5, - "cached_input": 0.275 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.6-sol", - "variant": "", - "input": 5.5, - "output": 33, - "cached_input": 0.55 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.6-sol", - "variant": "above_272k_tokens", - "input": 11, - "output": 49.5, - "cached_input": 1.1 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.6-sol", - "variant": "priority", - "input": 13.75, - "output": 82.5, - "cached_input": 1.375 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.6-terra", - "variant": "", - "input": 2.75, - "output": 16.5, - "cached_input": 0.275 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.6-terra", - "variant": "above_272k_tokens", - "input": 5.5, - "output": 24.75, - "cached_input": 0.55 - }, - { - "provider": "Azure/OpenAI", - "model": "us/gpt-5.6-terra", - "variant": "priority", - "input": 6.875, - "output": 41.25, - "cached_input": 0.6875 - }, - { - "provider": "Azure/OpenAI", - "model": "us/o1-2024-12-17", - "variant": "", - "input": 16.5, - "output": 66, - "cached_input": 8.25 - }, - { - "provider": "Azure/OpenAI", - "model": "us/o1-mini-2024-09-12", - "variant": "", - "input": 1.21, - "output": 4.84, - "cached_input": 0.605 - }, - { - "provider": "Azure/OpenAI", - "model": "us/o1-mini-2024-09-12", - "variant": "batches", - "input": 0.605, - "output": 2.42 - }, - { - "provider": "Azure/OpenAI", - "model": "us/o1-preview-2024-09-12", - "variant": "", - "input": 16.5, - "output": 66, - "cached_input": 8.25 - }, - { - "provider": "Azure/OpenAI", - "model": "us/o3-2025-04-16", - "variant": "", - "input": 2.2, - "output": 8.8, - "cached_input": 0.55 - }, - { - "provider": "Azure/OpenAI", - "model": "us/o3-mini-2025-01-31", - "variant": "", - "input": 1.21, - "output": 4.84, - "cached_input": 0.605 - }, - { - "provider": "Azure/OpenAI", - "model": "us/o3-mini-2025-01-31", - "variant": "batches", - "input": 0.605, - "output": 2.42 - }, - { - "provider": "Azure/OpenAI", - "model": "us/o4-mini-2025-04-16", - "variant": "", - "input": 1.21, - "output": 4.84, - "cached_input": 0.31 - }, - { - "provider": "Google/Gemini", - "model": "deep-research-pro-preview-12-2025", - "variant": "", - "input": 2, - "output": 12 - }, - { - "provider": "Google/Gemini", - "model": "deep-research-pro-preview-12-2025", - "variant": "batches", - "input": 1, - "output": 6 - }, - { - "provider": "Google/Gemini", - "model": "gemini-1.5-flash", - "variant": "", - "input": 0.075, - "output": 0 - }, - { - "provider": "Google/Gemini", - "model": "gemini-1.5-flash", - "variant": "above_128k_tokens", - "input": 0.15 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.0-flash", - "variant": "", - "input": 0.1, - "output": 0.4, - "cached_input": 0.025 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.0-flash-001", - "variant": "", - "input": 0.1, - "output": 0.4, - "cached_input": 0.025 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.0-flash-lite", - "variant": "", - "input": 0.075, - "output": 0.3, - "cached_input": 0.0188 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.0-flash-lite-001", - "variant": "", - "input": 0.075, - "output": 0.3, - "cached_input": 0.0188 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.5-computer-use-preview-10-2025", - "variant": "", - "input": 1.25, - "output": 10 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.5-computer-use-preview-10-2025", - "variant": "above_200k_tokens", - "input": 2.5, - "output": 15 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.5-flash", - "variant": "", - "input": 0.3, - "output": 2.5, - "cached_input": 0.03 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.5-flash-image", - "variant": "", - "input": 0.3, - "output": 2.5, - "cached_input": 0.03 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.5-flash-lite", - "variant": "", - "input": 0.1, - "output": 0.4, - "cached_input": 0.01 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.5-flash-lite-preview-06-17", - "variant": "", - "input": 0.1, - "output": 0.4, - "cached_input": 0.025 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.5-flash-lite-preview-09-2025", - "variant": "", - "input": 0.1, - "output": 0.4, - "cached_input": 0.01 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.5-flash-native-audio-latest", - "variant": "", - "input": 0.3, - "output": 2.5 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.5-flash-native-audio-preview-09-2025", - "variant": "", - "input": 0.3, - "output": 2.5 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.5-flash-native-audio-preview-12-2025", - "variant": "", - "input": 0.3, - "output": 2.5 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.5-flash-preview-09-2025", - "variant": "", - "input": 0.3, - "output": 2.5, - "cached_input": 0.075 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.5-flash-preview-tts", - "variant": "", - "input": 0.3, - "output": 2.5 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.5-pro", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.5-pro", - "variant": "above_200k_tokens", - "input": 2.5, - "output": 15, - "cached_input": 0.25 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.5-pro", - "variant": "above_200k_tokens_priority", - "input": 2.5, - "output": 15 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.5-pro", - "variant": "priority", - "input": 1.25, - "output": 10 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.5-pro-preview-tts", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "Google/Gemini", - "model": "gemini-2.5-pro-preview-tts", - "variant": "above_200k_tokens", - "input": 2.5, - "output": 15, - "cached_input": 0.25 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3-flash-preview", - "variant": "", - "input": 0.5, - "output": 3, - "cached_input": 0.05 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3-flash-preview", - "variant": "priority", - "input": 0.9, - "output": 5.4, - "cached_input": 0.09 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3-pro-image", - "variant": "", - "input": 2, - "output": 12 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3-pro-image", - "variant": "batches", - "input": 1, - "output": 6 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3-pro-image-preview", - "variant": "", - "input": 2, - "output": 12 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3-pro-image-preview", - "variant": "batches", - "input": 1, - "output": 6 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3-pro-preview", - "variant": "", - "input": 2, - "output": 12, - "cached_input": 0.2 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3-pro-preview", - "variant": "above_200k_tokens", - "input": 4, - "output": 18, - "cached_input": 0.4 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3-pro-preview", - "variant": "above_200k_tokens_priority", - "input": 7.2, - "output": 32.4, - "cached_input": 0.72 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3-pro-preview", - "variant": "batches", - "input": 1, - "output": 6 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3-pro-preview", - "variant": "priority", - "input": 3.6, - "output": 21.6, - "cached_input": 0.36 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.1-flash-image", - "variant": "", - "input": 0.25, - "output": 1.5 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.1-flash-image", - "variant": "batches", - "input": 0.125, - "output": 0.75 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.1-flash-image-preview", - "variant": "", - "input": 0.25, - "output": 1.5 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.1-flash-image-preview", - "variant": "batches", - "input": 0.125, - "output": 0.75 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.1-flash-lite", - "variant": "", - "input": 0.25, - "output": 1.5, - "cached_input": 0.025 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.1-flash-lite", - "variant": "batches", - "input": 0.125, - "output": 0.75 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.1-flash-lite", - "variant": "flex", - "input": 0.125, - "output": 0.75, - "cached_input": 0.0125 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.1-flash-lite", - "variant": "priority", - "input": 0.45, - "output": 2.7, - "cached_input": 0.045 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.1-flash-lite-preview", - "variant": "", - "input": 0.25, - "output": 1.5, - "cached_input": 0.025 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.1-flash-live-preview", - "variant": "", - "input": 0.75, - "output": 4.5 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.1-pro-preview", - "variant": "", - "input": 2, - "output": 12, - "cached_input": 0.2 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.1-pro-preview", - "variant": "above_200k_tokens", - "input": 4, - "output": 18, - "cached_input": 0.4 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.1-pro-preview", - "variant": "above_200k_tokens_priority", - "input": 7.2, - "output": 32.4, - "cached_input": 0.72 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.1-pro-preview", - "variant": "batches", - "input": 1, - "output": 6 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.1-pro-preview", - "variant": "priority", - "input": 3.6, - "output": 21.6, - "cached_input": 0.36 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.1-pro-preview-customtools", - "variant": "", - "input": 2, - "output": 12, - "cached_input": 0.2 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.1-pro-preview-customtools", - "variant": "above_200k_tokens", - "input": 4, - "output": 18, - "cached_input": 0.4 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.1-pro-preview-customtools", - "variant": "above_200k_tokens_priority", - "input": 7.2, - "output": 32.4, - "cached_input": 0.72 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.1-pro-preview-customtools", - "variant": "batches", - "input": 1, - "output": 6 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.1-pro-preview-customtools", - "variant": "priority", - "input": 3.6, - "output": 21.6, - "cached_input": 0.36 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.5-flash", - "variant": "", - "input": 1.5, - "output": 9, - "cached_input": 0.15 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.5-flash", - "variant": "priority", - "input": 2.7, - "output": 16.2, - "cached_input": 0.27 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.5-flash-lite", - "variant": "", - "input": 0.3, - "output": 2.5, - "cached_input": 0.03 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.5-flash-lite", - "variant": "batches", - "input": 0.15, - "output": 1.25 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.5-flash-lite", - "variant": "flex", - "input": 0.15, - "output": 1.25, - "cached_input": 0.02 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.5-flash-lite", - "variant": "priority", - "input": 0.54, - "output": 4.5, - "cached_input": 0.05 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.6-flash", - "variant": "", - "input": 1.5, - "output": 7.5, - "cached_input": 0.15 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.6-flash", - "variant": "batches", - "input": 0.75, - "output": 3.75 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.6-flash", - "variant": "flex", - "input": 0.75, - "output": 3.75, - "cached_input": 0.075 - }, - { - "provider": "Google/Gemini", - "model": "gemini-3.6-flash", - "variant": "priority", - "input": 2.7, - "output": 13.5, - "cached_input": 0.27 - }, - { - "provider": "Google/Gemini", - "model": "gemini-embedding-001", - "variant": "", - "input": 0.15, - "output": 0 - }, - { - "provider": "Google/Gemini", - "model": "gemini-embedding-2", - "variant": "", - "input": 0.2, - "output": 0 - }, - { - "provider": "Google/Gemini", - "model": "gemini-embedding-2-preview", - "variant": "", - "input": 0.2, - "output": 0 - }, - { - "provider": "Google/Gemini", - "model": "gemini-exp-1206", - "variant": "", - "input": 0.3, - "output": 2.5, - "cached_input": 0.03 - }, - { - "provider": "Google/Gemini", - "model": "gemini-flash-latest", - "variant": "", - "input": 0.3, - "output": 2.5, - "cached_input": 0.03 - }, - { - "provider": "Google/Gemini", - "model": "gemini-flash-lite-latest", - "variant": "", - "input": 0.1, - "output": 0.4, - "cached_input": 0.01 - }, - { - "provider": "Google/Gemini", - "model": "gemini-gemma-2-27b-it", - "variant": "", - "input": 0.35, - "output": 1.05 - }, - { - "provider": "Google/Gemini", - "model": "gemini-gemma-2-9b-it", - "variant": "", - "input": 0.35, - "output": 1.05 - }, - { - "provider": "Google/Gemini", - "model": "gemini-live-2.5-flash-preview-native-audio-09-2025", - "variant": "", - "input": 0.3, - "output": 2, - "cached_input": 0.075 - }, - { - "provider": "Google/Gemini", - "model": "gemini-omni-flash-preview", - "variant": "", - "input": 1.5, - "output": 9 - }, - { - "provider": "Google/Gemini", - "model": "gemini-pro-latest", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "Google/Gemini", - "model": "gemini-pro-latest", - "variant": "above_200k_tokens", - "input": 2.5, - "output": 15, - "cached_input": 0.25 - }, - { - "provider": "Google/Gemini", - "model": "gemini-robotics-er-1.5-preview", - "variant": "", - "input": 0.3, - "output": 2.5, - "cached_input": 0 - }, - { - "provider": "Google/Vertex", - "model": "deep-research-pro-preview-12-2025", - "variant": "", - "input": 2, - "output": 12 - }, - { - "provider": "Google/Vertex", - "model": "deep-research-pro-preview-12-2025", - "variant": "batches", - "input": 1, - "output": 6 - }, - { - "provider": "Google/Vertex", - "model": "gemini-2.0-flash", - "variant": "", - "input": 0.1, - "output": 0.4, - "cached_input": 0.025 - }, - { - "provider": "Google/Vertex", - "model": "gemini-2.0-flash-001", - "variant": "", - "input": 0.15, - "output": 0.6, - "cached_input": 0.0375 - }, - { - "provider": "Google/Vertex", - "model": "gemini-2.0-flash-lite", - "variant": "", - "input": 0.075, - "output": 0.3, - "cached_input": 0.0188 - }, - { - "provider": "Google/Vertex", - "model": "gemini-2.0-flash-lite-001", - "variant": "", - "input": 0.075, - "output": 0.3, - "cached_input": 0.0188 - }, - { - "provider": "Google/Vertex", - "model": "gemini-2.5-computer-use-preview-10-2025", - "variant": "", - "input": 1.25, - "output": 10 - }, - { - "provider": "Google/Vertex", - "model": "gemini-2.5-computer-use-preview-10-2025", - "variant": "above_200k_tokens", - "input": 2.5, - "output": 15 - }, - { - "provider": "Google/Vertex", - "model": "gemini-2.5-flash", - "variant": "", - "input": 0.3, - "output": 2.5, - "cached_input": 0.03 - }, - { - "provider": "Google/Vertex", - "model": "gemini-2.5-flash-image", - "variant": "", - "input": 0.3, - "output": 2.5, - "cached_input": 0.03 - }, - { - "provider": "Google/Vertex", - "model": "gemini-2.5-flash-lite", - "variant": "", - "input": 0.1, - "output": 0.4, - "cached_input": 0.01 - }, - { - "provider": "Google/Vertex", - "model": "gemini-2.5-flash-lite-preview-06-17", - "variant": "", - "input": 0.1, - "output": 0.4, - "cached_input": 0.025 - }, - { - "provider": "Google/Vertex", - "model": "gemini-2.5-flash-lite-preview-09-2025", - "variant": "", - "input": 0.1, - "output": 0.4, - "cached_input": 0.01 - }, - { - "provider": "Google/Vertex", - "model": "gemini-2.5-flash-preview-09-2025", - "variant": "", - "input": 0.3, - "output": 2.5, - "cached_input": 0.075 - }, - { - "provider": "Google/Vertex", - "model": "gemini-2.5-pro", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "Google/Vertex", - "model": "gemini-2.5-pro", - "variant": "above_200k_tokens", - "input": 2.5, - "output": 15, - "cached_input": 0.25 - }, - { - "provider": "Google/Vertex", - "model": "gemini-2.5-pro-preview-tts", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "Google/Vertex", - "model": "gemini-2.5-pro-preview-tts", - "variant": "above_200k_tokens", - "input": 2.5, - "output": 15, - "cached_input": 0.25 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3-flash-preview", - "variant": "", - "input": 0.5, - "output": 3, - "cached_input": 0.05 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3-flash-preview", - "variant": "priority", - "input": 0.9, - "output": 5.4, - "cached_input": 0.09 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3-pro-image", - "variant": "", - "input": 2, - "output": 12 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3-pro-image", - "variant": "batches", - "input": 1, - "output": 6 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3-pro-image-preview", - "variant": "", - "input": 2, - "output": 12 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3-pro-image-preview", - "variant": "batches", - "input": 1, - "output": 6 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3-pro-preview", - "variant": "", - "input": 2, - "output": 12, - "cached_input": 0.2 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3-pro-preview", - "variant": "above_200k_tokens", - "input": 4, - "output": 18, - "cached_input": 0.4 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3-pro-preview", - "variant": "above_200k_tokens_priority", - "input": 7.2, - "output": 32.4, - "cached_input": 0.72 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3-pro-preview", - "variant": "batches", - "input": 1, - "output": 6 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3-pro-preview", - "variant": "priority", - "input": 3.6, - "output": 21.6, - "cached_input": 0.36 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.1-flash-image", - "variant": "", - "input": 0.5, - "output": 3 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.1-flash-image-preview", - "variant": "", - "input": 0.5, - "output": 3 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.1-flash-lite", - "variant": "", - "input": 0.25, - "output": 1.5, - "cached_input": 0.025 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.1-flash-lite", - "variant": "batches", - "input": 0.125, - "output": 0.75 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.1-flash-lite", - "variant": "flex", - "input": 0.125, - "output": 0.75, - "cached_input": 0.0125 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.1-flash-lite", - "variant": "priority", - "input": 0.45, - "output": 2.7, - "cached_input": 0.045 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.1-flash-lite-preview", - "variant": "", - "input": 0.25, - "output": 1.5, - "cached_input": 0.025 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.1-pro-preview", - "variant": "", - "input": 2, - "output": 12, - "cached_input": 0.2 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.1-pro-preview", - "variant": "above_200k_tokens", - "input": 4, - "output": 18, - "cached_input": 0.4 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.1-pro-preview", - "variant": "above_200k_tokens_priority", - "input": 7.2, - "output": 32.4, - "cached_input": 0.72 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.1-pro-preview", - "variant": "batches", - "input": 1, - "output": 6 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.1-pro-preview", - "variant": "priority", - "input": 3.6, - "output": 21.6, - "cached_input": 0.36 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.1-pro-preview-customtools", - "variant": "", - "input": 2, - "output": 12, - "cached_input": 0.2 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.1-pro-preview-customtools", - "variant": "above_200k_tokens", - "input": 4, - "output": 18, - "cached_input": 0.4 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.1-pro-preview-customtools", - "variant": "batches", - "input": 1, - "output": 6 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.5-flash", - "variant": "", - "input": 1.5, - "output": 9, - "cached_input": 0.15 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.5-flash", - "variant": "priority", - "input": 2.7, - "output": 16.2, - "cached_input": 0.27 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.5-flash-lite", - "variant": "", - "input": 0.3, - "output": 2.5, - "cached_input": 0.03 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.5-flash-lite", - "variant": "batches", - "input": 0.15, - "output": 1.25 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.5-flash-lite", - "variant": "flex", - "input": 0.15, - "output": 1.25, - "cached_input": 0.02 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.5-flash-lite", - "variant": "priority", - "input": 0.54, - "output": 4.5, - "cached_input": 0.05 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.6-flash", - "variant": "", - "input": 1.5, - "output": 7.5, - "cached_input": 0.15 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.6-flash", - "variant": "batches", - "input": 0.75, - "output": 3.75 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.6-flash", - "variant": "flex", - "input": 0.75, - "output": 3.75, - "cached_input": 0.075 - }, - { - "provider": "Google/Vertex", - "model": "gemini-3.6-flash", - "variant": "priority", - "input": 2.7, - "output": 13.5, - "cached_input": 0.27 - }, - { - "provider": "Google/Vertex", - "model": "gemini-live-2.5-flash-preview-native-audio-09-2025", - "variant": "", - "input": 0.3, - "output": 2, - "cached_input": 0.075 - }, - { - "provider": "Google/Vertex", - "model": "gemini-omni-flash-preview", - "variant": "", - "input": 1.5, - "output": 9 - }, - { - "provider": "Google/Vertex", - "model": "gemini-robotics-er-1.5-preview", - "variant": "", - "input": 0.3, - "output": 2.5, - "cached_input": 0 - }, - { - "provider": "Google/Vertex", - "model": "vertex_ai/deep-research-pro-preview-12-2025", - "variant": "", - "input": 2, - "output": 12 - }, - { - "provider": "Google/Vertex", - "model": "vertex_ai/deep-research-pro-preview-12-2025", - "variant": "batches", - "input": 1, - "output": 6 - }, - { - "provider": "Google/Vertex", - "model": "vertex_ai/gemini-2.5-flash-image", - "variant": "", - "input": 0.3, - "output": 2.5, - "cached_input": 0.03 - }, - { - "provider": "Google/Vertex", - "model": "vertex_ai/gemini-3-pro-image", - "variant": "", - "input": 2, - "output": 12 - }, - { - "provider": "Google/Vertex", - "model": "vertex_ai/gemini-3-pro-image", - "variant": "batches", - "input": 1, - "output": 6 - }, - { - "provider": "Google/Vertex", - "model": "vertex_ai/gemini-3-pro-image-preview", - "variant": "", - "input": 2, - "output": 12 - }, - { - "provider": "Google/Vertex", - "model": "vertex_ai/gemini-3-pro-image-preview", - "variant": "batches", - "input": 1, - "output": 6 - }, - { - "provider": "Google/Vertex", - "model": "vertex_ai/gemini-3.1-flash-image", - "variant": "", - "input": 0.5, - "output": 3 - }, - { - "provider": "Google/Vertex", - "model": "vertex_ai/gemini-3.1-flash-image-preview", - "variant": "", - "input": 0.5, - "output": 3 - }, - { - "provider": "Google/Vertex", - "model": "vertex_ai/gemini-3.1-flash-lite", - "variant": "", - "input": 0.25, - "output": 1.5, - "cached_input": 0.025 - }, - { - "provider": "Google/Vertex", - "model": "vertex_ai/gemini-3.1-flash-lite", - "variant": "batches", - "input": 0.125, - "output": 0.75 - }, - { - "provider": "Google/Vertex", - "model": "vertex_ai/gemini-3.1-flash-lite", - "variant": "flex", - "input": 0.125, - "output": 0.75, - "cached_input": 0.0125 - }, - { - "provider": "Google/Vertex", - "model": "vertex_ai/gemini-3.1-flash-lite", - "variant": "priority", - "input": 0.45, - "output": 2.7, - "cached_input": 0.045 - }, - { - "provider": "Google/Vertex", - "model": "vertex_ai/gemini-3.1-flash-lite-preview", - "variant": "", - "input": 0.25, - "output": 1.5, - "cached_input": 0.025 - }, - { - "provider": "Google/Vertex", - "model": "vertex_ai/gemini-3.5-flash-lite", - "variant": "", - "input": 0.3, - "output": 2.5, - "cached_input": 0.03 - }, - { - "provider": "Google/Vertex", - "model": "vertex_ai/gemini-3.5-flash-lite", - "variant": "batches", - "input": 0.15, - "output": 1.25 - }, - { - "provider": "Google/Vertex", - "model": "vertex_ai/gemini-3.5-flash-lite", - "variant": "flex", - "input": 0.15, - "output": 1.25, - "cached_input": 0.02 - }, - { - "provider": "Google/Vertex", - "model": "vertex_ai/gemini-3.5-flash-lite", - "variant": "priority", - "input": 0.54, - "output": 4.5, - "cached_input": 0.05 - }, - { - "provider": "Groq", - "model": "gemma-7b-it", - "variant": "", - "input": 0.05, - "output": 0.08 - }, - { - "provider": "Groq", - "model": "llama-3.1-8b-instant", - "variant": "", - "input": 0.05, - "output": 0.08 - }, - { - "provider": "Groq", - "model": "llama-3.3-70b-versatile", - "variant": "", - "input": 0.59, - "output": 0.79 - }, - { - "provider": "Groq", - "model": "meta-llama/llama-4-maverick-17b-128e-instruct", - "variant": "", - "input": 0.2, - "output": 0.6 - }, - { - "provider": "Groq", - "model": "meta-llama/llama-4-scout-17b-16e-instruct", - "variant": "", - "input": 0.11, - "output": 0.34 - }, - { - "provider": "Groq", - "model": "meta-llama/llama-guard-4-12b", - "variant": "", - "input": 0.2, - "output": 0.2 - }, - { - "provider": "Groq", - "model": "moonshotai/kimi-k2-instruct-0905", - "variant": "", - "input": 1, - "output": 3, - "cached_input": 0.5 - }, - { - "provider": "Groq", - "model": "openai/gpt-oss-120b", - "variant": "", - "input": 0.15, - "output": 0.6, - "cached_input": 0.075 - }, - { - "provider": "Groq", - "model": "openai/gpt-oss-20b", - "variant": "", - "input": 0.075, - "output": 0.3, - "cached_input": 0.0375 - }, - { - "provider": "Groq", - "model": "openai/gpt-oss-safeguard-20b", - "variant": "", - "input": 0.075, - "output": 0.3, - "cached_input": 0.037 - }, - { - "provider": "Groq", - "model": "qwen/qwen3-32b", - "variant": "", - "input": 0.29, - "output": 0.59 - }, - { - "provider": "Mistral", - "model": "codestral-2405", - "variant": "", - "input": 1, - "output": 3 - }, - { - "provider": "Mistral", - "model": "codestral-2508", - "variant": "", - "input": 0.3, - "output": 0.9 - }, - { - "provider": "Mistral", - "model": "codestral-embed", - "variant": "", - "input": 0.15 - }, - { - "provider": "Mistral", - "model": "codestral-embed-2505", - "variant": "", - "input": 0.15 - }, - { - "provider": "Mistral", - "model": "codestral-latest", - "variant": "", - "input": 1, - "output": 3 - }, - { - "provider": "Mistral", - "model": "codestral-mamba-latest", - "variant": "", - "input": 0.25, - "output": 0.25 - }, - { - "provider": "Mistral", - "model": "devstral-2512", - "variant": "", - "input": 0.4, - "output": 2 - }, - { - "provider": "Mistral", - "model": "devstral-latest", - "variant": "", - "input": 0.4, - "output": 2 - }, - { - "provider": "Mistral", - "model": "devstral-medium-2507", - "variant": "", - "input": 0.4, - "output": 2 - }, - { - "provider": "Mistral", - "model": "devstral-medium-latest", - "variant": "", - "input": 0.4, - "output": 2 - }, - { - "provider": "Mistral", - "model": "devstral-small-2505", - "variant": "", - "input": 0.1, - "output": 0.3 - }, - { - "provider": "Mistral", - "model": "devstral-small-2507", - "variant": "", - "input": 0.1, - "output": 0.3 - }, - { - "provider": "Mistral", - "model": "devstral-small-latest", - "variant": "", - "input": 0.1, - "output": 0.3 - }, - { - "provider": "Mistral", - "model": "labs-devstral-small-2512", - "variant": "", - "input": 0.1, - "output": 0.3 - }, - { - "provider": "Mistral", - "model": "magistral-medium-1-2-2509", - "variant": "", - "input": 2, - "output": 5 - }, - { - "provider": "Mistral", - "model": "magistral-medium-2506", - "variant": "", - "input": 2, - "output": 5 - }, - { - "provider": "Mistral", - "model": "magistral-medium-2509", - "variant": "", - "input": 2, - "output": 5 - }, - { - "provider": "Mistral", - "model": "magistral-medium-latest", - "variant": "", - "input": 2, - "output": 5 - }, - { - "provider": "Mistral", - "model": "magistral-small-1-2-2509", - "variant": "", - "input": 0.5, - "output": 1.5 - }, - { - "provider": "Mistral", - "model": "magistral-small-2506", - "variant": "", - "input": 0.5, - "output": 1.5 - }, - { - "provider": "Mistral", - "model": "magistral-small-latest", - "variant": "", - "input": 0.5, - "output": 1.5 - }, - { - "provider": "Mistral", - "model": "ministral-3-14b-2512", - "variant": "", - "input": 0.2, - "output": 0.2 - }, - { - "provider": "Mistral", - "model": "ministral-3-3b-2512", - "variant": "", - "input": 0.1, - "output": 0.1 - }, - { - "provider": "Mistral", - "model": "ministral-3-8b-2512", - "variant": "", - "input": 0.15, - "output": 0.15 - }, - { - "provider": "Mistral", - "model": "ministral-8b-2512", - "variant": "", - "input": 0.15, - "output": 0.15 - }, - { - "provider": "Mistral", - "model": "ministral-8b-latest", - "variant": "", - "input": 0.15, - "output": 0.15 - }, - { - "provider": "Mistral", - "model": "mistral-embed", - "variant": "", - "input": 0.1 - }, - { - "provider": "Mistral", - "model": "mistral-large-2402", - "variant": "", - "input": 4, - "output": 12 - }, - { - "provider": "Mistral", - "model": "mistral-large-2407", - "variant": "", - "input": 3, - "output": 9 - }, - { - "provider": "Mistral", - "model": "mistral-large-2411", - "variant": "", - "input": 2, - "output": 6 - }, - { - "provider": "Mistral", - "model": "mistral-large-2512", - "variant": "", - "input": 0.5, - "output": 1.5 - }, - { - "provider": "Mistral", - "model": "mistral-large-3", - "variant": "", - "input": 0.5, - "output": 1.5 - }, - { - "provider": "Mistral", - "model": "mistral-large-latest", - "variant": "", - "input": 0.5, - "output": 1.5 - }, - { - "provider": "Mistral", - "model": "mistral-medium", - "variant": "", - "input": 2.7, - "output": 8.1 - }, - { - "provider": "Mistral", - "model": "mistral-medium-2312", - "variant": "", - "input": 2.7, - "output": 8.1 - }, - { - "provider": "Mistral", - "model": "mistral-medium-2505", - "variant": "", - "input": 0.4, - "output": 2 - }, - { - "provider": "Mistral", - "model": "mistral-medium-2508", - "variant": "", - "input": 0.4, - "output": 2 - }, - { - "provider": "Mistral", - "model": "mistral-medium-2604", - "variant": "", - "input": 1.5, - "output": 7.5 - }, - { - "provider": "Mistral", - "model": "mistral-medium-3-1-2508", - "variant": "", - "input": 0.4, - "output": 2 - }, - { - "provider": "Mistral", - "model": "mistral-medium-3-5", - "variant": "", - "input": 1.5, - "output": 7.5 - }, - { - "provider": "Mistral", - "model": "mistral-medium-latest", - "variant": "", - "input": 1.5, - "output": 7.5 - }, - { - "provider": "Mistral", - "model": "mistral-small", - "variant": "", - "input": 0.1, - "output": 0.3 - }, - { - "provider": "Mistral", - "model": "mistral-small-3-2-2506", - "variant": "", - "input": 0.06, - "output": 0.18 - }, - { - "provider": "Mistral", - "model": "mistral-small-latest", - "variant": "", - "input": 0.06, - "output": 0.18 - }, - { - "provider": "Mistral", - "model": "mistral-tiny", - "variant": "", - "input": 0.25, - "output": 0.25 - }, - { - "provider": "Mistral", - "model": "open-codestral-mamba", - "variant": "", - "input": 0.25, - "output": 0.25 - }, - { - "provider": "Mistral", - "model": "open-mistral-7b", - "variant": "", - "input": 0.25, - "output": 0.25 - }, - { - "provider": "Mistral", - "model": "open-mistral-nemo", - "variant": "", - "input": 0.3, - "output": 0.3 - }, - { - "provider": "Mistral", - "model": "open-mistral-nemo-2407", - "variant": "", - "input": 0.3, - "output": 0.3 - }, - { - "provider": "Mistral", - "model": "open-mixtral-8x22b", - "variant": "", - "input": 2, - "output": 6 - }, - { - "provider": "Mistral", - "model": "open-mixtral-8x7b", - "variant": "", - "input": 0.7, - "output": 0.7 - }, - { - "provider": "Mistral", - "model": "pixtral-12b-2409", - "variant": "", - "input": 0.15, - "output": 0.15 - }, - { - "provider": "Mistral", - "model": "pixtral-large-2411", - "variant": "", - "input": 2, - "output": 6 - }, - { - "provider": "Mistral", - "model": "pixtral-large-latest", - "variant": "", - "input": 2, - "output": 6 - }, - { - "provider": "OpenAI", - "model": "chatgpt-4o-latest", - "variant": "", - "input": 5, - "output": 15 - }, - { - "provider": "OpenAI", - "model": "chatgpt-image-latest", - "variant": "", - "input": 5, - "cached_input": 1.25 - }, - { - "provider": "OpenAI", - "model": "codex-mini-latest", - "variant": "", - "input": 1.5, - "output": 6, - "cached_input": 0.375 - }, - { - "provider": "OpenAI", - "model": "ft:gpt-3.5-turbo", - "variant": "", - "input": 3, - "output": 6 - }, - { - "provider": "OpenAI", - "model": "ft:gpt-3.5-turbo", - "variant": "batches", - "input": 1.5, - "output": 3 - }, - { - "provider": "OpenAI", - "model": "ft:gpt-3.5-turbo-0125", - "variant": "", - "input": 3, - "output": 6 - }, - { - "provider": "OpenAI", - "model": "ft:gpt-3.5-turbo-0613", - "variant": "", - "input": 3, - "output": 6 - }, - { - "provider": "OpenAI", - "model": "ft:gpt-3.5-turbo-1106", - "variant": "", - "input": 3, - "output": 6 - }, - { - "provider": "OpenAI", - "model": "ft:gpt-4-0613", - "variant": "", - "input": 30, - "output": 60 - }, - { - "provider": "OpenAI", - "model": "ft:gpt-4.1-2025-04-14", - "variant": "", - "input": 3, - "output": 12, - "cached_input": 0.75 - }, - { - "provider": "OpenAI", - "model": "ft:gpt-4.1-2025-04-14", - "variant": "batches", - "input": 1.5, - "output": 6 - }, - { - "provider": "OpenAI", - "model": "ft:gpt-4.1-mini-2025-04-14", - "variant": "", - "input": 0.8, - "output": 3.2, - "cached_input": 0.2 - }, - { - "provider": "OpenAI", - "model": "ft:gpt-4.1-mini-2025-04-14", - "variant": "batches", - "input": 0.4, - "output": 1.6 - }, - { - "provider": "OpenAI", - "model": "ft:gpt-4.1-nano-2025-04-14", - "variant": "", - "input": 0.2, - "output": 0.8, - "cached_input": 0.05 - }, - { - "provider": "OpenAI", - "model": "ft:gpt-4.1-nano-2025-04-14", - "variant": "batches", - "input": 0.1, - "output": 0.4 - }, - { - "provider": "OpenAI", - "model": "ft:gpt-4o-2024-08-06", - "variant": "", - "input": 3.75, - "output": 15, - "cached_input": 1.875 - }, - { - "provider": "OpenAI", - "model": "ft:gpt-4o-2024-08-06", - "variant": "batches", - "input": 1.875, - "output": 7.5 - }, - { - "provider": "OpenAI", - "model": "ft:gpt-4o-2024-11-20", - "variant": "", - "input": 3.75, - "output": 15 - }, - { - "provider": "OpenAI", - "model": "ft:gpt-4o-mini-2024-07-18", - "variant": "", - "input": 0.3, - "output": 1.2, - "cached_input": 0.15 - }, - { - "provider": "OpenAI", - "model": "ft:gpt-4o-mini-2024-07-18", - "variant": "batches", - "input": 0.15, - "output": 0.6 - }, - { - "provider": "OpenAI", - "model": "ft:o4-mini-2025-04-16", - "variant": "", - "input": 4, - "output": 16, - "cached_input": 1 - }, - { - "provider": "OpenAI", - "model": "ft:o4-mini-2025-04-16", - "variant": "batches", - "input": 2, - "output": 8 - }, - { - "provider": "OpenAI", - "model": "gpt-3.5-turbo", - "variant": "", - "input": 0.5, - "output": 1.5 - }, - { - "provider": "OpenAI", - "model": "gpt-3.5-turbo-0125", - "variant": "", - "input": 0.5, - "output": 1.5 - }, - { - "provider": "OpenAI", - "model": "gpt-3.5-turbo-1106", - "variant": "", - "input": 1, - "output": 2 - }, - { - "provider": "OpenAI", - "model": "gpt-3.5-turbo-16k", - "variant": "", - "input": 3, - "output": 4 - }, - { - "provider": "OpenAI", - "model": "gpt-4", - "variant": "", - "input": 30, - "output": 60 - }, - { - "provider": "OpenAI", - "model": "gpt-4-0125-preview", - "variant": "", - "input": 10, - "output": 30 - }, - { - "provider": "OpenAI", - "model": "gpt-4-0314", - "variant": "", - "input": 30, - "output": 60 - }, - { - "provider": "OpenAI", - "model": "gpt-4-0613", - "variant": "", - "input": 30, - "output": 60 - }, - { - "provider": "OpenAI", - "model": "gpt-4-1106-preview", - "variant": "", - "input": 10, - "output": 30 - }, - { - "provider": "OpenAI", - "model": "gpt-4-turbo", - "variant": "", - "input": 10, - "output": 30 - }, - { - "provider": "OpenAI", - "model": "gpt-4-turbo-2024-04-09", - "variant": "", - "input": 10, - "output": 30 - }, - { - "provider": "OpenAI", - "model": "gpt-4-turbo-preview", - "variant": "", - "input": 10, - "output": 30 - }, - { - "provider": "OpenAI", - "model": "gpt-4.1", - "variant": "", - "input": 2, - "output": 8, - "cached_input": 0.5 - }, - { - "provider": "OpenAI", - "model": "gpt-4.1", - "variant": "batches", - "input": 1, - "output": 4 - }, - { - "provider": "OpenAI", - "model": "gpt-4.1", - "variant": "priority", - "input": 3.5, - "output": 14, - "cached_input": 0.875 - }, - { - "provider": "OpenAI", - "model": "gpt-4.1-2025-04-14", - "variant": "", - "input": 2, - "output": 8, - "cached_input": 0.5 - }, - { - "provider": "OpenAI", - "model": "gpt-4.1-2025-04-14", - "variant": "batches", - "input": 1, - "output": 4 - }, - { - "provider": "OpenAI", - "model": "gpt-4.1-mini", - "variant": "", - "input": 0.4, - "output": 1.6, - "cached_input": 0.1 - }, - { - "provider": "OpenAI", - "model": "gpt-4.1-mini", - "variant": "batches", - "input": 0.2, - "output": 0.8 - }, - { - "provider": "OpenAI", - "model": "gpt-4.1-mini", - "variant": "priority", - "input": 0.7, - "output": 2.8, - "cached_input": 0.175 - }, - { - "provider": "OpenAI", - "model": "gpt-4.1-mini-2025-04-14", - "variant": "", - "input": 0.4, - "output": 1.6, - "cached_input": 0.1 - }, - { - "provider": "OpenAI", - "model": "gpt-4.1-mini-2025-04-14", - "variant": "batches", - "input": 0.2, - "output": 0.8 - }, - { - "provider": "OpenAI", - "model": "gpt-4.1-nano", - "variant": "", - "input": 0.1, - "output": 0.4, - "cached_input": 0.025 - }, - { - "provider": "OpenAI", - "model": "gpt-4.1-nano", - "variant": "batches", - "input": 0.05, - "output": 0.2 - }, - { - "provider": "OpenAI", - "model": "gpt-4.1-nano", - "variant": "priority", - "input": 0.2, - "output": 0.8, - "cached_input": 0.05 - }, - { - "provider": "OpenAI", - "model": "gpt-4.1-nano-2025-04-14", - "variant": "", - "input": 0.1, - "output": 0.4, - "cached_input": 0.025 - }, - { - "provider": "OpenAI", - "model": "gpt-4.1-nano-2025-04-14", - "variant": "batches", - "input": 0.05, - "output": 0.2 - }, - { - "provider": "OpenAI", - "model": "gpt-4o", - "variant": "", - "input": 2.5, - "output": 10, - "cached_input": 1.25 - }, - { - "provider": "OpenAI", - "model": "gpt-4o", - "variant": "batches", - "input": 1.25, - "output": 5 - }, - { - "provider": "OpenAI", - "model": "gpt-4o", - "variant": "priority", - "input": 4.25, - "output": 17, - "cached_input": 2.125 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-2024-05-13", - "variant": "", - "input": 5, - "output": 15 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-2024-05-13", - "variant": "batches", - "input": 2.5, - "output": 7.5 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-2024-05-13", - "variant": "priority", - "input": 8.75, - "output": 26.25 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-2024-08-06", - "variant": "", - "input": 2.5, - "output": 10, - "cached_input": 1.25 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-2024-08-06", - "variant": "batches", - "input": 1.25, - "output": 5 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-2024-11-20", - "variant": "", - "input": 2.5, - "output": 10, - "cached_input": 1.25 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-2024-11-20", - "variant": "batches", - "input": 1.25, - "output": 5 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-audio-preview", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-audio-preview-2024-12-17", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-audio-preview-2025-06-03", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-mini", - "variant": "", - "input": 0.15, - "output": 0.6, - "cached_input": 0.075 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-mini", - "variant": "batches", - "input": 0.075, - "output": 0.3 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-mini", - "variant": "priority", - "input": 0.25, - "output": 1, - "cached_input": 0.125 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-mini-2024-07-18", - "variant": "", - "input": 0.15, - "output": 0.6, - "cached_input": 0.075 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-mini-2024-07-18", - "variant": "batches", - "input": 0.075, - "output": 0.3 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-mini-audio-preview", - "variant": "", - "input": 0.15, - "output": 0.6 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-mini-audio-preview-2024-12-17", - "variant": "", - "input": 0.15, - "output": 0.6 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-mini-realtime-preview", - "variant": "", - "input": 0.6, - "output": 2.4, - "cached_input": 0.3 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-mini-realtime-preview-2024-12-17", - "variant": "", - "input": 0.6, - "output": 2.4, - "cached_input": 0.3 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-mini-search-preview", - "variant": "", - "input": 0.15, - "output": 0.6, - "cached_input": 0.075 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-mini-search-preview", - "variant": "batches", - "input": 0.075, - "output": 0.3 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-mini-search-preview-2025-03-11", - "variant": "", - "input": 0.15, - "output": 0.6, - "cached_input": 0.075 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-mini-search-preview-2025-03-11", - "variant": "batches", - "input": 0.075, - "output": 0.3 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-mini-transcribe", - "variant": "", - "input": 1.25, - "output": 5 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-mini-transcribe-2025-03-20", - "variant": "", - "input": 1.25, - "output": 5 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-mini-transcribe-2025-12-15", - "variant": "", - "input": 1.25, - "output": 5 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-mini-tts", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-mini-tts-2025-03-20", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-mini-tts-2025-12-15", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-realtime-preview", - "variant": "", - "input": 5, - "output": 20, - "cached_input": 2.5 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-realtime-preview-2024-12-17", - "variant": "", - "input": 5, - "output": 20, - "cached_input": 2.5 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-realtime-preview-2025-06-03", - "variant": "", - "input": 5, - "output": 20, - "cached_input": 2.5 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-search-preview", - "variant": "", - "input": 2.5, - "output": 10, - "cached_input": 1.25 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-search-preview", - "variant": "batches", - "input": 1.25, - "output": 5 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-search-preview-2025-03-11", - "variant": "", - "input": 2.5, - "output": 10, - "cached_input": 1.25 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-search-preview-2025-03-11", - "variant": "batches", - "input": 1.25, - "output": 5 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-transcribe", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "OpenAI", - "model": "gpt-4o-transcribe-diarize", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "OpenAI", - "model": "gpt-5", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "OpenAI", - "model": "gpt-5", - "variant": "flex", - "input": 0.625, - "output": 5, - "cached_input": 0.0625 - }, - { - "provider": "OpenAI", - "model": "gpt-5", - "variant": "priority", - "input": 2.5, - "output": 20, - "cached_input": 0.25 - }, - { - "provider": "OpenAI", - "model": "gpt-5-2025-08-07", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "OpenAI", - "model": "gpt-5-2025-08-07", - "variant": "flex", - "input": 0.625, - "output": 5, - "cached_input": 0.0625 - }, - { - "provider": "OpenAI", - "model": "gpt-5-2025-08-07", - "variant": "priority", - "input": 2.5, - "output": 20, - "cached_input": 0.25 - }, - { - "provider": "OpenAI", - "model": "gpt-5-chat", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "OpenAI", - "model": "gpt-5-chat-latest", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "OpenAI", - "model": "gpt-5-codex", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "OpenAI", - "model": "gpt-5-mini", - "variant": "", - "input": 0.25, - "output": 2, - "cached_input": 0.025 - }, - { - "provider": "OpenAI", - "model": "gpt-5-mini", - "variant": "flex", - "input": 0.125, - "output": 1, - "cached_input": 0.0125 - }, - { - "provider": "OpenAI", - "model": "gpt-5-mini", - "variant": "priority", - "input": 0.45, - "output": 3.6, - "cached_input": 0.045 - }, - { - "provider": "OpenAI", - "model": "gpt-5-mini-2025-08-07", - "variant": "", - "input": 0.25, - "output": 2, - "cached_input": 0.025 - }, - { - "provider": "OpenAI", - "model": "gpt-5-mini-2025-08-07", - "variant": "flex", - "input": 0.125, - "output": 1, - "cached_input": 0.0125 - }, - { - "provider": "OpenAI", - "model": "gpt-5-mini-2025-08-07", - "variant": "priority", - "input": 0.45, - "output": 3.6, - "cached_input": 0.045 - }, - { - "provider": "OpenAI", - "model": "gpt-5-nano", - "variant": "", - "input": 0.05, - "output": 0.4, - "cached_input": 0.005 - }, - { - "provider": "OpenAI", - "model": "gpt-5-nano", - "variant": "flex", - "input": 0.025, - "output": 0.2, - "cached_input": 0.0025 - }, - { - "provider": "OpenAI", - "model": "gpt-5-nano", - "variant": "priority", - "input": 2.5 - }, - { - "provider": "OpenAI", - "model": "gpt-5-nano-2025-08-07", - "variant": "", - "input": 0.05, - "output": 0.4, - "cached_input": 0.005 - }, - { - "provider": "OpenAI", - "model": "gpt-5-nano-2025-08-07", - "variant": "flex", - "input": 0.025, - "output": 0.2, - "cached_input": 0.0025 - }, - { - "provider": "OpenAI", - "model": "gpt-5-pro", - "variant": "", - "input": 15, - "output": 120 - }, - { - "provider": "OpenAI", - "model": "gpt-5-pro", - "variant": "batches", - "input": 7.5, - "output": 60 - }, - { - "provider": "OpenAI", - "model": "gpt-5-pro-2025-10-06", - "variant": "", - "input": 15, - "output": 120 - }, - { - "provider": "OpenAI", - "model": "gpt-5-pro-2025-10-06", - "variant": "batches", - "input": 7.5, - "output": 60 - }, - { - "provider": "OpenAI", - "model": "gpt-5-search-api", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "OpenAI", - "model": "gpt-5-search-api-2025-10-14", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "OpenAI", - "model": "gpt-5.1", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "OpenAI", - "model": "gpt-5.1", - "variant": "priority", - "input": 2.5, - "output": 20, - "cached_input": 0.25 - }, - { - "provider": "OpenAI", - "model": "gpt-5.1-2025-11-13", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "OpenAI", - "model": "gpt-5.1-2025-11-13", - "variant": "priority", - "input": 2.5, - "output": 20, - "cached_input": 0.25 - }, - { - "provider": "OpenAI", - "model": "gpt-5.1-chat-latest", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "OpenAI", - "model": "gpt-5.1-chat-latest", - "variant": "priority", - "input": 2.5, - "output": 20, - "cached_input": 0.25 - }, - { - "provider": "OpenAI", - "model": "gpt-5.1-codex", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "OpenAI", - "model": "gpt-5.1-codex", - "variant": "priority", - "input": 2.5, - "output": 20, - "cached_input": 0.25 - }, - { - "provider": "OpenAI", - "model": "gpt-5.1-codex-max", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "OpenAI", - "model": "gpt-5.1-codex-mini", - "variant": "", - "input": 0.25, - "output": 2, - "cached_input": 0.025 - }, - { - "provider": "OpenAI", - "model": "gpt-5.1-codex-mini", - "variant": "priority", - "input": 0.45, - "output": 3.6, - "cached_input": 0.045 - }, - { - "provider": "OpenAI", - "model": "gpt-5.2", - "variant": "", - "input": 1.75, - "output": 14, - "cached_input": 0.175 - }, - { - "provider": "OpenAI", - "model": "gpt-5.2", - "variant": "priority", - "input": 3.5, - "output": 28, - "cached_input": 0.35 - }, - { - "provider": "OpenAI", - "model": "gpt-5.2-2025-12-11", - "variant": "", - "input": 1.75, - "output": 14, - "cached_input": 0.175 - }, - { - "provider": "OpenAI", - "model": "gpt-5.2-2025-12-11", - "variant": "priority", - "input": 3.5, - "output": 28, - "cached_input": 0.35 - }, - { - "provider": "OpenAI", - "model": "gpt-5.2-chat-latest", - "variant": "", - "input": 1.75, - "output": 14, - "cached_input": 0.175 - }, - { - "provider": "OpenAI", - "model": "gpt-5.2-chat-latest", - "variant": "priority", - "input": 3.5, - "output": 28, - "cached_input": 0.35 - }, - { - "provider": "OpenAI", - "model": "gpt-5.2-codex", - "variant": "", - "input": 1.75, - "output": 14, - "cached_input": 0.175 - }, - { - "provider": "OpenAI", - "model": "gpt-5.2-codex", - "variant": "priority", - "input": 3.5, - "output": 28, - "cached_input": 0.35 - }, - { - "provider": "OpenAI", - "model": "gpt-5.2-pro", - "variant": "", - "input": 21, - "output": 168 - }, - { - "provider": "OpenAI", - "model": "gpt-5.2-pro-2025-12-11", - "variant": "", - "input": 21, - "output": 168 - }, - { - "provider": "OpenAI", - "model": "gpt-5.3-chat-latest", - "variant": "", - "input": 1.75, - "output": 14, - "cached_input": 0.175 - }, - { - "provider": "OpenAI", - "model": "gpt-5.3-chat-latest", - "variant": "priority", - "input": 3.5, - "output": 28, - "cached_input": 0.35 - }, - { - "provider": "OpenAI", - "model": "gpt-5.3-codex", - "variant": "", - "input": 1.75, - "output": 14, - "cached_input": 0.175 - }, - { - "provider": "OpenAI", - "model": "gpt-5.3-codex", - "variant": "priority", - "input": 3.5, - "output": 28, - "cached_input": 0.35 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4", - "variant": "", - "input": 2.5, - "output": 15, - "cached_input": 0.25 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4", - "variant": "above_272k_tokens", - "input": 5, - "output": 22.5, - "cached_input": 0.5 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4", - "variant": "batches", - "input": 1.25, - "output": 7.5 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4", - "variant": "flex", - "input": 1.25, - "output": 7.5, - "cached_input": 0.13 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4", - "variant": "priority", - "input": 5, - "output": 30, - "cached_input": 0.5 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-2026-03-05", - "variant": "", - "input": 2.5, - "output": 15, - "cached_input": 0.25 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-2026-03-05", - "variant": "above_272k_tokens", - "input": 5, - "output": 22.5, - "cached_input": 0.5 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-2026-03-05", - "variant": "batches", - "input": 1.25, - "output": 7.5 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-2026-03-05", - "variant": "flex", - "input": 1.25, - "output": 7.5, - "cached_input": 0.13 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-2026-03-05", - "variant": "priority", - "input": 5, - "output": 30, - "cached_input": 0.5 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-mini", - "variant": "", - "input": 0.75, - "output": 4.5, - "cached_input": 0.075 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-mini", - "variant": "batches", - "input": 0.375, - "output": 2.25 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-mini", - "variant": "flex", - "input": 0.375, - "output": 2.25, - "cached_input": 0.0375 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-mini", - "variant": "priority", - "input": 1.5, - "output": 9, - "cached_input": 0.15 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-mini-2026-03-17", - "variant": "", - "input": 0.75, - "output": 4.5, - "cached_input": 0.075 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-mini-2026-03-17", - "variant": "batches", - "input": 0.375, - "output": 2.25 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-mini-2026-03-17", - "variant": "flex", - "input": 0.375, - "output": 2.25, - "cached_input": 0.0375 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-mini-2026-03-17", - "variant": "priority", - "input": 1.5, - "output": 9, - "cached_input": 0.15 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-nano", - "variant": "", - "input": 0.2, - "output": 1.25, - "cached_input": 0.02 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-nano", - "variant": "batches", - "input": 0.1, - "output": 0.625 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-nano", - "variant": "flex", - "input": 0.1, - "output": 0.625, - "cached_input": 0.01 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-nano-2026-03-17", - "variant": "", - "input": 0.2, - "output": 1.25, - "cached_input": 0.02 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-nano-2026-03-17", - "variant": "batches", - "input": 0.1, - "output": 0.625 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-nano-2026-03-17", - "variant": "flex", - "input": 0.1, - "output": 0.625, - "cached_input": 0.01 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-pro", - "variant": "", - "input": 30, - "output": 180, - "cached_input": 3 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-pro", - "variant": "above_272k_tokens", - "input": 60, - "output": 270, - "cached_input": 6 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-pro", - "variant": "batches", - "input": 15, - "output": 90 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-pro", - "variant": "flex", - "input": 15, - "output": 90 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-pro-2026-03-05", - "variant": "", - "input": 30, - "output": 180, - "cached_input": 3 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-pro-2026-03-05", - "variant": "above_272k_tokens", - "input": 60, - "output": 270, - "cached_input": 6 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-pro-2026-03-05", - "variant": "batches", - "input": 15, - "output": 90 - }, - { - "provider": "OpenAI", - "model": "gpt-5.4-pro-2026-03-05", - "variant": "flex", - "input": 15, - "output": 90 - }, - { - "provider": "OpenAI", - "model": "gpt-5.5", - "variant": "", - "input": 5, - "output": 30, - "cached_input": 0.5 - }, - { - "provider": "OpenAI", - "model": "gpt-5.5", - "variant": "above_272k_tokens", - "input": 10, - "output": 45, - "cached_input": 1 - }, - { - "provider": "OpenAI", - "model": "gpt-5.5", - "variant": "batches", - "input": 2.5, - "output": 15 - }, - { - "provider": "OpenAI", - "model": "gpt-5.5", - "variant": "flex", - "input": 2.5, - "output": 15, - "cached_input": 0.25 - }, - { - "provider": "OpenAI", - "model": "gpt-5.5", - "variant": "priority", - "input": 10, - "output": 60, - "cached_input": 1 - }, - { - "provider": "OpenAI", - "model": "gpt-5.5-2026-04-23", - "variant": "", - "input": 5, - "output": 30, - "cached_input": 0.5 - }, - { - "provider": "OpenAI", - "model": "gpt-5.5-2026-04-23", - "variant": "above_272k_tokens", - "input": 10, - "output": 45, - "cached_input": 1 - }, - { - "provider": "OpenAI", - "model": "gpt-5.5-2026-04-23", - "variant": "batches", - "input": 2.5, - "output": 15 - }, - { - "provider": "OpenAI", - "model": "gpt-5.5-2026-04-23", - "variant": "flex", - "input": 2.5, - "output": 15, - "cached_input": 0.25 - }, - { - "provider": "OpenAI", - "model": "gpt-5.5-2026-04-23", - "variant": "priority", - "input": 10, - "output": 60, - "cached_input": 1 - }, - { - "provider": "OpenAI", - "model": "gpt-5.5-pro", - "variant": "", - "input": 30, - "output": 180, - "cached_input": 3 - }, - { - "provider": "OpenAI", - "model": "gpt-5.5-pro", - "variant": "above_272k_tokens", - "input": 60, - "output": 270, - "cached_input": 6 - }, - { - "provider": "OpenAI", - "model": "gpt-5.5-pro", - "variant": "batches", - "input": 15, - "output": 90 - }, - { - "provider": "OpenAI", - "model": "gpt-5.5-pro", - "variant": "flex", - "input": 15, - "output": 90 - }, - { - "provider": "OpenAI", - "model": "gpt-5.5-pro-2026-04-23", - "variant": "", - "input": 30, - "output": 180, - "cached_input": 3 - }, - { - "provider": "OpenAI", - "model": "gpt-5.5-pro-2026-04-23", - "variant": "above_272k_tokens", - "input": 60, - "output": 270, - "cached_input": 6 - }, - { - "provider": "OpenAI", - "model": "gpt-5.5-pro-2026-04-23", - "variant": "batches", - "input": 15, - "output": 90 - }, - { - "provider": "OpenAI", - "model": "gpt-5.5-pro-2026-04-23", - "variant": "flex", - "input": 15, - "output": 90 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6", - "variant": "", - "input": 5, - "output": 30, - "cached_input": 0.5 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6", - "variant": "above_272k_tokens", - "input": 10, - "output": 45, - "cached_input": 1 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6", - "variant": "above_272k_tokens_flex", - "input": 5, - "output": 22.5, - "cached_input": 0.5 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6", - "variant": "batches", - "input": 2.5, - "output": 15 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6", - "variant": "flex", - "input": 2.5, - "output": 15, - "cached_input": 0.25 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6", - "variant": "priority", - "input": 10, - "output": 60, - "cached_input": 1 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6-luna", - "variant": "", - "input": 0.2, - "output": 1.2, - "cached_input": 0.02 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6-luna", - "variant": "above_272k_tokens", - "input": 0.4, - "output": 1.8, - "cached_input": 0.04 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6-luna", - "variant": "above_272k_tokens_flex", - "input": 0.2, - "output": 0.9, - "cached_input": 0.02 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6-luna", - "variant": "batches", - "input": 0.1, - "output": 0.6 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6-luna", - "variant": "flex", - "input": 0.1, - "output": 0.6, - "cached_input": 0.01 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6-luna", - "variant": "priority", - "input": 0.4, - "output": 2.4, - "cached_input": 0.04 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6-sol", - "variant": "", - "input": 5, - "output": 30, - "cached_input": 0.5 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6-sol", - "variant": "above_272k_tokens", - "input": 10, - "output": 45, - "cached_input": 1 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6-sol", - "variant": "above_272k_tokens_flex", - "input": 5, - "output": 22.5, - "cached_input": 0.5 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6-sol", - "variant": "batches", - "input": 2.5, - "output": 15 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6-sol", - "variant": "flex", - "input": 2.5, - "output": 15, - "cached_input": 0.25 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6-sol", - "variant": "priority", - "input": 10, - "output": 60, - "cached_input": 1 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6-terra", - "variant": "", - "input": 2, - "output": 12, - "cached_input": 0.2 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6-terra", - "variant": "above_272k_tokens", - "input": 4, - "output": 18, - "cached_input": 0.4 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6-terra", - "variant": "above_272k_tokens_flex", - "input": 2, - "output": 9, - "cached_input": 0.2 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6-terra", - "variant": "batches", - "input": 1, - "output": 6 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6-terra", - "variant": "flex", - "input": 1, - "output": 6, - "cached_input": 0.1 - }, - { - "provider": "OpenAI", - "model": "gpt-5.6-terra", - "variant": "priority", - "input": 4, - "output": 24, - "cached_input": 0.4 - }, - { - "provider": "OpenAI", - "model": "gpt-audio", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "OpenAI", - "model": "gpt-audio-1.5", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "OpenAI", - "model": "gpt-audio-2025-08-28", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "OpenAI", - "model": "gpt-audio-mini", - "variant": "", - "input": 0.6, - "output": 2.4 - }, - { - "provider": "OpenAI", - "model": "gpt-audio-mini-2025-10-06", - "variant": "", - "input": 0.6, - "output": 2.4 - }, - { - "provider": "OpenAI", - "model": "gpt-audio-mini-2025-12-15", - "variant": "", - "input": 0.6, - "output": 2.4 - }, - { - "provider": "OpenAI", - "model": "gpt-image-1", - "variant": "", - "input": 5, - "cached_input": 1.25 - }, - { - "provider": "OpenAI", - "model": "gpt-image-1-mini", - "variant": "", - "input": 2, - "cached_input": 0.2 - }, - { - "provider": "OpenAI", - "model": "gpt-image-1.5", - "variant": "", - "input": 5, - "output": 10, - "cached_input": 1.25 - }, - { - "provider": "OpenAI", - "model": "gpt-image-1.5-2025-12-16", - "variant": "", - "input": 5, - "output": 10, - "cached_input": 1.25 - }, - { - "provider": "OpenAI", - "model": "gpt-image-2", - "variant": "", - "input": 5, - "output": 10, - "cached_input": 1.25 - }, - { - "provider": "OpenAI", - "model": "gpt-image-2-2026-04-21", - "variant": "", - "input": 5, - "output": 10, - "cached_input": 1.25 - }, - { - "provider": "OpenAI", - "model": "gpt-realtime", - "variant": "", - "input": 4, - "output": 16, - "cached_input": 0.4 - }, - { - "provider": "OpenAI", - "model": "gpt-realtime-1.5", - "variant": "", - "input": 4, - "output": 16, - "cached_input": 0.4 - }, - { - "provider": "OpenAI", - "model": "gpt-realtime-2", - "variant": "", - "input": 4, - "output": 16, - "cached_input": 0.4 - }, - { - "provider": "OpenAI", - "model": "gpt-realtime-2.1", - "variant": "", - "input": 4, - "output": 24, - "cached_input": 0.4 - }, - { - "provider": "OpenAI", - "model": "gpt-realtime-2.1-mini", - "variant": "", - "input": 0.6, - "output": 2.4, - "cached_input": 0.06 - }, - { - "provider": "OpenAI", - "model": "gpt-realtime-2025-08-28", - "variant": "", - "input": 4, - "output": 16, - "cached_input": 0.4 - }, - { - "provider": "OpenAI", - "model": "gpt-realtime-mini", - "variant": "", - "input": 0.6, - "output": 2.4 - }, - { - "provider": "OpenAI", - "model": "gpt-realtime-mini-2025-10-06", - "variant": "", - "input": 0.6, - "output": 2.4, - "cached_input": 0.06 - }, - { - "provider": "OpenAI", - "model": "gpt-realtime-mini-2025-12-15", - "variant": "", - "input": 0.6, - "output": 2.4, - "cached_input": 0.06 - }, - { - "provider": "OpenAI", - "model": "o1", - "variant": "", - "input": 15, - "output": 60, - "cached_input": 7.5 - }, - { - "provider": "OpenAI", - "model": "o1-2024-12-17", - "variant": "", - "input": 15, - "output": 60, - "cached_input": 7.5 - }, - { - "provider": "OpenAI", - "model": "o1-pro", - "variant": "", - "input": 150, - "output": 600 - }, - { - "provider": "OpenAI", - "model": "o1-pro", - "variant": "batches", - "input": 75, - "output": 300 - }, - { - "provider": "OpenAI", - "model": "o1-pro-2025-03-19", - "variant": "", - "input": 150, - "output": 600 - }, - { - "provider": "OpenAI", - "model": "o1-pro-2025-03-19", - "variant": "batches", - "input": 75, - "output": 300 - }, - { - "provider": "OpenAI", - "model": "o3", - "variant": "", - "input": 2, - "output": 8, - "cached_input": 0.5 - }, - { - "provider": "OpenAI", - "model": "o3", - "variant": "flex", - "input": 1, - "output": 4, - "cached_input": 0.25 - }, - { - "provider": "OpenAI", - "model": "o3", - "variant": "priority", - "input": 3.5, - "output": 14, - "cached_input": 0.875 - }, - { - "provider": "OpenAI", - "model": "o3-2025-04-16", - "variant": "", - "input": 2, - "output": 8, - "cached_input": 0.5 - }, - { - "provider": "OpenAI", - "model": "o3-deep-research", - "variant": "", - "input": 10, - "output": 40, - "cached_input": 2.5 - }, - { - "provider": "OpenAI", - "model": "o3-deep-research", - "variant": "batches", - "input": 5, - "output": 20 - }, - { - "provider": "OpenAI", - "model": "o3-deep-research-2025-06-26", - "variant": "", - "input": 10, - "output": 40, - "cached_input": 2.5 - }, - { - "provider": "OpenAI", - "model": "o3-deep-research-2025-06-26", - "variant": "batches", - "input": 5, - "output": 20 - }, - { - "provider": "OpenAI", - "model": "o3-mini", - "variant": "", - "input": 1.1, - "output": 4.4, - "cached_input": 0.55 - }, - { - "provider": "OpenAI", - "model": "o3-mini-2025-01-31", - "variant": "", - "input": 1.1, - "output": 4.4, - "cached_input": 0.55 - }, - { - "provider": "OpenAI", - "model": "o3-pro", - "variant": "", - "input": 20, - "output": 80 - }, - { - "provider": "OpenAI", - "model": "o3-pro", - "variant": "batches", - "input": 10, - "output": 40 - }, - { - "provider": "OpenAI", - "model": "o3-pro-2025-06-10", - "variant": "", - "input": 20, - "output": 80 - }, - { - "provider": "OpenAI", - "model": "o3-pro-2025-06-10", - "variant": "batches", - "input": 10, - "output": 40 - }, - { - "provider": "OpenAI", - "model": "o4-mini", - "variant": "", - "input": 1.1, - "output": 4.4, - "cached_input": 0.275 - }, - { - "provider": "OpenAI", - "model": "o4-mini", - "variant": "flex", - "input": 0.55, - "output": 2.2, - "cached_input": 0.1375 - }, - { - "provider": "OpenAI", - "model": "o4-mini", - "variant": "priority", - "input": 2, - "output": 8, - "cached_input": 0.5 - }, - { - "provider": "OpenAI", - "model": "o4-mini-2025-04-16", - "variant": "", - "input": 1.1, - "output": 4.4, - "cached_input": 0.275 - }, - { - "provider": "OpenAI", - "model": "o4-mini-deep-research", - "variant": "", - "input": 2, - "output": 8, - "cached_input": 0.5 - }, - { - "provider": "OpenAI", - "model": "o4-mini-deep-research", - "variant": "batches", - "input": 1, - "output": 4 - }, - { - "provider": "OpenAI", - "model": "o4-mini-deep-research-2025-06-26", - "variant": "", - "input": 2, - "output": 8, - "cached_input": 0.5 - }, - { - "provider": "OpenAI", - "model": "o4-mini-deep-research-2025-06-26", - "variant": "batches", - "input": 1, - "output": 4 - }, - { - "provider": "OpenAI", - "model": "text-embedding-3-large", - "variant": "", - "input": 0.13, - "output": 0 - }, - { - "provider": "OpenAI", - "model": "text-embedding-3-large", - "variant": "batches", - "input": 0.065, - "output": 0 - }, - { - "provider": "OpenAI", - "model": "text-embedding-3-small", - "variant": "", - "input": 0.02, - "output": 0 - }, - { - "provider": "OpenAI", - "model": "text-embedding-3-small", - "variant": "batches", - "input": 0.01, - "output": 0 - }, - { - "provider": "OpenAI", - "model": "text-embedding-ada-002", - "variant": "", - "input": 0.1, - "output": 0 - }, - { - "provider": "OpenAI", - "model": "text-embedding-ada-002-v2", - "variant": "", - "input": 0.1, - "output": 0 - }, - { - "provider": "OpenAI", - "model": "text-embedding-ada-002-v2", - "variant": "batches", - "input": 0.05, - "output": 0 - }, - { - "provider": "OpenRouter", - "model": "anthropic/claude-3-haiku", - "variant": "", - "input": 0.25, - "output": 1.25 - }, - { - "provider": "OpenRouter", - "model": "anthropic/claude-3.5-sonnet", - "variant": "", - "input": 3, - "output": 15 - }, - { - "provider": "OpenRouter", - "model": "anthropic/claude-3.7-sonnet", - "variant": "", - "input": 3, - "output": 15 - }, - { - "provider": "OpenRouter", - "model": "anthropic/claude-haiku-4.5", - "variant": "", - "input": 1, - "output": 5, - "cached_input": 0.1 - }, - { - "provider": "OpenRouter", - "model": "anthropic/claude-opus-4", - "variant": "", - "input": 15, - "output": 75, - "cached_input": 1.5 - }, - { - "provider": "OpenRouter", - "model": "anthropic/claude-opus-4.1", - "variant": "", - "input": 15, - "output": 75, - "cached_input": 1.5 - }, - { - "provider": "OpenRouter", - "model": "anthropic/claude-opus-4.5", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "OpenRouter", - "model": "anthropic/claude-opus-4.6", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "OpenRouter", - "model": "anthropic/claude-opus-4.7", - "variant": "", - "input": 5, - "output": 25, - "cached_input": 0.5 - }, - { - "provider": "OpenRouter", - "model": "anthropic/claude-sonnet-4", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "OpenRouter", - "model": "anthropic/claude-sonnet-4", - "variant": "above_200k_tokens", - "input": 6, - "output": 22.5, - "cached_input": 0.6 - }, - { - "provider": "OpenRouter", - "model": "anthropic/claude-sonnet-4.5", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "OpenRouter", - "model": "anthropic/claude-sonnet-4.5", - "variant": "above_200k_tokens", - "input": 6, - "output": 22.5, - "cached_input": 0.6 - }, - { - "provider": "OpenRouter", - "model": "anthropic/claude-sonnet-4.6", - "variant": "", - "input": 3, - "output": 15, - "cached_input": 0.3 - }, - { - "provider": "OpenRouter", - "model": "anthropic/claude-sonnet-4.6", - "variant": "above_200k_tokens", - "input": 6, - "output": 22.5, - "cached_input": 0.6 - }, - { - "provider": "OpenRouter", - "model": "bytedance/ui-tars-1.5-7b", - "variant": "", - "input": 0.1, - "output": 0.2 - }, - { - "provider": "OpenRouter", - "model": "deepseek/deepseek-chat", - "variant": "", - "input": 0.14, - "output": 0.28 - }, - { - "provider": "OpenRouter", - "model": "deepseek/deepseek-chat-v3-0324", - "variant": "", - "input": 0.14, - "output": 0.28 - }, - { - "provider": "OpenRouter", - "model": "deepseek/deepseek-chat-v3.1", - "variant": "", - "input": 0.2, - "output": 0.8 - }, - { - "provider": "OpenRouter", - "model": "deepseek/deepseek-chat-v3.1", - "variant": "cache_hit", - "input": 0.02 - }, - { - "provider": "OpenRouter", - "model": "deepseek/deepseek-r1", - "variant": "", - "input": 0.55, - "output": 2.19 - }, - { - "provider": "OpenRouter", - "model": "deepseek/deepseek-r1", - "variant": "cache_hit", - "input": 0.14 - }, - { - "provider": "OpenRouter", - "model": "deepseek/deepseek-r1-0528", - "variant": "", - "input": 0.5, - "output": 2.15 - }, - { - "provider": "OpenRouter", - "model": "deepseek/deepseek-r1-0528", - "variant": "cache_hit", - "input": 0.14 - }, - { - "provider": "OpenRouter", - "model": "deepseek/deepseek-v3.2", - "variant": "", - "input": 0.28, - "output": 0.4 - }, - { - "provider": "OpenRouter", - "model": "deepseek/deepseek-v3.2", - "variant": "cache_hit", - "input": 0.028 - }, - { - "provider": "OpenRouter", - "model": "deepseek/deepseek-v3.2-exp", - "variant": "", - "input": 0.2, - "output": 0.4 - }, - { - "provider": "OpenRouter", - "model": "deepseek/deepseek-v3.2-exp", - "variant": "cache_hit", - "input": 0.02 - }, - { - "provider": "OpenRouter", - "model": "google/gemini-2.0-flash-001", - "variant": "", - "input": 0.1, - "output": 0.4 - }, - { - "provider": "OpenRouter", - "model": "google/gemini-2.5-flash", - "variant": "", - "input": 0.3, - "output": 2.5 - }, - { - "provider": "OpenRouter", - "model": "google/gemini-2.5-pro", - "variant": "", - "input": 1.25, - "output": 10 - }, - { - "provider": "OpenRouter", - "model": "google/gemini-3-flash-preview", - "variant": "", - "input": 0.5, - "output": 3, - "cached_input": 0.05 - }, - { - "provider": "OpenRouter", - "model": "google/gemini-3-pro-preview", - "variant": "", - "input": 2, - "output": 12, - "cached_input": 0.2 - }, - { - "provider": "OpenRouter", - "model": "google/gemini-3-pro-preview", - "variant": "above_200k_tokens", - "input": 4, - "output": 18, - "cached_input": 0.4 - }, - { - "provider": "OpenRouter", - "model": "google/gemini-3-pro-preview", - "variant": "batches", - "input": 1, - "output": 6 - }, - { - "provider": "OpenRouter", - "model": "google/gemini-3.1-flash-lite", - "variant": "", - "input": 0.25, - "output": 1.5, - "cached_input": 0.025 - }, - { - "provider": "OpenRouter", - "model": "google/gemini-3.1-flash-lite-preview", - "variant": "", - "input": 0.25, - "output": 1.5, - "cached_input": 0.025 - }, - { - "provider": "OpenRouter", - "model": "google/gemini-3.1-pro-preview", - "variant": "", - "input": 2, - "output": 12, - "cached_input": 0.2 - }, - { - "provider": "OpenRouter", - "model": "google/gemini-3.1-pro-preview", - "variant": "above_200k_tokens", - "input": 4, - "output": 18, - "cached_input": 0.4 - }, - { - "provider": "OpenRouter", - "model": "gryphe/mythomax-l2-13b", - "variant": "", - "input": 1.875, - "output": 1.875 - }, - { - "provider": "OpenRouter", - "model": "mancer/weaver", - "variant": "", - "input": 5.625, - "output": 5.625 - }, - { - "provider": "OpenRouter", - "model": "meta-llama/llama-3-70b-instruct", - "variant": "", - "input": 0.59, - "output": 0.79 - }, - { - "provider": "OpenRouter", - "model": "minimax/minimax-m2", - "variant": "", - "input": 0.255, - "output": 1.02 - }, - { - "provider": "OpenRouter", - "model": "minimax/minimax-m2.1", - "variant": "", - "input": 0.27, - "output": 1.2, - "cached_input": 0 - }, - { - "provider": "OpenRouter", - "model": "minimax/minimax-m2.5", - "variant": "", - "input": 0.3, - "output": 1.1, - "cached_input": 0.15 - }, - { - "provider": "OpenRouter", - "model": "mistralai/devstral-2512", - "variant": "", - "input": 0.15, - "output": 0.6 - }, - { - "provider": "OpenRouter", - "model": "mistralai/ministral-14b-2512", - "variant": "", - "input": 0.2, - "output": 0.2 - }, - { - "provider": "OpenRouter", - "model": "mistralai/ministral-3b-2512", - "variant": "", - "input": 0.1, - "output": 0.1 - }, - { - "provider": "OpenRouter", - "model": "mistralai/ministral-8b-2512", - "variant": "", - "input": 0.15, - "output": 0.15 - }, - { - "provider": "OpenRouter", - "model": "mistralai/mistral-7b-instruct", - "variant": "", - "input": 0.13, - "output": 0.13 - }, - { - "provider": "OpenRouter", - "model": "mistralai/mistral-large", - "variant": "", - "input": 8, - "output": 24 - }, - { - "provider": "OpenRouter", - "model": "mistralai/mistral-large-2512", - "variant": "", - "input": 0.5, - "output": 1.5 - }, - { - "provider": "OpenRouter", - "model": "mistralai/mistral-small-3.1-24b-instruct", - "variant": "", - "input": 0.1, - "output": 0.3 - }, - { - "provider": "OpenRouter", - "model": "mistralai/mistral-small-3.2-24b-instruct", - "variant": "", - "input": 0.1, - "output": 0.3 - }, - { - "provider": "OpenRouter", - "model": "mistralai/mixtral-8x22b-instruct", - "variant": "", - "input": 0.65, - "output": 0.65 - }, - { - "provider": "OpenRouter", - "model": "moonshotai/kimi-k2.5", - "variant": "", - "input": 0.6, - "output": 3, - "cached_input": 0.1 - }, - { - "provider": "OpenRouter", - "model": "openai/gpt-3.5-turbo", - "variant": "", - "input": 1.5, - "output": 2 - }, - { - "provider": "OpenRouter", - "model": "openai/gpt-3.5-turbo-16k", - "variant": "", - "input": 3, - "output": 4 - }, - { - "provider": "OpenRouter", - "model": "openai/gpt-4", - "variant": "", - "input": 30, - "output": 60 - }, - { - "provider": "OpenRouter", - "model": "openai/gpt-4.1", - "variant": "", - "input": 2, - "output": 8, - "cached_input": 0.5 - }, - { - "provider": "OpenRouter", - "model": "openai/gpt-4.1-mini", - "variant": "", - "input": 0.4, - "output": 1.6, - "cached_input": 0.1 - }, - { - "provider": "OpenRouter", - "model": "openai/gpt-4.1-nano", - "variant": "", - "input": 0.1, - "output": 0.4, - "cached_input": 0.025 - }, - { - "provider": "OpenRouter", - "model": "openai/gpt-4o", - "variant": "", - "input": 2.5, - "output": 10 - }, - { - "provider": "OpenRouter", - "model": "openai/gpt-4o-2024-05-13", - "variant": "", - "input": 5, - "output": 15 - }, - { - "provider": "OpenRouter", - "model": "openai/gpt-5", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "OpenRouter", - "model": "openai/gpt-5-chat", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "OpenRouter", - "model": "openai/gpt-5-codex", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "OpenRouter", - "model": "openai/gpt-5-mini", - "variant": "", - "input": 0.25, - "output": 2, - "cached_input": 0.025 - }, - { - "provider": "OpenRouter", - "model": "openai/gpt-5-nano", - "variant": "", - "input": 0.05, - "output": 0.4, - "cached_input": 0.005 - }, - { - "provider": "OpenRouter", - "model": "openai/gpt-5.1-codex-max", - "variant": "", - "input": 1.25, - "output": 10, - "cached_input": 0.125 - }, - { - "provider": "OpenRouter", - "model": "openai/gpt-5.2", - "variant": "", - "input": 1.75, - "output": 14, - "cached_input": 0.175 - }, - { - "provider": "OpenRouter", - "model": "openai/gpt-5.2-chat", - "variant": "", - "input": 1.75, - "output": 14, - "cached_input": 0.175 - }, - { - "provider": "OpenRouter", - "model": "openai/gpt-5.2-codex", - "variant": "", - "input": 1.75, - "output": 14, - "cached_input": 0.175 - }, - { - "provider": "OpenRouter", - "model": "openai/gpt-5.2-pro", - "variant": "", - "input": 21, - "output": 168 - }, - { - "provider": "OpenRouter", - "model": "openai/gpt-oss-120b", - "variant": "", - "input": 0.18, - "output": 0.8 - }, - { - "provider": "OpenRouter", - "model": "openai/gpt-oss-20b", - "variant": "", - "input": 0.02, - "output": 0.1 - }, - { - "provider": "OpenRouter", - "model": "openai/o1", - "variant": "", - "input": 15, - "output": 60, - "cached_input": 7.5 - }, - { - "provider": "OpenRouter", - "model": "openai/o3-mini", - "variant": "", - "input": 1.1, - "output": 4.4 - }, - { - "provider": "OpenRouter", - "model": "openai/o3-mini-high", - "variant": "", - "input": 1.1, - "output": 4.4 - }, - { - "provider": "OpenRouter", - "model": "qwen/qwen-2.5-coder-32b-instruct", - "variant": "", - "input": 0.18, - "output": 0.18 - }, - { - "provider": "OpenRouter", - "model": "qwen/qwen-vl-plus", - "variant": "", - "input": 0.21, - "output": 0.63 - }, - { - "provider": "OpenRouter", - "model": "qwen/qwen3-235b-a22b-2507", - "variant": "", - "input": 0.071, - "output": 0.1 - }, - { - "provider": "OpenRouter", - "model": "qwen/qwen3-235b-a22b-thinking-2507", - "variant": "", - "input": 0.11, - "output": 0.6 - }, - { - "provider": "OpenRouter", - "model": "qwen/qwen3-coder", - "variant": "", - "input": 0.22, - "output": 0.95 - }, - { - "provider": "OpenRouter", - "model": "qwen/qwen3-coder-plus", - "variant": "", - "input": 1, - "output": 5 - }, - { - "provider": "OpenRouter", - "model": "qwen/qwen3.5-122b-a10b", - "variant": "", - "input": 0.4, - "output": 2 - }, - { - "provider": "OpenRouter", - "model": "qwen/qwen3.5-27b", - "variant": "", - "input": 0.3, - "output": 2.4 - }, - { - "provider": "OpenRouter", - "model": "qwen/qwen3.5-35b-a3b", - "variant": "", - "input": 0.25, - "output": 2 - }, - { - "provider": "OpenRouter", - "model": "qwen/qwen3.5-397b-a17b", - "variant": "", - "input": 0.6, - "output": 3.6 - }, - { - "provider": "OpenRouter", - "model": "qwen/qwen3.5-flash-02-23", - "variant": "", - "input": 0.1, - "output": 0.4 - }, - { - "provider": "OpenRouter", - "model": "qwen/qwen3.5-plus-02-15", - "variant": "", - "input": 0.4, - "output": 2.4 - }, - { - "provider": "OpenRouter", - "model": "qwen/qwen3.5-plus-02-15", - "variant": "above_256k_tokens", - "input": 0.5, - "output": 3 - }, - { - "provider": "OpenRouter", - "model": "qwen/qwen3.6-plus", - "variant": "", - "input": 0.325, - "output": 1.95 - }, - { - "provider": "OpenRouter", - "model": "switchpoint/router", - "variant": "", - "input": 0.85, - "output": 3.4 - }, - { - "provider": "OpenRouter", - "model": "undi95/remm-slerp-l2-13b", - "variant": "", - "input": 1.875, - "output": 1.875 - }, - { - "provider": "OpenRouter", - "model": "x-ai/grok-4", - "variant": "", - "input": 3, - "output": 15 - }, - { - "provider": "OpenRouter", - "model": "xiaomi/mimo-v2-flash", - "variant": "", - "input": 0.1, - "output": 0.3, - "cached_input": 0.01 - }, - { - "provider": "OpenRouter", - "model": "xiaomi/mimo-v2.5", - "variant": "", - "input": 0.4, - "output": 2, - "cached_input": 0.08 - }, - { - "provider": "OpenRouter", - "model": "xiaomi/mimo-v2.5-pro", - "variant": "", - "input": 1, - "output": 3, - "cached_input": 0.2 - }, - { - "provider": "OpenRouter", - "model": "z-ai/glm-4.6", - "variant": "", - "input": 0.4, - "output": 1.75 - }, - { - "provider": "OpenRouter", - "model": "z-ai/glm-4.6:exacto", - "variant": "", - "input": 0.45, - "output": 1.9 - }, - { - "provider": "OpenRouter", - "model": "z-ai/glm-4.7", - "variant": "", - "input": 0.4, - "output": 1.5, - "cached_input": 0 - }, - { - "provider": "OpenRouter", - "model": "z-ai/glm-4.7-flash", - "variant": "", - "input": 0.07, - "output": 0.4, - "cached_input": 0 - }, - { - "provider": "OpenRouter", - "model": "z-ai/glm-5", - "variant": "", - "input": 0.8, - "output": 2.56 - }, - { - "provider": "OpenRouter", - "model": "z-ai/glm-5.1", - "variant": "", - "input": 1.05, - "output": 3.5, - "cached_input": 0.525 - }, - { - "provider": "Posit", - "model": "claude-fable-5", - "variant": "", - "input": 11, - "output": 55, - "cached_input": 1.1 - }, - { - "provider": "Posit", - "model": "claude-haiku-4-5", - "variant": "", - "input": 1.1, - "output": 5.5, - "cached_input": 0.11 - }, - { - "provider": "Posit", - "model": "claude-opus-4-5", - "variant": "", - "input": 5.5, - "output": 27.5, - "cached_input": 0.55 - }, - { - "provider": "Posit", - "model": "claude-opus-4-6", - "variant": "", - "input": 5.5, - "output": 27.5, - "cached_input": 0.55 - }, - { - "provider": "Posit", - "model": "claude-opus-4-7", - "variant": "", - "input": 5.5, - "output": 27.5, - "cached_input": 0.55 - }, - { - "provider": "Posit", - "model": "claude-opus-4-8", - "variant": "", - "input": 5.5, - "output": 27.5, - "cached_input": 0.55 - }, - { - "provider": "Posit", - "model": "claude-sonnet-4-5", - "variant": "", - "input": 3.3, - "output": 16.5, - "cached_input": 0.33 - }, - { - "provider": "Posit", - "model": "claude-sonnet-4-5", - "variant": "above_200k_tokens", - "input": 6.6, - "output": 24.75, - "cached_input": 0.66 - }, - { - "provider": "Posit", - "model": "claude-sonnet-4-6", - "variant": "", - "input": 3.3, - "output": 16.5, - "cached_input": 0.33 - }, - { - "provider": "Posit", - "model": "google/gemma-4-26B-A4B-it", - "variant": "", - "input": 0.3, - "output": 1.5, - "cached_input": 0.03 - } -] +{ + "schema_version": 1, + "min_ellmer_version": "0.5.0", + "updated_at": "2026-08-03T09:30:30Z", + "data": [ + { + "provider": "AWS/Bedrock", + "model": "ai21.j2-mid-v1", + "variant": "", + "input": 12.5, + "output": 12.5 + }, + { + "provider": "AWS/Bedrock", + "model": "ai21.j2-ultra-v1", + "variant": "", + "input": 18.8, + "output": 18.8 + }, + { + "provider": "AWS/Bedrock", + "model": "ai21.jamba-1-5-large-v1:0", + "variant": "", + "input": 2, + "output": 8 + }, + { + "provider": "AWS/Bedrock", + "model": "ai21.jamba-1-5-mini-v1:0", + "variant": "", + "input": 0.2, + "output": 0.4 + }, + { + "provider": "AWS/Bedrock", + "model": "ai21.jamba-instruct-v1:0", + "variant": "", + "input": 0.5, + "output": 0.7 + }, + { + "provider": "AWS/Bedrock", + "model": "amazon.nova-2-lite-v1:0", + "variant": "", + "input": 0.3, + "output": 2.5, + "cached_input": 0.075 + }, + { + "provider": "AWS/Bedrock", + "model": "amazon.nova-2-multimodal-embeddings-v1:0", + "variant": "", + "input": 0.135, + "output": 0 + }, + { + "provider": "AWS/Bedrock", + "model": "amazon.nova-2-pro-preview-20251202-v1:0", + "variant": "", + "input": 2.1875, + "output": 17.5, + "cached_input": 0.546875 + }, + { + "provider": "AWS/Bedrock", + "model": "amazon.nova-lite-v1:0", + "variant": "", + "input": 0.06, + "output": 0.24 + }, + { + "provider": "AWS/Bedrock", + "model": "amazon.nova-micro-v1:0", + "variant": "", + "input": 0.035, + "output": 0.14 + }, + { + "provider": "AWS/Bedrock", + "model": "amazon.nova-pro-v1:0", + "variant": "", + "input": 0.8, + "output": 3.2 + }, + { + "provider": "AWS/Bedrock", + "model": "amazon.titan-embed-g1-text-02", + "variant": "", + "input": 0.1, + "output": 0 + }, + { + "provider": "AWS/Bedrock", + "model": "amazon.titan-embed-image-v1", + "variant": "", + "input": 0.8, + "output": 0 + }, + { + "provider": "AWS/Bedrock", + "model": "amazon.titan-embed-text-v1", + "variant": "", + "input": 0.1, + "output": 0 + }, + { + "provider": "AWS/Bedrock", + "model": "amazon.titan-embed-text-v2:0", + "variant": "", + "input": 0.02, + "output": 0 + }, + { + "provider": "AWS/Bedrock", + "model": "amazon.titan-text-express-v1", + "variant": "", + "input": 1.3, + "output": 1.7 + }, + { + "provider": "AWS/Bedrock", + "model": "amazon.titan-text-lite-v1", + "variant": "", + "input": 0.3, + "output": 0.4 + }, + { + "provider": "AWS/Bedrock", + "model": "amazon.titan-text-premier-v1:0", + "variant": "", + "input": 0.5, + "output": 1.5 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-3-5-haiku-20241022-v1:0", + "variant": "", + "input": 0.8, + "output": 4, + "cached_input": 0.08 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-3-5-sonnet-20240620-v1:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-3-5-sonnet-20240620-v1:0", + "variant": "above_200k_tokens", + "input": 6, + "output": 30, + "cached_input": 0.6 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-3-5-sonnet-20241022-v2:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-3-5-sonnet-20241022-v2:0", + "variant": "above_200k_tokens", + "input": 6, + "output": 30, + "cached_input": 0.6 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-3-7-sonnet-20240620-v1:0", + "variant": "", + "input": 3.6, + "output": 18, + "cached_input": 0.36 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-3-7-sonnet-20250219-v1:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-3-haiku-20240307-v1:0", + "variant": "", + "input": 0.25, + "output": 1.25, + "cached_input": 0.025 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-3-opus-20240229-v1:0", + "variant": "", + "input": 15, + "output": 75, + "cached_input": 1.5 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-3-sonnet-20240229-v1:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-fable-5", + "variant": "", + "input": 10, + "output": 50, + "cached_input": 1 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-haiku-4-5-20251001-v1:0", + "variant": "", + "input": 1, + "output": 5, + "cached_input": 0.1 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-haiku-4-5@20251001", + "variant": "", + "input": 1, + "output": 5, + "cached_input": 0.1 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-instant-v1", + "variant": "", + "input": 0.8, + "output": 2.4 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-opus-4-1-20250805-v1:0", + "variant": "", + "input": 15, + "output": 75, + "cached_input": 1.5 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-opus-4-20250514-v1:0", + "variant": "", + "input": 15, + "output": 75, + "cached_input": 1.5 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-opus-4-5-20251101-v1:0", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-opus-4-6-v1", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-opus-4-7", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-opus-4-8", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-opus-5", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-sonnet-4-20250514-v1:0", + "variant": "above_200k_tokens", + "input": 6, + "output": 22.5, + "cached_input": 0.6 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-sonnet-4-5-20250929-v1:0", + "variant": "above_200k_tokens", + "input": 6, + "output": 22.5, + "cached_input": 0.6 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-sonnet-4-6", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-sonnet-5", + "variant": "", + "input": 2, + "output": 10, + "cached_input": 0.2 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-v1", + "variant": "", + "input": 8, + "output": 24 + }, + { + "provider": "AWS/Bedrock", + "model": "anthropic.claude-v2:1", + "variant": "", + "input": 8, + "output": 24 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-northeast-1/anthropic.claude-instant-v1", + "variant": "", + "input": 2.23, + "output": 7.55 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-northeast-1/anthropic.claude-v1", + "variant": "", + "input": 8, + "output": 24 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-northeast-1/anthropic.claude-v2:1", + "variant": "", + "input": 8, + "output": 24 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-northeast-1/deepseek.v3.2", + "variant": "", + "input": 0.74, + "output": 2.22 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-northeast-1/minimax.minimax-m2.1", + "variant": "", + "input": 0.36, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-northeast-1/minimax.minimax-m2.5", + "variant": "", + "input": 0.36, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-northeast-1/moonshotai.kimi-k2-thinking", + "variant": "", + "input": 0.73, + "output": 3.03 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-northeast-1/moonshotai.kimi-k2.5", + "variant": "", + "input": 0.72, + "output": 3.6 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-northeast-1/qwen.qwen3-coder-next", + "variant": "", + "input": 0.6, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-south-1/deepseek.v3.2", + "variant": "", + "input": 0.74, + "output": 2.22 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-south-1/meta.llama3-70b-instruct-v1:0", + "variant": "", + "input": 3.18, + "output": 4.2 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-south-1/meta.llama3-8b-instruct-v1:0", + "variant": "", + "input": 0.36, + "output": 0.72 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-south-1/minimax.minimax-m2.1", + "variant": "", + "input": 0.36, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-south-1/minimax.minimax-m2.5", + "variant": "", + "input": 0.36, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-south-1/moonshotai.kimi-k2-thinking", + "variant": "", + "input": 0.71, + "output": 2.94 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-south-1/moonshotai.kimi-k2.5", + "variant": "", + "input": 0.72, + "output": 3.6 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-south-1/qwen.qwen3-coder-next", + "variant": "", + "input": 0.6, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-southeast-2/minimax.minimax-m2.5", + "variant": "", + "input": 0.309, + "output": 1.236 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-southeast-3/deepseek.v3.2", + "variant": "", + "input": 0.74, + "output": 2.22 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-southeast-3/minimax.minimax-m2.1", + "variant": "", + "input": 0.36, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-southeast-3/minimax.minimax-m2.5", + "variant": "", + "input": 0.36, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-southeast-3/moonshotai.kimi-k2.5", + "variant": "", + "input": 0.72, + "output": 3.6 + }, + { + "provider": "AWS/Bedrock", + "model": "ap-southeast-3/qwen.qwen3-coder-next", + "variant": "", + "input": 0.6, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "apac.amazon.nova-2-lite-v1:0", + "variant": "", + "input": 0.33, + "output": 2.75, + "cached_input": 0.0825 + }, + { + "provider": "AWS/Bedrock", + "model": "apac.amazon.nova-2-pro-preview-20251202-v1:0", + "variant": "", + "input": 2.1875, + "output": 17.5, + "cached_input": 0.546875 + }, + { + "provider": "AWS/Bedrock", + "model": "apac.amazon.nova-lite-v1:0", + "variant": "", + "input": 0.063, + "output": 0.252 + }, + { + "provider": "AWS/Bedrock", + "model": "apac.amazon.nova-micro-v1:0", + "variant": "", + "input": 0.037, + "output": 0.148 + }, + { + "provider": "AWS/Bedrock", + "model": "apac.amazon.nova-pro-v1:0", + "variant": "", + "input": 0.84, + "output": 3.36 + }, + { + "provider": "AWS/Bedrock", + "model": "apac.anthropic.claude-3-5-sonnet-20240620-v1:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "apac.anthropic.claude-3-5-sonnet-20241022-v2:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "apac.anthropic.claude-3-haiku-20240307-v1:0", + "variant": "", + "input": 0.25, + "output": 1.25, + "cached_input": 0.025 + }, + { + "provider": "AWS/Bedrock", + "model": "apac.anthropic.claude-3-sonnet-20240229-v1:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "apac.anthropic.claude-haiku-4-5-20251001-v1:0", + "variant": "", + "input": 1.1, + "output": 5.5, + "cached_input": 0.11 + }, + { + "provider": "AWS/Bedrock", + "model": "apac.anthropic.claude-sonnet-4-20250514-v1:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "apac.anthropic.claude-sonnet-4-20250514-v1:0", + "variant": "above_200k_tokens", + "input": 6, + "output": 22.5, + "cached_input": 0.6 + }, + { + "provider": "AWS/Bedrock", + "model": "au.anthropic.claude-haiku-4-5-20251001-v1:0", + "variant": "", + "input": 1.1, + "output": 5.5, + "cached_input": 0.11 + }, + { + "provider": "AWS/Bedrock", + "model": "au.anthropic.claude-opus-4-6-v1", + "variant": "", + "input": 5.5, + "output": 27.5, + "cached_input": 0.55 + }, + { + "provider": "AWS/Bedrock", + "model": "au.anthropic.claude-opus-4-7", + "variant": "", + "input": 5.5, + "output": 27.5, + "cached_input": 0.55 + }, + { + "provider": "AWS/Bedrock", + "model": "au.anthropic.claude-opus-4-8", + "variant": "", + "input": 5.5, + "output": 27.5, + "cached_input": 0.55 + }, + { + "provider": "AWS/Bedrock", + "model": "au.anthropic.claude-opus-5", + "variant": "", + "input": 5.5, + "output": 27.5, + "cached_input": 0.55 + }, + { + "provider": "AWS/Bedrock", + "model": "au.anthropic.claude-sonnet-4-5-20250929-v1:0", + "variant": "", + "input": 3.3, + "output": 16.5, + "cached_input": 0.33 + }, + { + "provider": "AWS/Bedrock", + "model": "au.anthropic.claude-sonnet-4-5-20250929-v1:0", + "variant": "above_200k_tokens", + "input": 6.6, + "output": 24.75, + "cached_input": 0.66 + }, + { + "provider": "AWS/Bedrock", + "model": "au.anthropic.claude-sonnet-4-6", + "variant": "", + "input": 3.3, + "output": 16.5, + "cached_input": 0.33 + }, + { + "provider": "AWS/Bedrock", + "model": "au.anthropic.claude-sonnet-5", + "variant": "", + "input": 2.2, + "output": 11, + "cached_input": 0.22 + }, + { + "provider": "AWS/Bedrock", + "model": "ca-central-1/meta.llama3-70b-instruct-v1:0", + "variant": "", + "input": 3.05, + "output": 4.03 + }, + { + "provider": "AWS/Bedrock", + "model": "ca-central-1/meta.llama3-8b-instruct-v1:0", + "variant": "", + "input": 0.35, + "output": 0.69 + }, + { + "provider": "AWS/Bedrock", + "model": "claude-sonnet-4-5-20250929-v1:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "claude-sonnet-4-5-20250929-v1:0", + "variant": "above_200k_tokens", + "input": 6, + "output": 22.5, + "cached_input": 0.6 + }, + { + "provider": "AWS/Bedrock", + "model": "cohere.command-light-text-v14", + "variant": "", + "input": 0.3, + "output": 0.6 + }, + { + "provider": "AWS/Bedrock", + "model": "cohere.command-r-plus-v1:0", + "variant": "", + "input": 3, + "output": 15 + }, + { + "provider": "AWS/Bedrock", + "model": "cohere.command-r-v1:0", + "variant": "", + "input": 0.5, + "output": 1.5 + }, + { + "provider": "AWS/Bedrock", + "model": "cohere.command-text-v14", + "variant": "", + "input": 1.5, + "output": 2 + }, + { + "provider": "AWS/Bedrock", + "model": "cohere.embed-english-v3", + "variant": "", + "input": 0.1, + "output": 0 + }, + { + "provider": "AWS/Bedrock", + "model": "cohere.embed-multilingual-v3", + "variant": "", + "input": 0.1, + "output": 0 + }, + { + "provider": "AWS/Bedrock", + "model": "cohere.embed-v4:0", + "variant": "", + "input": 0.12, + "output": 0 + }, + { + "provider": "AWS/Bedrock", + "model": "deepseek.v3-v1:0", + "variant": "", + "input": 0.58, + "output": 1.68 + }, + { + "provider": "AWS/Bedrock", + "model": "deepseek.v3.2", + "variant": "", + "input": 0.62, + "output": 1.85 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-central-1/anthropic.claude-instant-v1", + "variant": "", + "input": 2.48, + "output": 8.38 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-central-1/anthropic.claude-v1", + "variant": "", + "input": 8, + "output": 24 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-central-1/anthropic.claude-v2:1", + "variant": "", + "input": 8, + "output": 24 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-central-1/minimax.minimax-m2.1", + "variant": "", + "input": 0.36, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-central-1/minimax.minimax-m2.5", + "variant": "", + "input": 0.36, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-central-1/qwen.qwen3-coder-next", + "variant": "", + "input": 0.6, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-north-1/deepseek.v3.2", + "variant": "", + "input": 0.74, + "output": 2.22 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-north-1/minimax.minimax-m2.1", + "variant": "", + "input": 0.36, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-north-1/minimax.minimax-m2.5", + "variant": "", + "input": 0.36, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-north-1/moonshotai.kimi-k2.5", + "variant": "", + "input": 0.72, + "output": 3.6 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-south-1/minimax.minimax-m2.1", + "variant": "", + "input": 0.36, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-south-1/minimax.minimax-m2.5", + "variant": "", + "input": 0.36, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-south-1/qwen.qwen3-coder-next", + "variant": "", + "input": 0.6, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-west-1/meta.llama3-70b-instruct-v1:0", + "variant": "", + "input": 2.86, + "output": 3.78 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-west-1/meta.llama3-8b-instruct-v1:0", + "variant": "", + "input": 0.32, + "output": 0.65 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-west-1/minimax.minimax-m2.1", + "variant": "", + "input": 0.36, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-west-1/minimax.minimax-m2.5", + "variant": "", + "input": 0.36, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-west-1/qwen.qwen3-coder-next", + "variant": "", + "input": 0.6, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-west-2/meta.llama3-70b-instruct-v1:0", + "variant": "", + "input": 3.45, + "output": 4.55 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-west-2/meta.llama3-8b-instruct-v1:0", + "variant": "", + "input": 0.39, + "output": 0.78 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-west-2/minimax.minimax-m2.1", + "variant": "", + "input": 0.47, + "output": 1.86 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-west-2/minimax.minimax-m2.5", + "variant": "", + "input": 0.47, + "output": 1.86 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-west-2/qwen.qwen3-coder-next", + "variant": "", + "input": 0.78, + "output": 1.86 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-west-3/mistral.mistral-7b-instruct-v0:2", + "variant": "", + "input": 0.2, + "output": 0.26 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-west-3/mistral.mistral-large-2402-v1:0", + "variant": "", + "input": 10.4, + "output": 31.2 + }, + { + "provider": "AWS/Bedrock", + "model": "eu-west-3/mistral.mixtral-8x7b-instruct-v0:1", + "variant": "", + "input": 0.59, + "output": 0.91 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.amazon.nova-2-lite-v1:0", + "variant": "", + "input": 0.33, + "output": 2.75, + "cached_input": 0.0825 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.amazon.nova-2-pro-preview-20251202-v1:0", + "variant": "", + "input": 2.1875, + "output": 17.5, + "cached_input": 0.546875 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.amazon.nova-lite-v1:0", + "variant": "", + "input": 0.078, + "output": 0.312 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.amazon.nova-micro-v1:0", + "variant": "", + "input": 0.046, + "output": 0.184 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.amazon.nova-pro-v1:0", + "variant": "", + "input": 1.05, + "output": 4.2 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-3-5-haiku-20241022-v1:0", + "variant": "", + "input": 0.25, + "output": 1.25, + "cached_input": 0.025 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-3-5-sonnet-20240620-v1:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-3-5-sonnet-20241022-v2:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-3-7-sonnet-20250219-v1:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-3-haiku-20240307-v1:0", + "variant": "", + "input": 0.25, + "output": 1.25, + "cached_input": 0.025 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-3-opus-20240229-v1:0", + "variant": "", + "input": 15, + "output": 75, + "cached_input": 1.5 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-3-sonnet-20240229-v1:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-fable-5", + "variant": "", + "input": 11, + "output": 55, + "cached_input": 1.1 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-haiku-4-5-20251001-v1:0", + "variant": "", + "input": 1.1, + "output": 5.5, + "cached_input": 0.11 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-opus-4-1-20250805-v1:0", + "variant": "", + "input": 15, + "output": 75, + "cached_input": 1.5 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-opus-4-20250514-v1:0", + "variant": "", + "input": 15, + "output": 75, + "cached_input": 1.5 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-opus-4-5-20251101-v1:0", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-opus-4-6-v1", + "variant": "", + "input": 5.5, + "output": 27.5, + "cached_input": 0.55 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-opus-4-7", + "variant": "", + "input": 5.5, + "output": 27.5, + "cached_input": 0.55 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-opus-4-8", + "variant": "", + "input": 5.5, + "output": 27.5, + "cached_input": 0.55 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-opus-5", + "variant": "", + "input": 5.5, + "output": 27.5, + "cached_input": 0.55 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-sonnet-4-20250514-v1:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-sonnet-4-20250514-v1:0", + "variant": "above_200k_tokens", + "input": 6, + "output": 22.5, + "cached_input": 0.6 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0", + "variant": "", + "input": 3.3, + "output": 16.5, + "cached_input": 0.33 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-sonnet-4-5-20250929-v1:0", + "variant": "above_200k_tokens", + "input": 6.6, + "output": 24.75, + "cached_input": 0.66 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-sonnet-4-6", + "variant": "", + "input": 3.3, + "output": 16.5, + "cached_input": 0.33 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.anthropic.claude-sonnet-5", + "variant": "", + "input": 2.2, + "output": 11, + "cached_input": 0.22 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.deepseek.v3.2", + "variant": "", + "input": 0.74, + "output": 2.22 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.meta.llama3-2-1b-instruct-v1:0", + "variant": "", + "input": 0.13, + "output": 0.13 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.meta.llama3-2-3b-instruct-v1:0", + "variant": "", + "input": 0.19, + "output": 0.19 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.mistral.pixtral-large-2502-v1:0", + "variant": "", + "input": 2, + "output": 6 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.twelvelabs.marengo-embed-2-7-v1:0", + "variant": "", + "input": 70, + "output": 0 + }, + { + "provider": "AWS/Bedrock", + "model": "eu.twelvelabs.pegasus-1-2-v1:0", + "variant": "", + "output": 7.5 + }, + { + "provider": "AWS/Bedrock", + "model": "global.amazon.nova-2-lite-v1:0", + "variant": "", + "input": 0.3, + "output": 2.5, + "cached_input": 0.075 + }, + { + "provider": "AWS/Bedrock", + "model": "global.anthropic.claude-fable-5", + "variant": "", + "input": 10, + "output": 50, + "cached_input": 1 + }, + { + "provider": "AWS/Bedrock", + "model": "global.anthropic.claude-haiku-4-5-20251001-v1:0", + "variant": "", + "input": 1, + "output": 5, + "cached_input": 0.1 + }, + { + "provider": "AWS/Bedrock", + "model": "global.anthropic.claude-opus-4-5-20251101-v1:0", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "AWS/Bedrock", + "model": "global.anthropic.claude-opus-4-6-v1", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "AWS/Bedrock", + "model": "global.anthropic.claude-opus-4-7", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "AWS/Bedrock", + "model": "global.anthropic.claude-opus-4-8", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "AWS/Bedrock", + "model": "global.anthropic.claude-opus-5", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "AWS/Bedrock", + "model": "global.anthropic.claude-sonnet-4-20250514-v1:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "global.anthropic.claude-sonnet-4-20250514-v1:0", + "variant": "above_200k_tokens", + "input": 6, + "output": 22.5, + "cached_input": 0.6 + }, + { + "provider": "AWS/Bedrock", + "model": "global.anthropic.claude-sonnet-4-5-20250929-v1:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "global.anthropic.claude-sonnet-4-5-20250929-v1:0", + "variant": "above_200k_tokens", + "input": 6, + "output": 22.5, + "cached_input": 0.6 + }, + { + "provider": "AWS/Bedrock", + "model": "global.anthropic.claude-sonnet-4-6", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "global.anthropic.claude-sonnet-5", + "variant": "", + "input": 2, + "output": 10, + "cached_input": 0.2 + }, + { + "provider": "AWS/Bedrock", + "model": "google.gemma-3-12b-it", + "variant": "", + "input": 0.09, + "output": 0.29 + }, + { + "provider": "AWS/Bedrock", + "model": "google.gemma-3-27b-it", + "variant": "", + "input": 0.23, + "output": 0.38 + }, + { + "provider": "AWS/Bedrock", + "model": "google.gemma-3-4b-it", + "variant": "", + "input": 0.04, + "output": 0.08 + }, + { + "provider": "AWS/Bedrock", + "model": "google.gemma-4-26b-a4b", + "variant": "", + "input": 0.13, + "output": 0.4 + }, + { + "provider": "AWS/Bedrock", + "model": "google.gemma-4-31b", + "variant": "", + "input": 0.14, + "output": 0.4 + }, + { + "provider": "AWS/Bedrock", + "model": "google.gemma-4-e2b", + "variant": "", + "input": 0.04, + "output": 0.08 + }, + { + "provider": "AWS/Bedrock", + "model": "invoke/anthropic.claude-3-5-sonnet-20240620-v1:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "jp.anthropic.claude-haiku-4-5-20251001-v1:0", + "variant": "", + "input": 1.1, + "output": 5.5, + "cached_input": 0.11 + }, + { + "provider": "AWS/Bedrock", + "model": "jp.anthropic.claude-opus-4-7", + "variant": "", + "input": 5.5, + "output": 27.5, + "cached_input": 0.55 + }, + { + "provider": "AWS/Bedrock", + "model": "jp.anthropic.claude-opus-4-8", + "variant": "", + "input": 5.5, + "output": 27.5, + "cached_input": 0.55 + }, + { + "provider": "AWS/Bedrock", + "model": "jp.anthropic.claude-opus-5", + "variant": "", + "input": 5.5, + "output": 27.5, + "cached_input": 0.55 + }, + { + "provider": "AWS/Bedrock", + "model": "jp.anthropic.claude-sonnet-4-5-20250929-v1:0", + "variant": "", + "input": 3.3, + "output": 16.5, + "cached_input": 0.33 + }, + { + "provider": "AWS/Bedrock", + "model": "jp.anthropic.claude-sonnet-4-5-20250929-v1:0", + "variant": "above_200k_tokens", + "input": 6.6, + "output": 24.75, + "cached_input": 0.66 + }, + { + "provider": "AWS/Bedrock", + "model": "jp.anthropic.claude-sonnet-4-6", + "variant": "", + "input": 3.3, + "output": 16.5, + "cached_input": 0.33 + }, + { + "provider": "AWS/Bedrock", + "model": "jp.anthropic.claude-sonnet-5", + "variant": "", + "input": 2.2, + "output": 11, + "cached_input": 0.22 + }, + { + "provider": "AWS/Bedrock", + "model": "meta.llama2-13b-chat-v1", + "variant": "", + "input": 0.75, + "output": 1 + }, + { + "provider": "AWS/Bedrock", + "model": "meta.llama2-70b-chat-v1", + "variant": "", + "input": 1.95, + "output": 2.56 + }, + { + "provider": "AWS/Bedrock", + "model": "meta.llama3-1-405b-instruct-v1:0", + "variant": "", + "input": 5.32, + "output": 16 + }, + { + "provider": "AWS/Bedrock", + "model": "meta.llama3-1-70b-instruct-v1:0", + "variant": "", + "input": 0.99, + "output": 0.99 + }, + { + "provider": "AWS/Bedrock", + "model": "meta.llama3-1-8b-instruct-v1:0", + "variant": "", + "input": 0.22, + "output": 0.22 + }, + { + "provider": "AWS/Bedrock", + "model": "meta.llama3-2-11b-instruct-v1:0", + "variant": "", + "input": 0.35, + "output": 0.35 + }, + { + "provider": "AWS/Bedrock", + "model": "meta.llama3-2-1b-instruct-v1:0", + "variant": "", + "input": 0.1, + "output": 0.1 + }, + { + "provider": "AWS/Bedrock", + "model": "meta.llama3-2-3b-instruct-v1:0", + "variant": "", + "input": 0.15, + "output": 0.15 + }, + { + "provider": "AWS/Bedrock", + "model": "meta.llama3-2-90b-instruct-v1:0", + "variant": "", + "input": 2, + "output": 2 + }, + { + "provider": "AWS/Bedrock", + "model": "meta.llama3-3-70b-instruct-v1:0", + "variant": "", + "input": 0.72, + "output": 0.72 + }, + { + "provider": "AWS/Bedrock", + "model": "meta.llama3-70b-instruct-v1:0", + "variant": "", + "input": 2.65, + "output": 3.5 + }, + { + "provider": "AWS/Bedrock", + "model": "meta.llama3-8b-instruct-v1:0", + "variant": "", + "input": 0.3, + "output": 0.6 + }, + { + "provider": "AWS/Bedrock", + "model": "meta.llama4-maverick-17b-instruct-v1:0", + "variant": "", + "input": 0.24, + "output": 0.97 + }, + { + "provider": "AWS/Bedrock", + "model": "meta.llama4-maverick-17b-instruct-v1:0", + "variant": "batches", + "input": 0.12, + "output": 0.485 + }, + { + "provider": "AWS/Bedrock", + "model": "meta.llama4-scout-17b-instruct-v1:0", + "variant": "", + "input": 0.17, + "output": 0.66 + }, + { + "provider": "AWS/Bedrock", + "model": "meta.llama4-scout-17b-instruct-v1:0", + "variant": "batches", + "input": 0.085, + "output": 0.33 + }, + { + "provider": "AWS/Bedrock", + "model": "minimax.minimax-m2", + "variant": "", + "input": 0.3, + "output": 1.2 + }, + { + "provider": "AWS/Bedrock", + "model": "minimax.minimax-m2.1", + "variant": "", + "input": 0.3, + "output": 1.2 + }, + { + "provider": "AWS/Bedrock", + "model": "minimax.minimax-m2.5", + "variant": "", + "input": 0.3, + "output": 1.2 + }, + { + "provider": "AWS/Bedrock", + "model": "mistral.devstral-2-123b", + "variant": "", + "input": 0.4, + "output": 2 + }, + { + "provider": "AWS/Bedrock", + "model": "mistral.magistral-small-2509", + "variant": "", + "input": 0.5, + "output": 1.5 + }, + { + "provider": "AWS/Bedrock", + "model": "mistral.ministral-3-14b-instruct", + "variant": "", + "input": 0.2, + "output": 0.2 + }, + { + "provider": "AWS/Bedrock", + "model": "mistral.ministral-3-3b-instruct", + "variant": "", + "input": 0.1, + "output": 0.1 + }, + { + "provider": "AWS/Bedrock", + "model": "mistral.ministral-3-8b-instruct", + "variant": "", + "input": 0.15, + "output": 0.15 + }, + { + "provider": "AWS/Bedrock", + "model": "mistral.mistral-7b-instruct-v0:2", + "variant": "", + "input": 0.15, + "output": 0.2 + }, + { + "provider": "AWS/Bedrock", + "model": "mistral.mistral-large-2402-v1:0", + "variant": "", + "input": 8, + "output": 24 + }, + { + "provider": "AWS/Bedrock", + "model": "mistral.mistral-large-2407-v1:0", + "variant": "", + "input": 3, + "output": 9 + }, + { + "provider": "AWS/Bedrock", + "model": "mistral.mistral-large-3-675b-instruct", + "variant": "", + "input": 0.5, + "output": 1.5 + }, + { + "provider": "AWS/Bedrock", + "model": "mistral.mistral-small-2402-v1:0", + "variant": "", + "input": 1, + "output": 3 + }, + { + "provider": "AWS/Bedrock", + "model": "mistral.mixtral-8x7b-instruct-v0:1", + "variant": "", + "input": 0.45, + "output": 0.7 + }, + { + "provider": "AWS/Bedrock", + "model": "mistral.voxtral-mini-3b-2507", + "variant": "", + "input": 0.04, + "output": 0.04 + }, + { + "provider": "AWS/Bedrock", + "model": "mistral.voxtral-small-24b-2507", + "variant": "", + "input": 0.1, + "output": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "moonshot.kimi-k2-thinking", + "variant": "", + "input": 0.6, + "output": 2.5 + }, + { + "provider": "AWS/Bedrock", + "model": "moonshotai.kimi-k2-thinking", + "variant": "", + "input": 0.73, + "output": 3.03 + }, + { + "provider": "AWS/Bedrock", + "model": "moonshotai.kimi-k2.5", + "variant": "", + "input": 0.6, + "output": 3.03 + }, + { + "provider": "AWS/Bedrock", + "model": "nvidia.nemotron-nano-12b-v2", + "variant": "", + "input": 0.2, + "output": 0.6 + }, + { + "provider": "AWS/Bedrock", + "model": "nvidia.nemotron-nano-3-30b", + "variant": "", + "input": 0.06, + "output": 0.24 + }, + { + "provider": "AWS/Bedrock", + "model": "nvidia.nemotron-nano-9b-v2", + "variant": "", + "input": 0.06, + "output": 0.23 + }, + { + "provider": "AWS/Bedrock", + "model": "nvidia.nemotron-super-3-120b", + "variant": "", + "input": 0.15, + "output": 0.65 + }, + { + "provider": "AWS/Bedrock", + "model": "openai.gpt-5.4", + "variant": "", + "input": 2.75, + "output": 16.5, + "cached_input": 0.275 + }, + { + "provider": "AWS/Bedrock", + "model": "openai.gpt-5.5", + "variant": "", + "input": 5.5, + "output": 33, + "cached_input": 0.55 + }, + { + "provider": "AWS/Bedrock", + "model": "openai.gpt-5.6-luna", + "variant": "", + "input": 0.22, + "output": 1.32, + "cached_input": 0.022 + }, + { + "provider": "AWS/Bedrock", + "model": "openai.gpt-5.6-sol", + "variant": "", + "input": 5.5, + "output": 33, + "cached_input": 0.55 + }, + { + "provider": "AWS/Bedrock", + "model": "openai.gpt-5.6-terra", + "variant": "", + "input": 2.2, + "output": 13.2, + "cached_input": 0.22 + }, + { + "provider": "AWS/Bedrock", + "model": "openai.gpt-oss-120b", + "variant": "", + "input": 0.15, + "output": 0.6 + }, + { + "provider": "AWS/Bedrock", + "model": "openai.gpt-oss-120b-1:0", + "variant": "", + "input": 0.15, + "output": 0.6 + }, + { + "provider": "AWS/Bedrock", + "model": "openai.gpt-oss-20b", + "variant": "", + "input": 0.075, + "output": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "openai.gpt-oss-20b-1:0", + "variant": "", + "input": 0.07, + "output": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "openai.gpt-oss-safeguard-120b", + "variant": "", + "input": 0.15, + "output": 0.6 + }, + { + "provider": "AWS/Bedrock", + "model": "openai.gpt-oss-safeguard-20b", + "variant": "", + "input": 0.07, + "output": 0.2 + }, + { + "provider": "AWS/Bedrock", + "model": "qwen.qwen3-235b-a22b-2507-v1:0", + "variant": "", + "input": 0.22, + "output": 0.88 + }, + { + "provider": "AWS/Bedrock", + "model": "qwen.qwen3-32b-v1:0", + "variant": "", + "input": 0.15, + "output": 0.6 + }, + { + "provider": "AWS/Bedrock", + "model": "qwen.qwen3-coder-30b-a3b-v1:0", + "variant": "", + "input": 0.15, + "output": 0.6 + }, + { + "provider": "AWS/Bedrock", + "model": "qwen.qwen3-coder-480b-a35b-v1:0", + "variant": "", + "input": 0.22, + "output": 1.8 + }, + { + "provider": "AWS/Bedrock", + "model": "qwen.qwen3-coder-next", + "variant": "", + "input": 0.5, + "output": 1.2 + }, + { + "provider": "AWS/Bedrock", + "model": "qwen.qwen3-next-80b-a3b", + "variant": "", + "input": 0.15, + "output": 1.2 + }, + { + "provider": "AWS/Bedrock", + "model": "qwen.qwen3-vl-235b-a22b", + "variant": "", + "input": 0.53, + "output": 2.66 + }, + { + "provider": "AWS/Bedrock", + "model": "sa-east-1/deepseek.v3.2", + "variant": "", + "input": 0.74, + "output": 2.22 + }, + { + "provider": "AWS/Bedrock", + "model": "sa-east-1/meta.llama3-70b-instruct-v1:0", + "variant": "", + "input": 4.45, + "output": 5.88 + }, + { + "provider": "AWS/Bedrock", + "model": "sa-east-1/meta.llama3-8b-instruct-v1:0", + "variant": "", + "input": 0.5, + "output": 1.01 + }, + { + "provider": "AWS/Bedrock", + "model": "sa-east-1/minimax.minimax-m2.1", + "variant": "", + "input": 0.36, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "sa-east-1/minimax.minimax-m2.5", + "variant": "", + "input": 0.36, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "sa-east-1/moonshotai.kimi-k2-thinking", + "variant": "", + "input": 0.73, + "output": 3.03 + }, + { + "provider": "AWS/Bedrock", + "model": "sa-east-1/moonshotai.kimi-k2.5", + "variant": "", + "input": 0.72, + "output": 3.6 + }, + { + "provider": "AWS/Bedrock", + "model": "sa-east-1/qwen.qwen3-coder-next", + "variant": "", + "input": 0.6, + "output": 1.44 + }, + { + "provider": "AWS/Bedrock", + "model": "twelvelabs.marengo-embed-2-7-v1:0", + "variant": "", + "input": 70, + "output": 0 + }, + { + "provider": "AWS/Bedrock", + "model": "twelvelabs.pegasus-1-2-v1:0", + "variant": "", + "output": 7.5 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-1/anthropic.claude-instant-v1", + "variant": "", + "input": 0.8, + "output": 2.4 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-1/anthropic.claude-v1", + "variant": "", + "input": 8, + "output": 24 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-1/anthropic.claude-v2:1", + "variant": "", + "input": 8, + "output": 24 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-1/deepseek.v3.2", + "variant": "", + "input": 0.62, + "output": 1.85 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-1/meta.llama3-70b-instruct-v1:0", + "variant": "", + "input": 2.65, + "output": 3.5 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-1/meta.llama3-8b-instruct-v1:0", + "variant": "", + "input": 0.3, + "output": 0.6 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-1/minimax.minimax-m2.1", + "variant": "", + "input": 0.3, + "output": 1.2 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-1/minimax.minimax-m2.5", + "variant": "", + "input": 0.3, + "output": 1.2 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-1/mistral.mistral-7b-instruct-v0:2", + "variant": "", + "input": 0.15, + "output": 0.2 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-1/mistral.mistral-large-2402-v1:0", + "variant": "", + "input": 8, + "output": 24 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-1/mistral.mixtral-8x7b-instruct-v0:1", + "variant": "", + "input": 0.45, + "output": 0.7 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-1/moonshotai.kimi-k2-thinking", + "variant": "", + "input": 0.6, + "output": 2.5 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-1/moonshotai.kimi-k2.5", + "variant": "", + "input": 0.6, + "output": 3 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-1/qwen.qwen3-coder-next", + "variant": "", + "input": 0.5, + "output": 1.2 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-1/zai.glm-5", + "variant": "", + "input": 1, + "output": 3.2 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-2/deepseek.v3.2", + "variant": "", + "input": 0.62, + "output": 1.85 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-2/minimax.minimax-m2.1", + "variant": "", + "input": 0.3, + "output": 1.2 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-2/minimax.minimax-m2.5", + "variant": "", + "input": 0.3, + "output": 1.2 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-2/moonshotai.kimi-k2-thinking", + "variant": "", + "input": 0.6, + "output": 2.5 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-2/moonshotai.kimi-k2.5", + "variant": "", + "input": 0.6, + "output": 3 + }, + { + "provider": "AWS/Bedrock", + "model": "us-east-2/qwen.qwen3-coder-next", + "variant": "", + "input": 0.5, + "output": 1.2 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-east-1/amazon.nova-pro-v1:0", + "variant": "", + "input": 0.96, + "output": 3.84 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-east-1/amazon.titan-embed-text-v1", + "variant": "", + "input": 0.1, + "output": 0 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-east-1/amazon.titan-embed-text-v2:0", + "variant": "", + "input": 0.2, + "output": 0 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-east-1/amazon.titan-text-express-v1", + "variant": "", + "input": 1.3, + "output": 1.7 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-east-1/amazon.titan-text-lite-v1", + "variant": "", + "input": 0.3, + "output": 0.4 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-east-1/amazon.titan-text-premier-v1:0", + "variant": "", + "input": 0.5, + "output": 1.5 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-east-1/anthropic.claude-3-5-sonnet-20240620-v1:0", + "variant": "", + "input": 3.6, + "output": 18, + "cached_input": 0.36 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-east-1/anthropic.claude-3-haiku-20240307-v1:0", + "variant": "", + "input": 0.3, + "output": 1.5, + "cached_input": 0.03 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-east-1/anthropic.claude-haiku-4-5-20251001-v1:0", + "variant": "", + "input": 1.2, + "output": 6, + "cached_input": 0.12 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-east-1/anthropic.claude-sonnet-4-5-20250929-v1:0", + "variant": "", + "input": 3.6, + "output": 18, + "cached_input": 0.36 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-east-1/claude-sonnet-4-5-20250929-v1:0", + "variant": "", + "input": 3.6, + "output": 18, + "cached_input": 0.36 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-east-1/meta.llama3-70b-instruct-v1:0", + "variant": "", + "input": 2.65, + "output": 3.5 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-east-1/meta.llama3-8b-instruct-v1:0", + "variant": "", + "input": 0.3, + "output": 2.65 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-west-1/amazon.nova-pro-v1:0", + "variant": "", + "input": 0.96, + "output": 3.84 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-west-1/amazon.titan-embed-text-v1", + "variant": "", + "input": 0.1, + "output": 0 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-west-1/amazon.titan-embed-text-v2:0", + "variant": "", + "input": 0.2, + "output": 0 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-west-1/amazon.titan-text-express-v1", + "variant": "", + "input": 1.3, + "output": 1.7 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-west-1/amazon.titan-text-lite-v1", + "variant": "", + "input": 0.3, + "output": 0.4 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-west-1/amazon.titan-text-premier-v1:0", + "variant": "", + "input": 0.5, + "output": 1.5 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-west-1/anthropic.claude-3-5-sonnet-20240620-v1:0", + "variant": "", + "input": 3.6, + "output": 18, + "cached_input": 0.36 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-west-1/anthropic.claude-3-7-sonnet-20250219-v1:0", + "variant": "", + "input": 3.6, + "output": 18, + "cached_input": 0.36 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-west-1/anthropic.claude-3-haiku-20240307-v1:0", + "variant": "", + "input": 0.3, + "output": 1.5, + "cached_input": 0.03 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-west-1/anthropic.claude-haiku-4-5-20251001-v1:0", + "variant": "", + "input": 1.2, + "output": 6, + "cached_input": 0.12 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-west-1/anthropic.claude-sonnet-4-5-20250929-v1:0", + "variant": "", + "input": 3.6, + "output": 18, + "cached_input": 0.36 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-west-1/claude-sonnet-4-5-20250929-v1:0", + "variant": "", + "input": 3.6, + "output": 18, + "cached_input": 0.36 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-west-1/meta.llama3-70b-instruct-v1:0", + "variant": "", + "input": 2.65, + "output": 3.5 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov-west-1/meta.llama3-8b-instruct-v1:0", + "variant": "", + "input": 0.3, + "output": 2.65 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0", + "variant": "", + "input": 3.6, + "output": 18, + "cached_input": 0.36 + }, + { + "provider": "AWS/Bedrock", + "model": "us-gov.anthropic.claude-sonnet-4-5-20250929-v1:0", + "variant": "above_200k_tokens", + "input": 7.2, + "output": 27, + "cached_input": 0.72 + }, + { + "provider": "AWS/Bedrock", + "model": "us-west-1/meta.llama3-70b-instruct-v1:0", + "variant": "", + "input": 2.65, + "output": 3.5 + }, + { + "provider": "AWS/Bedrock", + "model": "us-west-1/meta.llama3-8b-instruct-v1:0", + "variant": "", + "input": 0.3, + "output": 0.6 + }, + { + "provider": "AWS/Bedrock", + "model": "us-west-2/anthropic.claude-instant-v1", + "variant": "", + "input": 0.8, + "output": 2.4 + }, + { + "provider": "AWS/Bedrock", + "model": "us-west-2/anthropic.claude-v1", + "variant": "", + "input": 8, + "output": 24 + }, + { + "provider": "AWS/Bedrock", + "model": "us-west-2/anthropic.claude-v2:1", + "variant": "", + "input": 8, + "output": 24 + }, + { + "provider": "AWS/Bedrock", + "model": "us-west-2/deepseek.v3.2", + "variant": "", + "input": 0.62, + "output": 1.85 + }, + { + "provider": "AWS/Bedrock", + "model": "us-west-2/minimax.minimax-m2.1", + "variant": "", + "input": 0.3, + "output": 1.2 + }, + { + "provider": "AWS/Bedrock", + "model": "us-west-2/minimax.minimax-m2.5", + "variant": "", + "input": 0.3, + "output": 1.2 + }, + { + "provider": "AWS/Bedrock", + "model": "us-west-2/mistral.mistral-7b-instruct-v0:2", + "variant": "", + "input": 0.15, + "output": 0.2 + }, + { + "provider": "AWS/Bedrock", + "model": "us-west-2/mistral.mistral-large-2402-v1:0", + "variant": "", + "input": 8, + "output": 24 + }, + { + "provider": "AWS/Bedrock", + "model": "us-west-2/mistral.mixtral-8x7b-instruct-v0:1", + "variant": "", + "input": 0.45, + "output": 0.7 + }, + { + "provider": "AWS/Bedrock", + "model": "us-west-2/moonshotai.kimi-k2-thinking", + "variant": "", + "input": 0.6, + "output": 2.5 + }, + { + "provider": "AWS/Bedrock", + "model": "us-west-2/moonshotai.kimi-k2.5", + "variant": "", + "input": 0.6, + "output": 3 + }, + { + "provider": "AWS/Bedrock", + "model": "us-west-2/qwen.qwen3-coder-next", + "variant": "", + "input": 0.5, + "output": 1.2 + }, + { + "provider": "AWS/Bedrock", + "model": "us-west-2/zai.glm-5", + "variant": "", + "input": 1, + "output": 3.2 + }, + { + "provider": "AWS/Bedrock", + "model": "us.amazon.nova-2-lite-v1:0", + "variant": "", + "input": 0.33, + "output": 2.75, + "cached_input": 0.0825 + }, + { + "provider": "AWS/Bedrock", + "model": "us.amazon.nova-2-pro-preview-20251202-v1:0", + "variant": "", + "input": 2.1875, + "output": 17.5, + "cached_input": 0.546875 + }, + { + "provider": "AWS/Bedrock", + "model": "us.amazon.nova-lite-v1:0", + "variant": "", + "input": 0.06, + "output": 0.24 + }, + { + "provider": "AWS/Bedrock", + "model": "us.amazon.nova-micro-v1:0", + "variant": "", + "input": 0.035, + "output": 0.14 + }, + { + "provider": "AWS/Bedrock", + "model": "us.amazon.nova-premier-v1:0", + "variant": "", + "input": 2.5, + "output": 12.5 + }, + { + "provider": "AWS/Bedrock", + "model": "us.amazon.nova-pro-v1:0", + "variant": "", + "input": 0.8, + "output": 3.2 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-3-5-haiku-20241022-v1:0", + "variant": "", + "input": 0.8, + "output": 4, + "cached_input": 0.08 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-3-5-sonnet-20240620-v1:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-3-5-sonnet-20241022-v2:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-3-7-sonnet-20250219-v1:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-3-haiku-20240307-v1:0", + "variant": "", + "input": 0.25, + "output": 1.25, + "cached_input": 0.025 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-3-opus-20240229-v1:0", + "variant": "", + "input": 15, + "output": 75, + "cached_input": 1.5 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-3-sonnet-20240229-v1:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-fable-5", + "variant": "", + "input": 11, + "output": 55, + "cached_input": 1.1 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-haiku-4-5-20251001-v1:0", + "variant": "", + "input": 1.1, + "output": 5.5, + "cached_input": 0.11 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-opus-4-1-20250805-v1:0", + "variant": "", + "input": 15, + "output": 75, + "cached_input": 1.5 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-opus-4-20250514-v1:0", + "variant": "", + "input": 15, + "output": 75, + "cached_input": 1.5 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-opus-4-5-20251101-v1:0", + "variant": "", + "input": 5.5, + "output": 27.5, + "cached_input": 0.55 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-opus-4-6-v1", + "variant": "", + "input": 5.5, + "output": 27.5, + "cached_input": 0.55 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-opus-4-7", + "variant": "", + "input": 5.5, + "output": 27.5, + "cached_input": 0.55 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-opus-4-8", + "variant": "", + "input": 5.5, + "output": 27.5, + "cached_input": 0.55 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-opus-5", + "variant": "", + "input": 5.5, + "output": 27.5, + "cached_input": 0.55 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-sonnet-4-20250514-v1:0", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-sonnet-4-20250514-v1:0", + "variant": "above_200k_tokens", + "input": 6, + "output": 22.5, + "cached_input": 0.6 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-sonnet-4-5-20250929-v1:0", + "variant": "", + "input": 3.3, + "output": 16.5, + "cached_input": 0.33 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-sonnet-4-5-20250929-v1:0", + "variant": "above_200k_tokens", + "input": 6.6, + "output": 24.75, + "cached_input": 0.66 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-sonnet-4-6", + "variant": "", + "input": 3.3, + "output": 16.5, + "cached_input": 0.33 + }, + { + "provider": "AWS/Bedrock", + "model": "us.anthropic.claude-sonnet-5", + "variant": "", + "input": 2.2, + "output": 11, + "cached_input": 0.22 + }, + { + "provider": "AWS/Bedrock", + "model": "us.deepseek.r1-v1:0", + "variant": "", + "input": 1.35, + "output": 5.4 + }, + { + "provider": "AWS/Bedrock", + "model": "us.deepseek.v3.2", + "variant": "", + "input": 0.62, + "output": 1.85 + }, + { + "provider": "AWS/Bedrock", + "model": "us.meta.llama3-1-405b-instruct-v1:0", + "variant": "", + "input": 5.32, + "output": 16 + }, + { + "provider": "AWS/Bedrock", + "model": "us.meta.llama3-1-70b-instruct-v1:0", + "variant": "", + "input": 0.99, + "output": 0.99 + }, + { + "provider": "AWS/Bedrock", + "model": "us.meta.llama3-1-8b-instruct-v1:0", + "variant": "", + "input": 0.22, + "output": 0.22 + }, + { + "provider": "AWS/Bedrock", + "model": "us.meta.llama3-2-11b-instruct-v1:0", + "variant": "", + "input": 0.35, + "output": 0.35 + }, + { + "provider": "AWS/Bedrock", + "model": "us.meta.llama3-2-1b-instruct-v1:0", + "variant": "", + "input": 0.1, + "output": 0.1 + }, + { + "provider": "AWS/Bedrock", + "model": "us.meta.llama3-2-3b-instruct-v1:0", + "variant": "", + "input": 0.15, + "output": 0.15 + }, + { + "provider": "AWS/Bedrock", + "model": "us.meta.llama3-2-90b-instruct-v1:0", + "variant": "", + "input": 2, + "output": 2 + }, + { + "provider": "AWS/Bedrock", + "model": "us.meta.llama3-3-70b-instruct-v1:0", + "variant": "", + "input": 0.72, + "output": 0.72 + }, + { + "provider": "AWS/Bedrock", + "model": "us.meta.llama4-maverick-17b-instruct-v1:0", + "variant": "", + "input": 0.24, + "output": 0.97 + }, + { + "provider": "AWS/Bedrock", + "model": "us.meta.llama4-maverick-17b-instruct-v1:0", + "variant": "batches", + "input": 0.12, + "output": 0.485 + }, + { + "provider": "AWS/Bedrock", + "model": "us.meta.llama4-scout-17b-instruct-v1:0", + "variant": "", + "input": 0.17, + "output": 0.66 + }, + { + "provider": "AWS/Bedrock", + "model": "us.meta.llama4-scout-17b-instruct-v1:0", + "variant": "batches", + "input": 0.085, + "output": 0.33 + }, + { + "provider": "AWS/Bedrock", + "model": "us.mistral.pixtral-large-2502-v1:0", + "variant": "", + "input": 2, + "output": 6 + }, + { + "provider": "AWS/Bedrock", + "model": "us.twelvelabs.marengo-embed-2-7-v1:0", + "variant": "", + "input": 70, + "output": 0 + }, + { + "provider": "AWS/Bedrock", + "model": "us.twelvelabs.pegasus-1-2-v1:0", + "variant": "", + "output": 7.5 + }, + { + "provider": "AWS/Bedrock", + "model": "us.writer.palmyra-x4-v1:0", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "AWS/Bedrock", + "model": "us.writer.palmyra-x5-v1:0", + "variant": "", + "input": 0.6, + "output": 6 + }, + { + "provider": "AWS/Bedrock", + "model": "writer.palmyra-x4-v1:0", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "AWS/Bedrock", + "model": "writer.palmyra-x5-v1:0", + "variant": "", + "input": 0.6, + "output": 6 + }, + { + "provider": "AWS/Bedrock", + "model": "xai.grok-4.3", + "variant": "", + "input": 1.25, + "output": 2.5, + "cached_input": 0.2 + }, + { + "provider": "AWS/Bedrock", + "model": "zai.glm-4.7", + "variant": "", + "input": 0.6, + "output": 2.2 + }, + { + "provider": "AWS/Bedrock", + "model": "zai.glm-4.7-flash", + "variant": "", + "input": 0.07, + "output": 0.4 + }, + { + "provider": "AWS/Bedrock", + "model": "zai.glm-5", + "variant": "", + "input": 1, + "output": 3.2 + }, + { + "provider": "Anthropic", + "model": "claude-3-7-sonnet-20250219", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "Anthropic", + "model": "claude-3-haiku-20240307", + "variant": "", + "input": 0.25, + "output": 1.25, + "cached_input": 0.03 + }, + { + "provider": "Anthropic", + "model": "claude-3-opus-20240229", + "variant": "", + "input": 15, + "output": 75, + "cached_input": 1.5 + }, + { + "provider": "Anthropic", + "model": "claude-4-opus-20250514", + "variant": "", + "input": 15, + "output": 75, + "cached_input": 1.5 + }, + { + "provider": "Anthropic", + "model": "claude-4-sonnet-20250514", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "Anthropic", + "model": "claude-4-sonnet-20250514", + "variant": "above_200k_tokens", + "input": 6, + "output": 22.5, + "cached_input": 0.6 + }, + { + "provider": "Anthropic", + "model": "claude-fable-5", + "variant": "", + "input": 10, + "output": 50, + "cached_input": 1 + }, + { + "provider": "Anthropic", + "model": "claude-haiku-4-5", + "variant": "", + "input": 1, + "output": 5, + "cached_input": 0.1 + }, + { + "provider": "Anthropic", + "model": "claude-haiku-4-5-20251001", + "variant": "", + "input": 1, + "output": 5, + "cached_input": 0.1 + }, + { + "provider": "Anthropic", + "model": "claude-opus-4-1", + "variant": "", + "input": 15, + "output": 75, + "cached_input": 1.5 + }, + { + "provider": "Anthropic", + "model": "claude-opus-4-1-20250805", + "variant": "", + "input": 15, + "output": 75, + "cached_input": 1.5 + }, + { + "provider": "Anthropic", + "model": "claude-opus-4-20250514", + "variant": "", + "input": 15, + "output": 75, + "cached_input": 1.5 + }, + { + "provider": "Anthropic", + "model": "claude-opus-4-5", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "Anthropic", + "model": "claude-opus-4-5-20251101", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "Anthropic", + "model": "claude-opus-4-6", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "Anthropic", + "model": "claude-opus-4-6-20260205", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "Anthropic", + "model": "claude-opus-4-7", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "Anthropic", + "model": "claude-opus-4-7-20260416", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "Anthropic", + "model": "claude-opus-4-8", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "Anthropic", + "model": "claude-opus-5", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "Anthropic", + "model": "claude-sonnet-4-20250514", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "Anthropic", + "model": "claude-sonnet-4-20250514", + "variant": "above_200k_tokens", + "input": 6, + "output": 22.5, + "cached_input": 0.6 + }, + { + "provider": "Anthropic", + "model": "claude-sonnet-4-5", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "Anthropic", + "model": "claude-sonnet-4-5", + "variant": "above_200k_tokens", + "input": 6, + "output": 22.5, + "cached_input": 0.6 + }, + { + "provider": "Anthropic", + "model": "claude-sonnet-4-5-20250929", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "Anthropic", + "model": "claude-sonnet-4-5-20250929", + "variant": "above_200k_tokens", + "input": 6, + "output": 22.5, + "cached_input": 0.6 + }, + { + "provider": "Anthropic", + "model": "claude-sonnet-4-6", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "Anthropic", + "model": "claude-sonnet-5", + "variant": "", + "input": 2, + "output": 10, + "cached_input": 0.2 + }, + { + "provider": "Azure/OpenAI", + "model": "ada", + "variant": "", + "input": 0.1, + "output": 0 + }, + { + "provider": "Azure/OpenAI", + "model": "codex-mini", + "variant": "", + "input": 1.5, + "output": 6, + "cached_input": 0.375 + }, + { + "provider": "Azure/OpenAI", + "model": "command-r-plus", + "variant": "", + "input": 3, + "output": 15 + }, + { + "provider": "Azure/OpenAI", + "model": "computer-use-preview", + "variant": "", + "input": 3, + "output": 12 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-4o-2024-08-06", + "variant": "", + "input": 2.75, + "output": 11, + "cached_input": 1.375 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-4o-2024-11-20", + "variant": "", + "input": 2.75, + "output": 11 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-4o-mini-2024-07-18", + "variant": "", + "input": 0.165, + "output": 0.66, + "cached_input": 0.083 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-4o-mini-realtime-preview-2024-12-17", + "variant": "", + "input": 0.66, + "output": 2.64, + "cached_input": 0.33 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-4o-realtime-preview-2024-10-01", + "variant": "", + "input": 5.5, + "output": 22, + "cached_input": 2.75 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-4o-realtime-preview-2024-12-17", + "variant": "", + "input": 5.5, + "output": 22, + "cached_input": 2.75 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5-2025-08-07", + "variant": "", + "input": 1.375, + "output": 11, + "cached_input": 0.1375 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5-mini-2025-08-07", + "variant": "", + "input": 0.275, + "output": 2.2, + "cached_input": 0.0275 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5-nano-2025-08-07", + "variant": "", + "input": 0.055, + "output": 0.44, + "cached_input": 0.0055 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.1", + "variant": "", + "input": 1.38, + "output": 11, + "cached_input": 0.14 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.1-chat", + "variant": "", + "input": 1.38, + "output": 11, + "cached_input": 0.14 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.1-codex", + "variant": "", + "input": 1.38, + "output": 11, + "cached_input": 0.14 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.1-codex-mini", + "variant": "", + "input": 0.275, + "output": 2.2, + "cached_input": 0.028 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.4", + "variant": "", + "input": 2.75, + "output": 16.5, + "cached_input": 0.28 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.4", + "variant": "priority", + "input": 5.5, + "output": 33, + "cached_input": 0.55 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.4-2026-03-05", + "variant": "", + "input": 2.75, + "output": 16.5, + "cached_input": 0.28 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.4-2026-03-05", + "variant": "priority", + "input": 5.5, + "output": 33, + "cached_input": 0.55 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.5", + "variant": "", + "input": 5.5, + "output": 33, + "cached_input": 0.55 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.5", + "variant": "above_272k_tokens", + "input": 11, + "output": 49.5, + "cached_input": 1.1 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.5", + "variant": "priority", + "input": 13.75, + "output": 82.5, + "cached_input": 1.38 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.5-2026-04-23", + "variant": "", + "input": 5.5, + "output": 33, + "cached_input": 0.55 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.5-2026-04-23", + "variant": "above_272k_tokens", + "input": 11, + "output": 49.5, + "cached_input": 1.1 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.5-2026-04-23", + "variant": "priority", + "input": 13.75, + "output": 82.5, + "cached_input": 1.38 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.6", + "variant": "", + "input": 5.5, + "output": 33, + "cached_input": 0.55 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.6", + "variant": "above_272k_tokens", + "input": 11, + "output": 49.5, + "cached_input": 1.1 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.6", + "variant": "priority", + "input": 13.75, + "output": 82.5, + "cached_input": 1.375 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.6-luna", + "variant": "", + "input": 1.1, + "output": 6.6, + "cached_input": 0.11 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.6-luna", + "variant": "above_272k_tokens", + "input": 2.2, + "output": 9.9, + "cached_input": 0.22 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.6-luna", + "variant": "priority", + "input": 2.75, + "output": 16.5, + "cached_input": 0.275 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.6-sol", + "variant": "", + "input": 5.5, + "output": 33, + "cached_input": 0.55 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.6-sol", + "variant": "above_272k_tokens", + "input": 11, + "output": 49.5, + "cached_input": 1.1 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.6-sol", + "variant": "priority", + "input": 13.75, + "output": 82.5, + "cached_input": 1.375 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.6-terra", + "variant": "", + "input": 2.75, + "output": 16.5, + "cached_input": 0.275 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.6-terra", + "variant": "above_272k_tokens", + "input": 5.5, + "output": 24.75, + "cached_input": 0.55 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/gpt-5.6-terra", + "variant": "priority", + "input": 6.875, + "output": 41.25, + "cached_input": 0.6875 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/o1-2024-12-17", + "variant": "", + "input": 16.5, + "output": 66, + "cached_input": 8.25 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/o1-mini-2024-09-12", + "variant": "", + "input": 1.21, + "output": 4.84, + "cached_input": 0.605 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/o1-mini-2024-09-12", + "variant": "batches", + "input": 0.605, + "output": 2.42 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/o1-preview-2024-09-12", + "variant": "", + "input": 16.5, + "output": 66, + "cached_input": 8.25 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/o3-mini-2025-01-31", + "variant": "", + "input": 1.21, + "output": 4.84, + "cached_input": 0.605 + }, + { + "provider": "Azure/OpenAI", + "model": "eu/o3-mini-2025-01-31", + "variant": "batches", + "input": 0.605, + "output": 2.42 + }, + { + "provider": "Azure/OpenAI", + "model": "global-standard/gpt-4o-2024-08-06", + "variant": "", + "input": 2.5, + "output": 10, + "cached_input": 1.25 + }, + { + "provider": "Azure/OpenAI", + "model": "global-standard/gpt-4o-2024-11-20", + "variant": "", + "input": 2.5, + "output": 10, + "cached_input": 1.25 + }, + { + "provider": "Azure/OpenAI", + "model": "global-standard/gpt-4o-mini", + "variant": "", + "input": 0.15, + "output": 0.6 + }, + { + "provider": "Azure/OpenAI", + "model": "global/gpt-4o-2024-08-06", + "variant": "", + "input": 2.5, + "output": 10, + "cached_input": 1.25 + }, + { + "provider": "Azure/OpenAI", + "model": "global/gpt-4o-2024-11-20", + "variant": "", + "input": 2.5, + "output": 10, + "cached_input": 1.25 + }, + { + "provider": "Azure/OpenAI", + "model": "global/gpt-5.1", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "Azure/OpenAI", + "model": "global/gpt-5.1-chat", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "Azure/OpenAI", + "model": "global/gpt-5.1-codex", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "Azure/OpenAI", + "model": "global/gpt-5.1-codex-mini", + "variant": "", + "input": 0.25, + "output": 2, + "cached_input": 0.025 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-3.5-turbo", + "variant": "", + "input": 0.5, + "output": 1.5 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-3.5-turbo-0125", + "variant": "", + "input": 0.5, + "output": 1.5 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-35-turbo", + "variant": "", + "input": 0.5, + "output": 1.5 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-35-turbo-0125", + "variant": "", + "input": 0.5, + "output": 1.5 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-35-turbo-1106", + "variant": "", + "input": 1, + "output": 2 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-35-turbo-16k", + "variant": "", + "input": 3, + "output": 4 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-35-turbo-16k-0613", + "variant": "", + "input": 3, + "output": 4 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4", + "variant": "", + "input": 30, + "output": 60 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4-0125-preview", + "variant": "", + "input": 10, + "output": 30 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4-0613", + "variant": "", + "input": 30, + "output": 60 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4-1106-preview", + "variant": "", + "input": 10, + "output": 30 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4-32k", + "variant": "", + "input": 60, + "output": 120 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4-32k-0613", + "variant": "", + "input": 60, + "output": 120 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4-turbo", + "variant": "", + "input": 10, + "output": 30 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4-turbo-2024-04-09", + "variant": "", + "input": 10, + "output": 30 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4-turbo-vision-preview", + "variant": "", + "input": 10, + "output": 30 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4.1", + "variant": "", + "input": 2, + "output": 8, + "cached_input": 0.5 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4.1", + "variant": "batches", + "input": 1, + "output": 4 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4.1-2025-04-14", + "variant": "", + "input": 2, + "output": 8, + "cached_input": 0.5 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4.1-2025-04-14", + "variant": "batches", + "input": 1, + "output": 4 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4.1-mini", + "variant": "", + "input": 0.4, + "output": 1.6, + "cached_input": 0.1 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4.1-mini", + "variant": "batches", + "input": 0.2, + "output": 0.8 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4.1-mini-2025-04-14", + "variant": "", + "input": 0.4, + "output": 1.6, + "cached_input": 0.1 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4.1-mini-2025-04-14", + "variant": "batches", + "input": 0.2, + "output": 0.8 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4.1-nano", + "variant": "", + "input": 0.1, + "output": 0.4, + "cached_input": 0.025 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4.1-nano", + "variant": "batches", + "input": 0.05, + "output": 0.2 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4.1-nano-2025-04-14", + "variant": "", + "input": 0.1, + "output": 0.4, + "cached_input": 0.025 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4.1-nano-2025-04-14", + "variant": "batches", + "input": 0.05, + "output": 0.2 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4.5-preview", + "variant": "", + "input": 75, + "output": 150, + "cached_input": 37.5 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4.5-preview", + "variant": "batches", + "input": 37.5, + "output": 75 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4o", + "variant": "", + "input": 2.5, + "output": 10, + "cached_input": 1.25 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4o-2024-05-13", + "variant": "", + "input": 5, + "output": 15 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4o-2024-08-06", + "variant": "", + "input": 2.5, + "output": 10, + "cached_input": 1.25 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4o-2024-11-20", + "variant": "", + "input": 2.75, + "output": 11, + "cached_input": 1.25 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4o-audio-preview-2024-12-17", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4o-mini", + "variant": "", + "input": 0.165, + "output": 0.66, + "cached_input": 0.075 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4o-mini-2024-07-18", + "variant": "", + "input": 0.165, + "output": 0.66, + "cached_input": 0.075 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4o-mini-audio-preview-2024-12-17", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4o-mini-realtime-preview-2024-12-17", + "variant": "", + "input": 0.6, + "output": 2.4, + "cached_input": 0.3 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4o-mini-transcribe", + "variant": "", + "input": 1.25, + "output": 5 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4o-mini-tts", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4o-realtime-preview-2024-10-01", + "variant": "", + "input": 5, + "output": 20, + "cached_input": 2.5 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4o-realtime-preview-2024-12-17", + "variant": "", + "input": 5, + "output": 20, + "cached_input": 2.5 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4o-transcribe", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-4o-transcribe-diarize", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5-2025-08-07", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5-chat", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5-chat-latest", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5-codex", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5-mini", + "variant": "", + "input": 0.25, + "output": 2, + "cached_input": 0.025 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5-mini-2025-08-07", + "variant": "", + "input": 0.25, + "output": 2, + "cached_input": 0.025 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5-nano", + "variant": "", + "input": 0.05, + "output": 0.4, + "cached_input": 0.005 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5-nano-2025-08-07", + "variant": "", + "input": 0.05, + "output": 0.4, + "cached_input": 0.005 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5-pro", + "variant": "", + "input": 15, + "output": 120 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.1", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.1-2025-11-13", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.1-2025-11-13", + "variant": "priority", + "input": 2.5, + "output": 20, + "cached_input": 0.25 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.1-chat", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.1-chat-2025-11-13", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.1-chat-2025-11-13", + "variant": "priority", + "input": 2.5, + "output": 20, + "cached_input": 0.25 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.1-codex", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.1-codex-2025-11-13", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.1-codex-2025-11-13", + "variant": "priority", + "input": 2.5, + "output": 20, + "cached_input": 0.25 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.1-codex-max", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.1-codex-mini", + "variant": "", + "input": 0.25, + "output": 2, + "cached_input": 0.025 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.1-codex-mini-2025-11-13", + "variant": "", + "input": 0.25, + "output": 2, + "cached_input": 0.025 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.1-codex-mini-2025-11-13", + "variant": "priority", + "input": 0.45, + "output": 3.6, + "cached_input": 0.045 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.2", + "variant": "", + "input": 1.75, + "output": 14, + "cached_input": 0.175 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.2-2025-12-11", + "variant": "", + "input": 1.75, + "output": 14, + "cached_input": 0.175 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.2-2025-12-11", + "variant": "priority", + "input": 3.5, + "output": 28, + "cached_input": 0.35 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.2-chat", + "variant": "", + "input": 1.75, + "output": 14, + "cached_input": 0.175 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.2-chat", + "variant": "priority", + "input": 3.5, + "output": 28, + "cached_input": 0.35 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.2-chat-2025-12-11", + "variant": "", + "input": 1.75, + "output": 14, + "cached_input": 0.175 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.2-chat-2025-12-11", + "variant": "priority", + "input": 3.5, + "output": 28, + "cached_input": 0.35 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.2-codex", + "variant": "", + "input": 1.75, + "output": 14, + "cached_input": 0.175 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.2-pro", + "variant": "", + "input": 21, + "output": 168 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.2-pro-2025-12-11", + "variant": "", + "input": 21, + "output": 168 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.3-chat", + "variant": "", + "input": 1.75, + "output": 14, + "cached_input": 0.175 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.3-chat", + "variant": "priority", + "input": 3.5, + "output": 28, + "cached_input": 0.35 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.3-codex", + "variant": "", + "input": 1.75, + "output": 14, + "cached_input": 0.175 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.4", + "variant": "", + "input": 2.5, + "output": 15, + "cached_input": 0.25 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.4", + "variant": "above_272k_tokens", + "input": 5, + "output": 22.5, + "cached_input": 0.5 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.4", + "variant": "above_272k_tokens_priority", + "input": 10, + "output": 45, + "cached_input": 1 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.4", + "variant": "priority", + "input": 5, + "output": 30, + "cached_input": 0.5 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.4-2026-03-05", + "variant": "", + "input": 2.5, + "output": 15, + "cached_input": 0.25 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.4-2026-03-05", + "variant": "above_272k_tokens", + "input": 5, + "output": 22.5, + "cached_input": 0.5 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.4-2026-03-05", + "variant": "above_272k_tokens_priority", + "input": 10, + "output": 45, + "cached_input": 1 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.4-2026-03-05", + "variant": "priority", + "input": 5, + "output": 30, + "cached_input": 0.5 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.4-mini", + "variant": "", + "input": 0.75, + "output": 4.5, + "cached_input": 0.075 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.4-mini-2026-03-17", + "variant": "", + "input": 0.75, + "output": 4.5, + "cached_input": 0.075 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.4-nano", + "variant": "", + "input": 0.2, + "output": 1.25, + "cached_input": 0.02 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.4-nano-2026-03-17", + "variant": "", + "input": 0.2, + "output": 1.25, + "cached_input": 0.02 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.4-pro", + "variant": "", + "input": 30, + "output": 180, + "cached_input": 3 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.4-pro", + "variant": "above_272k_tokens", + "input": 60, + "output": 270, + "cached_input": 6 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.4-pro-2026-03-05", + "variant": "", + "input": 30, + "output": 180, + "cached_input": 3 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.4-pro-2026-03-05", + "variant": "above_272k_tokens", + "input": 60, + "output": 270, + "cached_input": 6 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.5", + "variant": "", + "input": 5, + "output": 30, + "cached_input": 0.5 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.5", + "variant": "above_272k_tokens", + "input": 10, + "output": 45, + "cached_input": 1 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.5", + "variant": "above_272k_tokens_priority", + "input": 20, + "output": 90, + "cached_input": 2 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.5", + "variant": "priority", + "input": 10, + "output": 60, + "cached_input": 1 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.5-2026-04-23", + "variant": "", + "input": 5, + "output": 30, + "cached_input": 0.5 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.5-2026-04-23", + "variant": "above_272k_tokens", + "input": 10, + "output": 45, + "cached_input": 1 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.5-2026-04-23", + "variant": "above_272k_tokens_priority", + "input": 20, + "output": 90, + "cached_input": 2 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.5-2026-04-23", + "variant": "priority", + "input": 10, + "output": 60, + "cached_input": 1 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.5-pro", + "variant": "", + "input": 30, + "output": 180, + "cached_input": 3 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.5-pro", + "variant": "above_272k_tokens", + "input": 60, + "output": 270, + "cached_input": 6 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.5-pro-2026-04-23", + "variant": "", + "input": 30, + "output": 180, + "cached_input": 3 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.5-pro-2026-04-23", + "variant": "above_272k_tokens", + "input": 60, + "output": 270, + "cached_input": 6 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.6", + "variant": "", + "input": 5, + "output": 30, + "cached_input": 0.5 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.6", + "variant": "above_272k_tokens", + "input": 10, + "output": 45, + "cached_input": 1 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.6", + "variant": "above_272k_tokens_priority", + "input": 20, + "output": 90, + "cached_input": 2 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.6", + "variant": "priority", + "input": 10, + "output": 60, + "cached_input": 1 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.6-luna", + "variant": "", + "input": 1, + "output": 6, + "cached_input": 0.1 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.6-luna", + "variant": "above_272k_tokens", + "input": 2, + "output": 9, + "cached_input": 0.2 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.6-luna", + "variant": "above_272k_tokens_priority", + "input": 4, + "output": 18, + "cached_input": 0.4 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.6-luna", + "variant": "priority", + "input": 2, + "output": 12, + "cached_input": 0.2 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.6-sol", + "variant": "", + "input": 5, + "output": 30, + "cached_input": 0.5 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.6-sol", + "variant": "above_272k_tokens", + "input": 10, + "output": 45, + "cached_input": 1 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.6-sol", + "variant": "above_272k_tokens_priority", + "input": 20, + "output": 90, + "cached_input": 2 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.6-sol", + "variant": "priority", + "input": 10, + "output": 60, + "cached_input": 1 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.6-terra", + "variant": "", + "input": 2.5, + "output": 15, + "cached_input": 0.25 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.6-terra", + "variant": "above_272k_tokens", + "input": 5, + "output": 22.5, + "cached_input": 0.5 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.6-terra", + "variant": "above_272k_tokens_priority", + "input": 10, + "output": 45, + "cached_input": 1 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-5.6-terra", + "variant": "priority", + "input": 5, + "output": 30, + "cached_input": 0.5 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-audio-1.5-2026-02-23", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-audio-2025-08-28", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-audio-mini-2025-10-06", + "variant": "", + "input": 0.6, + "output": 2.4 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-image-1", + "variant": "", + "input": 5, + "cached_input": 1.25 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-image-1-mini", + "variant": "", + "input": 2, + "cached_input": 0.2 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-image-1.5", + "variant": "", + "input": 5, + "cached_input": 1.25 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-image-1.5-2025-12-16", + "variant": "", + "input": 5, + "cached_input": 1.25 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-image-2", + "variant": "", + "input": 5, + "output": 10, + "cached_input": 1.25 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-image-2-2026-04-21", + "variant": "", + "input": 5, + "output": 10, + "cached_input": 1.25 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-realtime-1.5-2026-02-23", + "variant": "", + "input": 4, + "output": 16, + "cached_input": 4 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-realtime-2025-08-28", + "variant": "", + "input": 4, + "output": 16, + "cached_input": 4 + }, + { + "provider": "Azure/OpenAI", + "model": "gpt-realtime-mini-2025-10-06", + "variant": "", + "input": 0.6, + "output": 2.4, + "cached_input": 0.06 + }, + { + "provider": "Azure/OpenAI", + "model": "mistral-large-2402", + "variant": "", + "input": 8, + "output": 24 + }, + { + "provider": "Azure/OpenAI", + "model": "mistral-large-latest", + "variant": "", + "input": 8, + "output": 24 + }, + { + "provider": "Azure/OpenAI", + "model": "o1", + "variant": "", + "input": 15, + "output": 60, + "cached_input": 7.5 + }, + { + "provider": "Azure/OpenAI", + "model": "o1-2024-12-17", + "variant": "", + "input": 15, + "output": 60, + "cached_input": 7.5 + }, + { + "provider": "Azure/OpenAI", + "model": "o1-mini", + "variant": "", + "input": 1.21, + "output": 4.84, + "cached_input": 0.605 + }, + { + "provider": "Azure/OpenAI", + "model": "o1-mini-2024-09-12", + "variant": "", + "input": 1.1, + "output": 4.4, + "cached_input": 0.55 + }, + { + "provider": "Azure/OpenAI", + "model": "o1-preview", + "variant": "", + "input": 15, + "output": 60, + "cached_input": 7.5 + }, + { + "provider": "Azure/OpenAI", + "model": "o1-preview-2024-09-12", + "variant": "", + "input": 15, + "output": 60, + "cached_input": 7.5 + }, + { + "provider": "Azure/OpenAI", + "model": "o3", + "variant": "", + "input": 2, + "output": 8, + "cached_input": 0.5 + }, + { + "provider": "Azure/OpenAI", + "model": "o3-2025-04-16", + "variant": "", + "input": 2, + "output": 8, + "cached_input": 0.5 + }, + { + "provider": "Azure/OpenAI", + "model": "o3-deep-research", + "variant": "", + "input": 10, + "output": 40, + "cached_input": 2.5 + }, + { + "provider": "Azure/OpenAI", + "model": "o3-mini", + "variant": "", + "input": 1.1, + "output": 4.4, + "cached_input": 0.55 + }, + { + "provider": "Azure/OpenAI", + "model": "o3-mini-2025-01-31", + "variant": "", + "input": 1.1, + "output": 4.4, + "cached_input": 0.55 + }, + { + "provider": "Azure/OpenAI", + "model": "o3-pro", + "variant": "", + "input": 20, + "output": 80 + }, + { + "provider": "Azure/OpenAI", + "model": "o3-pro", + "variant": "batches", + "input": 10, + "output": 40 + }, + { + "provider": "Azure/OpenAI", + "model": "o3-pro-2025-06-10", + "variant": "", + "input": 20, + "output": 80 + }, + { + "provider": "Azure/OpenAI", + "model": "o3-pro-2025-06-10", + "variant": "batches", + "input": 10, + "output": 40 + }, + { + "provider": "Azure/OpenAI", + "model": "o4-mini", + "variant": "", + "input": 1.1, + "output": 4.4, + "cached_input": 0.275 + }, + { + "provider": "Azure/OpenAI", + "model": "o4-mini-2025-04-16", + "variant": "", + "input": 1.1, + "output": 4.4, + "cached_input": 0.275 + }, + { + "provider": "Azure/OpenAI", + "model": "text-embedding-3-large", + "variant": "", + "input": 0.13, + "output": 0 + }, + { + "provider": "Azure/OpenAI", + "model": "text-embedding-3-small", + "variant": "", + "input": 0.02, + "output": 0 + }, + { + "provider": "Azure/OpenAI", + "model": "text-embedding-ada-002", + "variant": "", + "input": 0.1, + "output": 0 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-4.1-2025-04-14", + "variant": "", + "input": 2.2, + "output": 8.8, + "cached_input": 0.55 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-4.1-2025-04-14", + "variant": "batches", + "input": 1.1, + "output": 4.4 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-4.1-mini-2025-04-14", + "variant": "", + "input": 0.44, + "output": 1.76, + "cached_input": 0.11 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-4.1-mini-2025-04-14", + "variant": "batches", + "input": 0.22, + "output": 0.88 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-4.1-nano-2025-04-14", + "variant": "", + "input": 0.11, + "output": 0.44, + "cached_input": 0.025 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-4.1-nano-2025-04-14", + "variant": "batches", + "input": 0.06, + "output": 0.22 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-4o-2024-08-06", + "variant": "", + "input": 2.75, + "output": 11, + "cached_input": 1.375 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-4o-2024-11-20", + "variant": "", + "input": 2.75, + "output": 11 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-4o-mini-2024-07-18", + "variant": "", + "input": 0.165, + "output": 0.66, + "cached_input": 0.083 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-4o-mini-realtime-preview-2024-12-17", + "variant": "", + "input": 0.66, + "output": 2.64, + "cached_input": 0.33 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-4o-realtime-preview-2024-10-01", + "variant": "", + "input": 5.5, + "output": 22, + "cached_input": 2.75 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-4o-realtime-preview-2024-12-17", + "variant": "", + "input": 5.5, + "output": 22, + "cached_input": 2.75 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5-2025-08-07", + "variant": "", + "input": 1.375, + "output": 11, + "cached_input": 0.1375 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5-mini-2025-08-07", + "variant": "", + "input": 0.275, + "output": 2.2, + "cached_input": 0.0275 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5-nano-2025-08-07", + "variant": "", + "input": 0.055, + "output": 0.44, + "cached_input": 0.0055 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.1", + "variant": "", + "input": 1.38, + "output": 11, + "cached_input": 0.14 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.1-chat", + "variant": "", + "input": 1.38, + "output": 11, + "cached_input": 0.14 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.1-codex", + "variant": "", + "input": 1.38, + "output": 11, + "cached_input": 0.14 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.1-codex-mini", + "variant": "", + "input": 0.275, + "output": 2.2, + "cached_input": 0.028 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.4", + "variant": "", + "input": 2.75, + "output": 16.5, + "cached_input": 0.28 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.4", + "variant": "priority", + "input": 5.5, + "output": 33, + "cached_input": 0.55 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.4-2026-03-05", + "variant": "", + "input": 2.75, + "output": 16.5, + "cached_input": 0.28 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.4-2026-03-05", + "variant": "priority", + "input": 5.5, + "output": 33, + "cached_input": 0.55 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.5", + "variant": "", + "input": 5.5, + "output": 33, + "cached_input": 0.55 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.5", + "variant": "above_272k_tokens", + "input": 11, + "output": 49.5, + "cached_input": 1.1 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.5", + "variant": "priority", + "input": 13.75, + "output": 82.5, + "cached_input": 1.38 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.5-2026-04-23", + "variant": "", + "input": 5.5, + "output": 33, + "cached_input": 0.55 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.5-2026-04-23", + "variant": "above_272k_tokens", + "input": 11, + "output": 49.5, + "cached_input": 1.1 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.5-2026-04-23", + "variant": "priority", + "input": 13.75, + "output": 82.5, + "cached_input": 1.38 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.6", + "variant": "", + "input": 5.5, + "output": 33, + "cached_input": 0.55 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.6", + "variant": "above_272k_tokens", + "input": 11, + "output": 49.5, + "cached_input": 1.1 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.6", + "variant": "priority", + "input": 13.75, + "output": 82.5, + "cached_input": 1.375 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.6-luna", + "variant": "", + "input": 1.1, + "output": 6.6, + "cached_input": 0.11 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.6-luna", + "variant": "above_272k_tokens", + "input": 2.2, + "output": 9.9, + "cached_input": 0.22 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.6-luna", + "variant": "priority", + "input": 2.75, + "output": 16.5, + "cached_input": 0.275 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.6-sol", + "variant": "", + "input": 5.5, + "output": 33, + "cached_input": 0.55 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.6-sol", + "variant": "above_272k_tokens", + "input": 11, + "output": 49.5, + "cached_input": 1.1 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.6-sol", + "variant": "priority", + "input": 13.75, + "output": 82.5, + "cached_input": 1.375 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.6-terra", + "variant": "", + "input": 2.75, + "output": 16.5, + "cached_input": 0.275 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.6-terra", + "variant": "above_272k_tokens", + "input": 5.5, + "output": 24.75, + "cached_input": 0.55 + }, + { + "provider": "Azure/OpenAI", + "model": "us/gpt-5.6-terra", + "variant": "priority", + "input": 6.875, + "output": 41.25, + "cached_input": 0.6875 + }, + { + "provider": "Azure/OpenAI", + "model": "us/o1-2024-12-17", + "variant": "", + "input": 16.5, + "output": 66, + "cached_input": 8.25 + }, + { + "provider": "Azure/OpenAI", + "model": "us/o1-mini-2024-09-12", + "variant": "", + "input": 1.21, + "output": 4.84, + "cached_input": 0.605 + }, + { + "provider": "Azure/OpenAI", + "model": "us/o1-mini-2024-09-12", + "variant": "batches", + "input": 0.605, + "output": 2.42 + }, + { + "provider": "Azure/OpenAI", + "model": "us/o1-preview-2024-09-12", + "variant": "", + "input": 16.5, + "output": 66, + "cached_input": 8.25 + }, + { + "provider": "Azure/OpenAI", + "model": "us/o3-2025-04-16", + "variant": "", + "input": 2.2, + "output": 8.8, + "cached_input": 0.55 + }, + { + "provider": "Azure/OpenAI", + "model": "us/o3-mini-2025-01-31", + "variant": "", + "input": 1.21, + "output": 4.84, + "cached_input": 0.605 + }, + { + "provider": "Azure/OpenAI", + "model": "us/o3-mini-2025-01-31", + "variant": "batches", + "input": 0.605, + "output": 2.42 + }, + { + "provider": "Azure/OpenAI", + "model": "us/o4-mini-2025-04-16", + "variant": "", + "input": 1.21, + "output": 4.84, + "cached_input": 0.31 + }, + { + "provider": "Google/Gemini", + "model": "deep-research-pro-preview-12-2025", + "variant": "", + "input": 2, + "output": 12 + }, + { + "provider": "Google/Gemini", + "model": "deep-research-pro-preview-12-2025", + "variant": "batches", + "input": 1, + "output": 6 + }, + { + "provider": "Google/Gemini", + "model": "gemini-1.5-flash", + "variant": "", + "input": 0.075, + "output": 0 + }, + { + "provider": "Google/Gemini", + "model": "gemini-1.5-flash", + "variant": "above_128k_tokens", + "input": 0.15 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.0-flash", + "variant": "", + "input": 0.1, + "output": 0.4, + "cached_input": 0.025 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.0-flash-001", + "variant": "", + "input": 0.1, + "output": 0.4, + "cached_input": 0.025 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.0-flash-lite", + "variant": "", + "input": 0.075, + "output": 0.3, + "cached_input": 0.01875 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.0-flash-lite-001", + "variant": "", + "input": 0.075, + "output": 0.3, + "cached_input": 0.01875 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.5-computer-use-preview-10-2025", + "variant": "", + "input": 1.25, + "output": 10 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.5-computer-use-preview-10-2025", + "variant": "above_200k_tokens", + "input": 2.5, + "output": 15 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.5-flash", + "variant": "", + "input": 0.3, + "output": 2.5, + "cached_input": 0.03 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.5-flash-image", + "variant": "", + "input": 0.3, + "output": 2.5, + "cached_input": 0.03 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.5-flash-lite", + "variant": "", + "input": 0.1, + "output": 0.4, + "cached_input": 0.01 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.5-flash-lite-preview-06-17", + "variant": "", + "input": 0.1, + "output": 0.4, + "cached_input": 0.025 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.5-flash-lite-preview-09-2025", + "variant": "", + "input": 0.1, + "output": 0.4, + "cached_input": 0.01 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.5-flash-native-audio-latest", + "variant": "", + "input": 0.3, + "output": 2.5 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.5-flash-native-audio-preview-09-2025", + "variant": "", + "input": 0.3, + "output": 2.5 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.5-flash-native-audio-preview-12-2025", + "variant": "", + "input": 0.3, + "output": 2.5 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.5-flash-preview-09-2025", + "variant": "", + "input": 0.3, + "output": 2.5, + "cached_input": 0.075 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.5-flash-preview-tts", + "variant": "", + "input": 0.3, + "output": 2.5 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.5-pro", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.5-pro", + "variant": "above_200k_tokens", + "input": 2.5, + "output": 15, + "cached_input": 0.25 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.5-pro", + "variant": "above_200k_tokens_priority", + "input": 2.5, + "output": 15 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.5-pro", + "variant": "priority", + "input": 1.25, + "output": 10 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.5-pro-preview-tts", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "Google/Gemini", + "model": "gemini-2.5-pro-preview-tts", + "variant": "above_200k_tokens", + "input": 2.5, + "output": 15, + "cached_input": 0.25 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3-flash-preview", + "variant": "", + "input": 0.5, + "output": 3, + "cached_input": 0.05 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3-flash-preview", + "variant": "priority", + "input": 0.9, + "output": 5.4, + "cached_input": 0.09 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3-pro-image", + "variant": "", + "input": 2, + "output": 12 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3-pro-image", + "variant": "batches", + "input": 1, + "output": 6 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3-pro-image-preview", + "variant": "", + "input": 2, + "output": 12 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3-pro-image-preview", + "variant": "batches", + "input": 1, + "output": 6 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3-pro-preview", + "variant": "", + "input": 2, + "output": 12, + "cached_input": 0.2 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3-pro-preview", + "variant": "above_200k_tokens", + "input": 4, + "output": 18, + "cached_input": 0.4 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3-pro-preview", + "variant": "above_200k_tokens_priority", + "input": 7.2, + "output": 32.4, + "cached_input": 0.72 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3-pro-preview", + "variant": "batches", + "input": 1, + "output": 6 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3-pro-preview", + "variant": "priority", + "input": 3.6, + "output": 21.6, + "cached_input": 0.36 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.1-flash-image", + "variant": "", + "input": 0.25, + "output": 1.5 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.1-flash-image", + "variant": "batches", + "input": 0.125, + "output": 0.75 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.1-flash-image-preview", + "variant": "", + "input": 0.25, + "output": 1.5 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.1-flash-image-preview", + "variant": "batches", + "input": 0.125, + "output": 0.75 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.1-flash-lite", + "variant": "", + "input": 0.25, + "output": 1.5, + "cached_input": 0.025 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.1-flash-lite", + "variant": "batches", + "input": 0.125, + "output": 0.75 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.1-flash-lite", + "variant": "flex", + "input": 0.125, + "output": 0.75, + "cached_input": 0.0125 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.1-flash-lite", + "variant": "priority", + "input": 0.45, + "output": 2.7, + "cached_input": 0.045 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.1-flash-lite-preview", + "variant": "", + "input": 0.25, + "output": 1.5, + "cached_input": 0.025 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.1-flash-live-preview", + "variant": "", + "input": 0.75, + "output": 4.5 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.1-pro-preview", + "variant": "", + "input": 2, + "output": 12, + "cached_input": 0.2 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.1-pro-preview", + "variant": "above_200k_tokens", + "input": 4, + "output": 18, + "cached_input": 0.4 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.1-pro-preview", + "variant": "above_200k_tokens_priority", + "input": 7.2, + "output": 32.4, + "cached_input": 0.72 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.1-pro-preview", + "variant": "batches", + "input": 1, + "output": 6 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.1-pro-preview", + "variant": "priority", + "input": 3.6, + "output": 21.6, + "cached_input": 0.36 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.1-pro-preview-customtools", + "variant": "", + "input": 2, + "output": 12, + "cached_input": 0.2 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.1-pro-preview-customtools", + "variant": "above_200k_tokens", + "input": 4, + "output": 18, + "cached_input": 0.4 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.1-pro-preview-customtools", + "variant": "above_200k_tokens_priority", + "input": 7.2, + "output": 32.4, + "cached_input": 0.72 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.1-pro-preview-customtools", + "variant": "batches", + "input": 1, + "output": 6 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.1-pro-preview-customtools", + "variant": "priority", + "input": 3.6, + "output": 21.6, + "cached_input": 0.36 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.5-flash", + "variant": "", + "input": 1.5, + "output": 9, + "cached_input": 0.15 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.5-flash", + "variant": "priority", + "input": 2.7, + "output": 16.2, + "cached_input": 0.27 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.5-flash-lite", + "variant": "", + "input": 0.3, + "output": 2.5, + "cached_input": 0.03 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.5-flash-lite", + "variant": "batches", + "input": 0.15, + "output": 1.25 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.5-flash-lite", + "variant": "flex", + "input": 0.15, + "output": 1.25, + "cached_input": 0.02 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.5-flash-lite", + "variant": "priority", + "input": 0.54, + "output": 4.5, + "cached_input": 0.05 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.6-flash", + "variant": "", + "input": 1.5, + "output": 7.5, + "cached_input": 0.15 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.6-flash", + "variant": "batches", + "input": 0.75, + "output": 3.75 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.6-flash", + "variant": "flex", + "input": 0.75, + "output": 3.75, + "cached_input": 0.075 + }, + { + "provider": "Google/Gemini", + "model": "gemini-3.6-flash", + "variant": "priority", + "input": 2.7, + "output": 13.5, + "cached_input": 0.27 + }, + { + "provider": "Google/Gemini", + "model": "gemini-embedding-001", + "variant": "", + "input": 0.15, + "output": 0 + }, + { + "provider": "Google/Gemini", + "model": "gemini-embedding-2", + "variant": "", + "input": 0.2, + "output": 0 + }, + { + "provider": "Google/Gemini", + "model": "gemini-embedding-2-preview", + "variant": "", + "input": 0.2, + "output": 0 + }, + { + "provider": "Google/Gemini", + "model": "gemini-exp-1206", + "variant": "", + "input": 0.3, + "output": 2.5, + "cached_input": 0.03 + }, + { + "provider": "Google/Gemini", + "model": "gemini-flash-latest", + "variant": "", + "input": 0.3, + "output": 2.5, + "cached_input": 0.03 + }, + { + "provider": "Google/Gemini", + "model": "gemini-flash-lite-latest", + "variant": "", + "input": 0.1, + "output": 0.4, + "cached_input": 0.01 + }, + { + "provider": "Google/Gemini", + "model": "gemini-gemma-2-27b-it", + "variant": "", + "input": 0.35, + "output": 1.05 + }, + { + "provider": "Google/Gemini", + "model": "gemini-gemma-2-9b-it", + "variant": "", + "input": 0.35, + "output": 1.05 + }, + { + "provider": "Google/Gemini", + "model": "gemini-live-2.5-flash-preview-native-audio-09-2025", + "variant": "", + "input": 0.3, + "output": 2, + "cached_input": 0.075 + }, + { + "provider": "Google/Gemini", + "model": "gemini-omni-flash-preview", + "variant": "", + "input": 1.5, + "output": 9 + }, + { + "provider": "Google/Gemini", + "model": "gemini-pro-latest", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "Google/Gemini", + "model": "gemini-pro-latest", + "variant": "above_200k_tokens", + "input": 2.5, + "output": 15, + "cached_input": 0.25 + }, + { + "provider": "Google/Gemini", + "model": "gemini-robotics-er-1.5-preview", + "variant": "", + "input": 0.3, + "output": 2.5, + "cached_input": 0 + }, + { + "provider": "Google/Vertex", + "model": "deep-research-pro-preview-12-2025", + "variant": "", + "input": 2, + "output": 12 + }, + { + "provider": "Google/Vertex", + "model": "deep-research-pro-preview-12-2025", + "variant": "batches", + "input": 1, + "output": 6 + }, + { + "provider": "Google/Vertex", + "model": "gemini-2.0-flash", + "variant": "", + "input": 0.1, + "output": 0.4, + "cached_input": 0.025 + }, + { + "provider": "Google/Vertex", + "model": "gemini-2.0-flash-001", + "variant": "", + "input": 0.15, + "output": 0.6, + "cached_input": 0.0375 + }, + { + "provider": "Google/Vertex", + "model": "gemini-2.0-flash-lite", + "variant": "", + "input": 0.075, + "output": 0.3, + "cached_input": 0.01875 + }, + { + "provider": "Google/Vertex", + "model": "gemini-2.0-flash-lite-001", + "variant": "", + "input": 0.075, + "output": 0.3, + "cached_input": 0.01875 + }, + { + "provider": "Google/Vertex", + "model": "gemini-2.5-computer-use-preview-10-2025", + "variant": "", + "input": 1.25, + "output": 10 + }, + { + "provider": "Google/Vertex", + "model": "gemini-2.5-computer-use-preview-10-2025", + "variant": "above_200k_tokens", + "input": 2.5, + "output": 15 + }, + { + "provider": "Google/Vertex", + "model": "gemini-2.5-flash", + "variant": "", + "input": 0.3, + "output": 2.5, + "cached_input": 0.03 + }, + { + "provider": "Google/Vertex", + "model": "gemini-2.5-flash-image", + "variant": "", + "input": 0.3, + "output": 2.5, + "cached_input": 0.03 + }, + { + "provider": "Google/Vertex", + "model": "gemini-2.5-flash-lite", + "variant": "", + "input": 0.1, + "output": 0.4, + "cached_input": 0.01 + }, + { + "provider": "Google/Vertex", + "model": "gemini-2.5-flash-lite-preview-06-17", + "variant": "", + "input": 0.1, + "output": 0.4, + "cached_input": 0.025 + }, + { + "provider": "Google/Vertex", + "model": "gemini-2.5-flash-lite-preview-09-2025", + "variant": "", + "input": 0.1, + "output": 0.4, + "cached_input": 0.01 + }, + { + "provider": "Google/Vertex", + "model": "gemini-2.5-flash-preview-09-2025", + "variant": "", + "input": 0.3, + "output": 2.5, + "cached_input": 0.075 + }, + { + "provider": "Google/Vertex", + "model": "gemini-2.5-pro", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "Google/Vertex", + "model": "gemini-2.5-pro", + "variant": "above_200k_tokens", + "input": 2.5, + "output": 15, + "cached_input": 0.25 + }, + { + "provider": "Google/Vertex", + "model": "gemini-2.5-pro-preview-tts", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "Google/Vertex", + "model": "gemini-2.5-pro-preview-tts", + "variant": "above_200k_tokens", + "input": 2.5, + "output": 15, + "cached_input": 0.25 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3-flash-preview", + "variant": "", + "input": 0.5, + "output": 3, + "cached_input": 0.05 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3-flash-preview", + "variant": "priority", + "input": 0.9, + "output": 5.4, + "cached_input": 0.09 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3-pro-image", + "variant": "", + "input": 2, + "output": 12 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3-pro-image", + "variant": "batches", + "input": 1, + "output": 6 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3-pro-image-preview", + "variant": "", + "input": 2, + "output": 12 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3-pro-image-preview", + "variant": "batches", + "input": 1, + "output": 6 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3-pro-preview", + "variant": "", + "input": 2, + "output": 12, + "cached_input": 0.2 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3-pro-preview", + "variant": "above_200k_tokens", + "input": 4, + "output": 18, + "cached_input": 0.4 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3-pro-preview", + "variant": "above_200k_tokens_priority", + "input": 7.2, + "output": 32.4, + "cached_input": 0.72 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3-pro-preview", + "variant": "batches", + "input": 1, + "output": 6 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3-pro-preview", + "variant": "priority", + "input": 3.6, + "output": 21.6, + "cached_input": 0.36 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.1-flash-image", + "variant": "", + "input": 0.5, + "output": 3 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.1-flash-image-preview", + "variant": "", + "input": 0.5, + "output": 3 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.1-flash-lite", + "variant": "", + "input": 0.25, + "output": 1.5, + "cached_input": 0.025 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.1-flash-lite", + "variant": "batches", + "input": 0.125, + "output": 0.75 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.1-flash-lite", + "variant": "flex", + "input": 0.125, + "output": 0.75, + "cached_input": 0.0125 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.1-flash-lite", + "variant": "priority", + "input": 0.45, + "output": 2.7, + "cached_input": 0.045 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.1-flash-lite-preview", + "variant": "", + "input": 0.25, + "output": 1.5, + "cached_input": 0.025 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.1-pro-preview", + "variant": "", + "input": 2, + "output": 12, + "cached_input": 0.2 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.1-pro-preview", + "variant": "above_200k_tokens", + "input": 4, + "output": 18, + "cached_input": 0.4 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.1-pro-preview", + "variant": "above_200k_tokens_priority", + "input": 7.2, + "output": 32.4, + "cached_input": 0.72 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.1-pro-preview", + "variant": "batches", + "input": 1, + "output": 6 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.1-pro-preview", + "variant": "priority", + "input": 3.6, + "output": 21.6, + "cached_input": 0.36 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.1-pro-preview-customtools", + "variant": "", + "input": 2, + "output": 12, + "cached_input": 0.2 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.1-pro-preview-customtools", + "variant": "above_200k_tokens", + "input": 4, + "output": 18, + "cached_input": 0.4 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.1-pro-preview-customtools", + "variant": "batches", + "input": 1, + "output": 6 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.5-flash", + "variant": "", + "input": 1.5, + "output": 9, + "cached_input": 0.15 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.5-flash", + "variant": "priority", + "input": 2.7, + "output": 16.2, + "cached_input": 0.27 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.5-flash-lite", + "variant": "", + "input": 0.3, + "output": 2.5, + "cached_input": 0.03 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.5-flash-lite", + "variant": "batches", + "input": 0.15, + "output": 1.25 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.5-flash-lite", + "variant": "flex", + "input": 0.15, + "output": 1.25, + "cached_input": 0.02 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.5-flash-lite", + "variant": "priority", + "input": 0.54, + "output": 4.5, + "cached_input": 0.05 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.6-flash", + "variant": "", + "input": 1.5, + "output": 7.5, + "cached_input": 0.15 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.6-flash", + "variant": "batches", + "input": 0.75, + "output": 3.75 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.6-flash", + "variant": "flex", + "input": 0.75, + "output": 3.75, + "cached_input": 0.075 + }, + { + "provider": "Google/Vertex", + "model": "gemini-3.6-flash", + "variant": "priority", + "input": 2.7, + "output": 13.5, + "cached_input": 0.27 + }, + { + "provider": "Google/Vertex", + "model": "gemini-live-2.5-flash-preview-native-audio-09-2025", + "variant": "", + "input": 0.3, + "output": 2, + "cached_input": 0.075 + }, + { + "provider": "Google/Vertex", + "model": "gemini-omni-flash-preview", + "variant": "", + "input": 1.5, + "output": 9 + }, + { + "provider": "Google/Vertex", + "model": "gemini-robotics-er-1.5-preview", + "variant": "", + "input": 0.3, + "output": 2.5, + "cached_input": 0 + }, + { + "provider": "Google/Vertex", + "model": "vertex_ai/deep-research-pro-preview-12-2025", + "variant": "", + "input": 2, + "output": 12 + }, + { + "provider": "Google/Vertex", + "model": "vertex_ai/deep-research-pro-preview-12-2025", + "variant": "batches", + "input": 1, + "output": 6 + }, + { + "provider": "Google/Vertex", + "model": "vertex_ai/gemini-2.5-flash-image", + "variant": "", + "input": 0.3, + "output": 2.5, + "cached_input": 0.03 + }, + { + "provider": "Google/Vertex", + "model": "vertex_ai/gemini-3-pro-image", + "variant": "", + "input": 2, + "output": 12 + }, + { + "provider": "Google/Vertex", + "model": "vertex_ai/gemini-3-pro-image", + "variant": "batches", + "input": 1, + "output": 6 + }, + { + "provider": "Google/Vertex", + "model": "vertex_ai/gemini-3-pro-image-preview", + "variant": "", + "input": 2, + "output": 12 + }, + { + "provider": "Google/Vertex", + "model": "vertex_ai/gemini-3-pro-image-preview", + "variant": "batches", + "input": 1, + "output": 6 + }, + { + "provider": "Google/Vertex", + "model": "vertex_ai/gemini-3.1-flash-image", + "variant": "", + "input": 0.5, + "output": 3 + }, + { + "provider": "Google/Vertex", + "model": "vertex_ai/gemini-3.1-flash-image-preview", + "variant": "", + "input": 0.5, + "output": 3 + }, + { + "provider": "Google/Vertex", + "model": "vertex_ai/gemini-3.1-flash-lite", + "variant": "", + "input": 0.25, + "output": 1.5, + "cached_input": 0.025 + }, + { + "provider": "Google/Vertex", + "model": "vertex_ai/gemini-3.1-flash-lite", + "variant": "batches", + "input": 0.125, + "output": 0.75 + }, + { + "provider": "Google/Vertex", + "model": "vertex_ai/gemini-3.1-flash-lite", + "variant": "flex", + "input": 0.125, + "output": 0.75, + "cached_input": 0.0125 + }, + { + "provider": "Google/Vertex", + "model": "vertex_ai/gemini-3.1-flash-lite", + "variant": "priority", + "input": 0.45, + "output": 2.7, + "cached_input": 0.045 + }, + { + "provider": "Google/Vertex", + "model": "vertex_ai/gemini-3.1-flash-lite-preview", + "variant": "", + "input": 0.25, + "output": 1.5, + "cached_input": 0.025 + }, + { + "provider": "Google/Vertex", + "model": "vertex_ai/gemini-3.5-flash-lite", + "variant": "", + "input": 0.3, + "output": 2.5, + "cached_input": 0.03 + }, + { + "provider": "Google/Vertex", + "model": "vertex_ai/gemini-3.5-flash-lite", + "variant": "batches", + "input": 0.15, + "output": 1.25 + }, + { + "provider": "Google/Vertex", + "model": "vertex_ai/gemini-3.5-flash-lite", + "variant": "flex", + "input": 0.15, + "output": 1.25, + "cached_input": 0.02 + }, + { + "provider": "Google/Vertex", + "model": "vertex_ai/gemini-3.5-flash-lite", + "variant": "priority", + "input": 0.54, + "output": 4.5, + "cached_input": 0.05 + }, + { + "provider": "Groq", + "model": "gemma-7b-it", + "variant": "", + "input": 0.05, + "output": 0.08 + }, + { + "provider": "Groq", + "model": "llama-3.1-8b-instant", + "variant": "", + "input": 0.05, + "output": 0.08 + }, + { + "provider": "Groq", + "model": "llama-3.3-70b-versatile", + "variant": "", + "input": 0.59, + "output": 0.79 + }, + { + "provider": "Groq", + "model": "meta-llama/llama-4-maverick-17b-128e-instruct", + "variant": "", + "input": 0.2, + "output": 0.6 + }, + { + "provider": "Groq", + "model": "meta-llama/llama-4-scout-17b-16e-instruct", + "variant": "", + "input": 0.11, + "output": 0.34 + }, + { + "provider": "Groq", + "model": "meta-llama/llama-guard-4-12b", + "variant": "", + "input": 0.2, + "output": 0.2 + }, + { + "provider": "Groq", + "model": "moonshotai/kimi-k2-instruct-0905", + "variant": "", + "input": 1, + "output": 3, + "cached_input": 0.5 + }, + { + "provider": "Groq", + "model": "openai/gpt-oss-120b", + "variant": "", + "input": 0.15, + "output": 0.6, + "cached_input": 0.075 + }, + { + "provider": "Groq", + "model": "openai/gpt-oss-20b", + "variant": "", + "input": 0.075, + "output": 0.3, + "cached_input": 0.0375 + }, + { + "provider": "Groq", + "model": "openai/gpt-oss-safeguard-20b", + "variant": "", + "input": 0.075, + "output": 0.3, + "cached_input": 0.037 + }, + { + "provider": "Groq", + "model": "qwen/qwen3-32b", + "variant": "", + "input": 0.29, + "output": 0.59 + }, + { + "provider": "Mistral", + "model": "codestral-2405", + "variant": "", + "input": 1, + "output": 3 + }, + { + "provider": "Mistral", + "model": "codestral-2508", + "variant": "", + "input": 0.3, + "output": 0.9 + }, + { + "provider": "Mistral", + "model": "codestral-embed", + "variant": "", + "input": 0.15 + }, + { + "provider": "Mistral", + "model": "codestral-embed-2505", + "variant": "", + "input": 0.15 + }, + { + "provider": "Mistral", + "model": "codestral-latest", + "variant": "", + "input": 1, + "output": 3 + }, + { + "provider": "Mistral", + "model": "codestral-mamba-latest", + "variant": "", + "input": 0.25, + "output": 0.25 + }, + { + "provider": "Mistral", + "model": "devstral-2512", + "variant": "", + "input": 0.4, + "output": 2 + }, + { + "provider": "Mistral", + "model": "devstral-latest", + "variant": "", + "input": 0.4, + "output": 2 + }, + { + "provider": "Mistral", + "model": "devstral-medium-2507", + "variant": "", + "input": 0.4, + "output": 2 + }, + { + "provider": "Mistral", + "model": "devstral-medium-latest", + "variant": "", + "input": 0.4, + "output": 2 + }, + { + "provider": "Mistral", + "model": "devstral-small-2505", + "variant": "", + "input": 0.1, + "output": 0.3 + }, + { + "provider": "Mistral", + "model": "devstral-small-2507", + "variant": "", + "input": 0.1, + "output": 0.3 + }, + { + "provider": "Mistral", + "model": "devstral-small-latest", + "variant": "", + "input": 0.1, + "output": 0.3 + }, + { + "provider": "Mistral", + "model": "labs-devstral-small-2512", + "variant": "", + "input": 0.1, + "output": 0.3 + }, + { + "provider": "Mistral", + "model": "magistral-medium-1-2-2509", + "variant": "", + "input": 2, + "output": 5 + }, + { + "provider": "Mistral", + "model": "magistral-medium-2506", + "variant": "", + "input": 2, + "output": 5 + }, + { + "provider": "Mistral", + "model": "magistral-medium-2509", + "variant": "", + "input": 2, + "output": 5 + }, + { + "provider": "Mistral", + "model": "magistral-medium-latest", + "variant": "", + "input": 2, + "output": 5 + }, + { + "provider": "Mistral", + "model": "magistral-small-1-2-2509", + "variant": "", + "input": 0.5, + "output": 1.5 + }, + { + "provider": "Mistral", + "model": "magistral-small-2506", + "variant": "", + "input": 0.5, + "output": 1.5 + }, + { + "provider": "Mistral", + "model": "magistral-small-latest", + "variant": "", + "input": 0.5, + "output": 1.5 + }, + { + "provider": "Mistral", + "model": "ministral-3-14b-2512", + "variant": "", + "input": 0.2, + "output": 0.2 + }, + { + "provider": "Mistral", + "model": "ministral-3-3b-2512", + "variant": "", + "input": 0.1, + "output": 0.1 + }, + { + "provider": "Mistral", + "model": "ministral-3-8b-2512", + "variant": "", + "input": 0.15, + "output": 0.15 + }, + { + "provider": "Mistral", + "model": "ministral-8b-2512", + "variant": "", + "input": 0.15, + "output": 0.15 + }, + { + "provider": "Mistral", + "model": "ministral-8b-latest", + "variant": "", + "input": 0.15, + "output": 0.15 + }, + { + "provider": "Mistral", + "model": "mistral-embed", + "variant": "", + "input": 0.1 + }, + { + "provider": "Mistral", + "model": "mistral-large-2402", + "variant": "", + "input": 4, + "output": 12 + }, + { + "provider": "Mistral", + "model": "mistral-large-2407", + "variant": "", + "input": 3, + "output": 9 + }, + { + "provider": "Mistral", + "model": "mistral-large-2411", + "variant": "", + "input": 2, + "output": 6 + }, + { + "provider": "Mistral", + "model": "mistral-large-2512", + "variant": "", + "input": 0.5, + "output": 1.5 + }, + { + "provider": "Mistral", + "model": "mistral-large-3", + "variant": "", + "input": 0.5, + "output": 1.5 + }, + { + "provider": "Mistral", + "model": "mistral-large-latest", + "variant": "", + "input": 0.5, + "output": 1.5 + }, + { + "provider": "Mistral", + "model": "mistral-medium", + "variant": "", + "input": 2.7, + "output": 8.1 + }, + { + "provider": "Mistral", + "model": "mistral-medium-2312", + "variant": "", + "input": 2.7, + "output": 8.1 + }, + { + "provider": "Mistral", + "model": "mistral-medium-2505", + "variant": "", + "input": 0.4, + "output": 2 + }, + { + "provider": "Mistral", + "model": "mistral-medium-2508", + "variant": "", + "input": 0.4, + "output": 2 + }, + { + "provider": "Mistral", + "model": "mistral-medium-2604", + "variant": "", + "input": 1.5, + "output": 7.5 + }, + { + "provider": "Mistral", + "model": "mistral-medium-3-1-2508", + "variant": "", + "input": 0.4, + "output": 2 + }, + { + "provider": "Mistral", + "model": "mistral-medium-3-5", + "variant": "", + "input": 1.5, + "output": 7.5 + }, + { + "provider": "Mistral", + "model": "mistral-medium-latest", + "variant": "", + "input": 1.5, + "output": 7.5 + }, + { + "provider": "Mistral", + "model": "mistral-small", + "variant": "", + "input": 0.1, + "output": 0.3 + }, + { + "provider": "Mistral", + "model": "mistral-small-3-2-2506", + "variant": "", + "input": 0.06, + "output": 0.18 + }, + { + "provider": "Mistral", + "model": "mistral-small-latest", + "variant": "", + "input": 0.06, + "output": 0.18 + }, + { + "provider": "Mistral", + "model": "mistral-tiny", + "variant": "", + "input": 0.25, + "output": 0.25 + }, + { + "provider": "Mistral", + "model": "open-codestral-mamba", + "variant": "", + "input": 0.25, + "output": 0.25 + }, + { + "provider": "Mistral", + "model": "open-mistral-7b", + "variant": "", + "input": 0.25, + "output": 0.25 + }, + { + "provider": "Mistral", + "model": "open-mistral-nemo", + "variant": "", + "input": 0.3, + "output": 0.3 + }, + { + "provider": "Mistral", + "model": "open-mistral-nemo-2407", + "variant": "", + "input": 0.3, + "output": 0.3 + }, + { + "provider": "Mistral", + "model": "open-mixtral-8x22b", + "variant": "", + "input": 2, + "output": 6 + }, + { + "provider": "Mistral", + "model": "open-mixtral-8x7b", + "variant": "", + "input": 0.7, + "output": 0.7 + }, + { + "provider": "Mistral", + "model": "pixtral-12b-2409", + "variant": "", + "input": 0.15, + "output": 0.15 + }, + { + "provider": "Mistral", + "model": "pixtral-large-2411", + "variant": "", + "input": 2, + "output": 6 + }, + { + "provider": "Mistral", + "model": "pixtral-large-latest", + "variant": "", + "input": 2, + "output": 6 + }, + { + "provider": "OpenAI", + "model": "chatgpt-4o-latest", + "variant": "", + "input": 5, + "output": 15 + }, + { + "provider": "OpenAI", + "model": "chatgpt-image-latest", + "variant": "", + "input": 5, + "cached_input": 1.25 + }, + { + "provider": "OpenAI", + "model": "codex-mini-latest", + "variant": "", + "input": 1.5, + "output": 6, + "cached_input": 0.375 + }, + { + "provider": "OpenAI", + "model": "ft:gpt-3.5-turbo", + "variant": "", + "input": 3, + "output": 6 + }, + { + "provider": "OpenAI", + "model": "ft:gpt-3.5-turbo", + "variant": "batches", + "input": 1.5, + "output": 3 + }, + { + "provider": "OpenAI", + "model": "ft:gpt-3.5-turbo-0125", + "variant": "", + "input": 3, + "output": 6 + }, + { + "provider": "OpenAI", + "model": "ft:gpt-3.5-turbo-0613", + "variant": "", + "input": 3, + "output": 6 + }, + { + "provider": "OpenAI", + "model": "ft:gpt-3.5-turbo-1106", + "variant": "", + "input": 3, + "output": 6 + }, + { + "provider": "OpenAI", + "model": "ft:gpt-4-0613", + "variant": "", + "input": 30, + "output": 60 + }, + { + "provider": "OpenAI", + "model": "ft:gpt-4.1-2025-04-14", + "variant": "", + "input": 3, + "output": 12, + "cached_input": 0.75 + }, + { + "provider": "OpenAI", + "model": "ft:gpt-4.1-2025-04-14", + "variant": "batches", + "input": 1.5, + "output": 6 + }, + { + "provider": "OpenAI", + "model": "ft:gpt-4.1-mini-2025-04-14", + "variant": "", + "input": 0.8, + "output": 3.2, + "cached_input": 0.2 + }, + { + "provider": "OpenAI", + "model": "ft:gpt-4.1-mini-2025-04-14", + "variant": "batches", + "input": 0.4, + "output": 1.6 + }, + { + "provider": "OpenAI", + "model": "ft:gpt-4.1-nano-2025-04-14", + "variant": "", + "input": 0.2, + "output": 0.8, + "cached_input": 0.05 + }, + { + "provider": "OpenAI", + "model": "ft:gpt-4.1-nano-2025-04-14", + "variant": "batches", + "input": 0.1, + "output": 0.4 + }, + { + "provider": "OpenAI", + "model": "ft:gpt-4o-2024-08-06", + "variant": "", + "input": 3.75, + "output": 15, + "cached_input": 1.875 + }, + { + "provider": "OpenAI", + "model": "ft:gpt-4o-2024-08-06", + "variant": "batches", + "input": 1.875, + "output": 7.5 + }, + { + "provider": "OpenAI", + "model": "ft:gpt-4o-2024-11-20", + "variant": "", + "input": 3.75, + "output": 15 + }, + { + "provider": "OpenAI", + "model": "ft:gpt-4o-mini-2024-07-18", + "variant": "", + "input": 0.3, + "output": 1.2, + "cached_input": 0.15 + }, + { + "provider": "OpenAI", + "model": "ft:gpt-4o-mini-2024-07-18", + "variant": "batches", + "input": 0.15, + "output": 0.6 + }, + { + "provider": "OpenAI", + "model": "ft:o4-mini-2025-04-16", + "variant": "", + "input": 4, + "output": 16, + "cached_input": 1 + }, + { + "provider": "OpenAI", + "model": "ft:o4-mini-2025-04-16", + "variant": "batches", + "input": 2, + "output": 8 + }, + { + "provider": "OpenAI", + "model": "gpt-3.5-turbo", + "variant": "", + "input": 0.5, + "output": 1.5 + }, + { + "provider": "OpenAI", + "model": "gpt-3.5-turbo-0125", + "variant": "", + "input": 0.5, + "output": 1.5 + }, + { + "provider": "OpenAI", + "model": "gpt-3.5-turbo-1106", + "variant": "", + "input": 1, + "output": 2 + }, + { + "provider": "OpenAI", + "model": "gpt-3.5-turbo-16k", + "variant": "", + "input": 3, + "output": 4 + }, + { + "provider": "OpenAI", + "model": "gpt-4", + "variant": "", + "input": 30, + "output": 60 + }, + { + "provider": "OpenAI", + "model": "gpt-4-0125-preview", + "variant": "", + "input": 10, + "output": 30 + }, + { + "provider": "OpenAI", + "model": "gpt-4-0314", + "variant": "", + "input": 30, + "output": 60 + }, + { + "provider": "OpenAI", + "model": "gpt-4-0613", + "variant": "", + "input": 30, + "output": 60 + }, + { + "provider": "OpenAI", + "model": "gpt-4-1106-preview", + "variant": "", + "input": 10, + "output": 30 + }, + { + "provider": "OpenAI", + "model": "gpt-4-turbo", + "variant": "", + "input": 10, + "output": 30 + }, + { + "provider": "OpenAI", + "model": "gpt-4-turbo-2024-04-09", + "variant": "", + "input": 10, + "output": 30 + }, + { + "provider": "OpenAI", + "model": "gpt-4-turbo-preview", + "variant": "", + "input": 10, + "output": 30 + }, + { + "provider": "OpenAI", + "model": "gpt-4.1", + "variant": "", + "input": 2, + "output": 8, + "cached_input": 0.5 + }, + { + "provider": "OpenAI", + "model": "gpt-4.1", + "variant": "batches", + "input": 1, + "output": 4 + }, + { + "provider": "OpenAI", + "model": "gpt-4.1", + "variant": "priority", + "input": 3.5, + "output": 14, + "cached_input": 0.875 + }, + { + "provider": "OpenAI", + "model": "gpt-4.1-2025-04-14", + "variant": "", + "input": 2, + "output": 8, + "cached_input": 0.5 + }, + { + "provider": "OpenAI", + "model": "gpt-4.1-2025-04-14", + "variant": "batches", + "input": 1, + "output": 4 + }, + { + "provider": "OpenAI", + "model": "gpt-4.1-mini", + "variant": "", + "input": 0.4, + "output": 1.6, + "cached_input": 0.1 + }, + { + "provider": "OpenAI", + "model": "gpt-4.1-mini", + "variant": "batches", + "input": 0.2, + "output": 0.8 + }, + { + "provider": "OpenAI", + "model": "gpt-4.1-mini", + "variant": "priority", + "input": 0.7, + "output": 2.8, + "cached_input": 0.175 + }, + { + "provider": "OpenAI", + "model": "gpt-4.1-mini-2025-04-14", + "variant": "", + "input": 0.4, + "output": 1.6, + "cached_input": 0.1 + }, + { + "provider": "OpenAI", + "model": "gpt-4.1-mini-2025-04-14", + "variant": "batches", + "input": 0.2, + "output": 0.8 + }, + { + "provider": "OpenAI", + "model": "gpt-4.1-nano", + "variant": "", + "input": 0.1, + "output": 0.4, + "cached_input": 0.025 + }, + { + "provider": "OpenAI", + "model": "gpt-4.1-nano", + "variant": "batches", + "input": 0.05, + "output": 0.2 + }, + { + "provider": "OpenAI", + "model": "gpt-4.1-nano", + "variant": "priority", + "input": 0.2, + "output": 0.8, + "cached_input": 0.05 + }, + { + "provider": "OpenAI", + "model": "gpt-4.1-nano-2025-04-14", + "variant": "", + "input": 0.1, + "output": 0.4, + "cached_input": 0.025 + }, + { + "provider": "OpenAI", + "model": "gpt-4.1-nano-2025-04-14", + "variant": "batches", + "input": 0.05, + "output": 0.2 + }, + { + "provider": "OpenAI", + "model": "gpt-4o", + "variant": "", + "input": 2.5, + "output": 10, + "cached_input": 1.25 + }, + { + "provider": "OpenAI", + "model": "gpt-4o", + "variant": "batches", + "input": 1.25, + "output": 5 + }, + { + "provider": "OpenAI", + "model": "gpt-4o", + "variant": "priority", + "input": 4.25, + "output": 17, + "cached_input": 2.125 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-2024-05-13", + "variant": "", + "input": 5, + "output": 15 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-2024-05-13", + "variant": "batches", + "input": 2.5, + "output": 7.5 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-2024-05-13", + "variant": "priority", + "input": 8.75, + "output": 26.25 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-2024-08-06", + "variant": "", + "input": 2.5, + "output": 10, + "cached_input": 1.25 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-2024-08-06", + "variant": "batches", + "input": 1.25, + "output": 5 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-2024-11-20", + "variant": "", + "input": 2.5, + "output": 10, + "cached_input": 1.25 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-2024-11-20", + "variant": "batches", + "input": 1.25, + "output": 5 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-audio-preview", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-audio-preview-2024-12-17", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-audio-preview-2025-06-03", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-mini", + "variant": "", + "input": 0.15, + "output": 0.6, + "cached_input": 0.075 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-mini", + "variant": "batches", + "input": 0.075, + "output": 0.3 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-mini", + "variant": "priority", + "input": 0.25, + "output": 1, + "cached_input": 0.125 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-mini-2024-07-18", + "variant": "", + "input": 0.15, + "output": 0.6, + "cached_input": 0.075 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-mini-2024-07-18", + "variant": "batches", + "input": 0.075, + "output": 0.3 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-mini-audio-preview", + "variant": "", + "input": 0.15, + "output": 0.6 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-mini-audio-preview-2024-12-17", + "variant": "", + "input": 0.15, + "output": 0.6 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-mini-realtime-preview", + "variant": "", + "input": 0.6, + "output": 2.4, + "cached_input": 0.3 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-mini-realtime-preview-2024-12-17", + "variant": "", + "input": 0.6, + "output": 2.4, + "cached_input": 0.3 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-mini-search-preview", + "variant": "", + "input": 0.15, + "output": 0.6, + "cached_input": 0.075 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-mini-search-preview", + "variant": "batches", + "input": 0.075, + "output": 0.3 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-mini-search-preview-2025-03-11", + "variant": "", + "input": 0.15, + "output": 0.6, + "cached_input": 0.075 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-mini-search-preview-2025-03-11", + "variant": "batches", + "input": 0.075, + "output": 0.3 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-mini-transcribe", + "variant": "", + "input": 1.25, + "output": 5 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-mini-transcribe-2025-03-20", + "variant": "", + "input": 1.25, + "output": 5 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-mini-transcribe-2025-12-15", + "variant": "", + "input": 1.25, + "output": 5 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-mini-tts", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-mini-tts-2025-03-20", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-mini-tts-2025-12-15", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-realtime-preview", + "variant": "", + "input": 5, + "output": 20, + "cached_input": 2.5 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-realtime-preview-2024-12-17", + "variant": "", + "input": 5, + "output": 20, + "cached_input": 2.5 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-realtime-preview-2025-06-03", + "variant": "", + "input": 5, + "output": 20, + "cached_input": 2.5 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-search-preview", + "variant": "", + "input": 2.5, + "output": 10, + "cached_input": 1.25 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-search-preview", + "variant": "batches", + "input": 1.25, + "output": 5 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-search-preview-2025-03-11", + "variant": "", + "input": 2.5, + "output": 10, + "cached_input": 1.25 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-search-preview-2025-03-11", + "variant": "batches", + "input": 1.25, + "output": 5 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-transcribe", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "OpenAI", + "model": "gpt-4o-transcribe-diarize", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "OpenAI", + "model": "gpt-5", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "OpenAI", + "model": "gpt-5", + "variant": "flex", + "input": 0.625, + "output": 5, + "cached_input": 0.0625 + }, + { + "provider": "OpenAI", + "model": "gpt-5", + "variant": "priority", + "input": 2.5, + "output": 20, + "cached_input": 0.25 + }, + { + "provider": "OpenAI", + "model": "gpt-5-2025-08-07", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "OpenAI", + "model": "gpt-5-2025-08-07", + "variant": "flex", + "input": 0.625, + "output": 5, + "cached_input": 0.0625 + }, + { + "provider": "OpenAI", + "model": "gpt-5-2025-08-07", + "variant": "priority", + "input": 2.5, + "output": 20, + "cached_input": 0.25 + }, + { + "provider": "OpenAI", + "model": "gpt-5-chat", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "OpenAI", + "model": "gpt-5-chat-latest", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "OpenAI", + "model": "gpt-5-codex", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "OpenAI", + "model": "gpt-5-mini", + "variant": "", + "input": 0.25, + "output": 2, + "cached_input": 0.025 + }, + { + "provider": "OpenAI", + "model": "gpt-5-mini", + "variant": "flex", + "input": 0.125, + "output": 1, + "cached_input": 0.0125 + }, + { + "provider": "OpenAI", + "model": "gpt-5-mini", + "variant": "priority", + "input": 0.45, + "output": 3.6, + "cached_input": 0.045 + }, + { + "provider": "OpenAI", + "model": "gpt-5-mini-2025-08-07", + "variant": "", + "input": 0.25, + "output": 2, + "cached_input": 0.025 + }, + { + "provider": "OpenAI", + "model": "gpt-5-mini-2025-08-07", + "variant": "flex", + "input": 0.125, + "output": 1, + "cached_input": 0.0125 + }, + { + "provider": "OpenAI", + "model": "gpt-5-mini-2025-08-07", + "variant": "priority", + "input": 0.45, + "output": 3.6, + "cached_input": 0.045 + }, + { + "provider": "OpenAI", + "model": "gpt-5-nano", + "variant": "", + "input": 0.05, + "output": 0.4, + "cached_input": 0.005 + }, + { + "provider": "OpenAI", + "model": "gpt-5-nano", + "variant": "flex", + "input": 0.025, + "output": 0.2, + "cached_input": 0.0025 + }, + { + "provider": "OpenAI", + "model": "gpt-5-nano", + "variant": "priority", + "input": 2.5 + }, + { + "provider": "OpenAI", + "model": "gpt-5-nano-2025-08-07", + "variant": "", + "input": 0.05, + "output": 0.4, + "cached_input": 0.005 + }, + { + "provider": "OpenAI", + "model": "gpt-5-nano-2025-08-07", + "variant": "flex", + "input": 0.025, + "output": 0.2, + "cached_input": 0.0025 + }, + { + "provider": "OpenAI", + "model": "gpt-5-pro", + "variant": "", + "input": 15, + "output": 120 + }, + { + "provider": "OpenAI", + "model": "gpt-5-pro", + "variant": "batches", + "input": 7.5, + "output": 60 + }, + { + "provider": "OpenAI", + "model": "gpt-5-pro-2025-10-06", + "variant": "", + "input": 15, + "output": 120 + }, + { + "provider": "OpenAI", + "model": "gpt-5-pro-2025-10-06", + "variant": "batches", + "input": 7.5, + "output": 60 + }, + { + "provider": "OpenAI", + "model": "gpt-5-search-api", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "OpenAI", + "model": "gpt-5-search-api-2025-10-14", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "OpenAI", + "model": "gpt-5.1", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "OpenAI", + "model": "gpt-5.1", + "variant": "priority", + "input": 2.5, + "output": 20, + "cached_input": 0.25 + }, + { + "provider": "OpenAI", + "model": "gpt-5.1-2025-11-13", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "OpenAI", + "model": "gpt-5.1-2025-11-13", + "variant": "priority", + "input": 2.5, + "output": 20, + "cached_input": 0.25 + }, + { + "provider": "OpenAI", + "model": "gpt-5.1-chat-latest", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "OpenAI", + "model": "gpt-5.1-chat-latest", + "variant": "priority", + "input": 2.5, + "output": 20, + "cached_input": 0.25 + }, + { + "provider": "OpenAI", + "model": "gpt-5.1-codex", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "OpenAI", + "model": "gpt-5.1-codex", + "variant": "priority", + "input": 2.5, + "output": 20, + "cached_input": 0.25 + }, + { + "provider": "OpenAI", + "model": "gpt-5.1-codex-max", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "OpenAI", + "model": "gpt-5.1-codex-mini", + "variant": "", + "input": 0.25, + "output": 2, + "cached_input": 0.025 + }, + { + "provider": "OpenAI", + "model": "gpt-5.1-codex-mini", + "variant": "priority", + "input": 0.45, + "output": 3.6, + "cached_input": 0.045 + }, + { + "provider": "OpenAI", + "model": "gpt-5.2", + "variant": "", + "input": 1.75, + "output": 14, + "cached_input": 0.175 + }, + { + "provider": "OpenAI", + "model": "gpt-5.2", + "variant": "priority", + "input": 3.5, + "output": 28, + "cached_input": 0.35 + }, + { + "provider": "OpenAI", + "model": "gpt-5.2-2025-12-11", + "variant": "", + "input": 1.75, + "output": 14, + "cached_input": 0.175 + }, + { + "provider": "OpenAI", + "model": "gpt-5.2-2025-12-11", + "variant": "priority", + "input": 3.5, + "output": 28, + "cached_input": 0.35 + }, + { + "provider": "OpenAI", + "model": "gpt-5.2-chat-latest", + "variant": "", + "input": 1.75, + "output": 14, + "cached_input": 0.175 + }, + { + "provider": "OpenAI", + "model": "gpt-5.2-chat-latest", + "variant": "priority", + "input": 3.5, + "output": 28, + "cached_input": 0.35 + }, + { + "provider": "OpenAI", + "model": "gpt-5.2-codex", + "variant": "", + "input": 1.75, + "output": 14, + "cached_input": 0.175 + }, + { + "provider": "OpenAI", + "model": "gpt-5.2-codex", + "variant": "priority", + "input": 3.5, + "output": 28, + "cached_input": 0.35 + }, + { + "provider": "OpenAI", + "model": "gpt-5.2-pro", + "variant": "", + "input": 21, + "output": 168 + }, + { + "provider": "OpenAI", + "model": "gpt-5.2-pro-2025-12-11", + "variant": "", + "input": 21, + "output": 168 + }, + { + "provider": "OpenAI", + "model": "gpt-5.3-chat-latest", + "variant": "", + "input": 1.75, + "output": 14, + "cached_input": 0.175 + }, + { + "provider": "OpenAI", + "model": "gpt-5.3-chat-latest", + "variant": "priority", + "input": 3.5, + "output": 28, + "cached_input": 0.35 + }, + { + "provider": "OpenAI", + "model": "gpt-5.3-codex", + "variant": "", + "input": 1.75, + "output": 14, + "cached_input": 0.175 + }, + { + "provider": "OpenAI", + "model": "gpt-5.3-codex", + "variant": "priority", + "input": 3.5, + "output": 28, + "cached_input": 0.35 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4", + "variant": "", + "input": 2.5, + "output": 15, + "cached_input": 0.25 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4", + "variant": "above_272k_tokens", + "input": 5, + "output": 22.5, + "cached_input": 0.5 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4", + "variant": "batches", + "input": 1.25, + "output": 7.5 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4", + "variant": "flex", + "input": 1.25, + "output": 7.5, + "cached_input": 0.13 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4", + "variant": "priority", + "input": 5, + "output": 30, + "cached_input": 0.5 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-2026-03-05", + "variant": "", + "input": 2.5, + "output": 15, + "cached_input": 0.25 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-2026-03-05", + "variant": "above_272k_tokens", + "input": 5, + "output": 22.5, + "cached_input": 0.5 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-2026-03-05", + "variant": "batches", + "input": 1.25, + "output": 7.5 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-2026-03-05", + "variant": "flex", + "input": 1.25, + "output": 7.5, + "cached_input": 0.13 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-2026-03-05", + "variant": "priority", + "input": 5, + "output": 30, + "cached_input": 0.5 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-mini", + "variant": "", + "input": 0.75, + "output": 4.5, + "cached_input": 0.075 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-mini", + "variant": "batches", + "input": 0.375, + "output": 2.25 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-mini", + "variant": "flex", + "input": 0.375, + "output": 2.25, + "cached_input": 0.0375 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-mini", + "variant": "priority", + "input": 1.5, + "output": 9, + "cached_input": 0.15 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-mini-2026-03-17", + "variant": "", + "input": 0.75, + "output": 4.5, + "cached_input": 0.075 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-mini-2026-03-17", + "variant": "batches", + "input": 0.375, + "output": 2.25 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-mini-2026-03-17", + "variant": "flex", + "input": 0.375, + "output": 2.25, + "cached_input": 0.0375 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-mini-2026-03-17", + "variant": "priority", + "input": 1.5, + "output": 9, + "cached_input": 0.15 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-nano", + "variant": "", + "input": 0.2, + "output": 1.25, + "cached_input": 0.02 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-nano", + "variant": "batches", + "input": 0.1, + "output": 0.625 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-nano", + "variant": "flex", + "input": 0.1, + "output": 0.625, + "cached_input": 0.01 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-nano-2026-03-17", + "variant": "", + "input": 0.2, + "output": 1.25, + "cached_input": 0.02 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-nano-2026-03-17", + "variant": "batches", + "input": 0.1, + "output": 0.625 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-nano-2026-03-17", + "variant": "flex", + "input": 0.1, + "output": 0.625, + "cached_input": 0.01 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-pro", + "variant": "", + "input": 30, + "output": 180, + "cached_input": 3 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-pro", + "variant": "above_272k_tokens", + "input": 60, + "output": 270, + "cached_input": 6 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-pro", + "variant": "batches", + "input": 15, + "output": 90 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-pro", + "variant": "flex", + "input": 15, + "output": 90 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-pro-2026-03-05", + "variant": "", + "input": 30, + "output": 180, + "cached_input": 3 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-pro-2026-03-05", + "variant": "above_272k_tokens", + "input": 60, + "output": 270, + "cached_input": 6 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-pro-2026-03-05", + "variant": "batches", + "input": 15, + "output": 90 + }, + { + "provider": "OpenAI", + "model": "gpt-5.4-pro-2026-03-05", + "variant": "flex", + "input": 15, + "output": 90 + }, + { + "provider": "OpenAI", + "model": "gpt-5.5", + "variant": "", + "input": 5, + "output": 30, + "cached_input": 0.5 + }, + { + "provider": "OpenAI", + "model": "gpt-5.5", + "variant": "above_272k_tokens", + "input": 10, + "output": 45, + "cached_input": 1 + }, + { + "provider": "OpenAI", + "model": "gpt-5.5", + "variant": "batches", + "input": 2.5, + "output": 15 + }, + { + "provider": "OpenAI", + "model": "gpt-5.5", + "variant": "flex", + "input": 2.5, + "output": 15, + "cached_input": 0.25 + }, + { + "provider": "OpenAI", + "model": "gpt-5.5", + "variant": "priority", + "input": 10, + "output": 60, + "cached_input": 1 + }, + { + "provider": "OpenAI", + "model": "gpt-5.5-2026-04-23", + "variant": "", + "input": 5, + "output": 30, + "cached_input": 0.5 + }, + { + "provider": "OpenAI", + "model": "gpt-5.5-2026-04-23", + "variant": "above_272k_tokens", + "input": 10, + "output": 45, + "cached_input": 1 + }, + { + "provider": "OpenAI", + "model": "gpt-5.5-2026-04-23", + "variant": "batches", + "input": 2.5, + "output": 15 + }, + { + "provider": "OpenAI", + "model": "gpt-5.5-2026-04-23", + "variant": "flex", + "input": 2.5, + "output": 15, + "cached_input": 0.25 + }, + { + "provider": "OpenAI", + "model": "gpt-5.5-2026-04-23", + "variant": "priority", + "input": 10, + "output": 60, + "cached_input": 1 + }, + { + "provider": "OpenAI", + "model": "gpt-5.5-pro", + "variant": "", + "input": 30, + "output": 180, + "cached_input": 3 + }, + { + "provider": "OpenAI", + "model": "gpt-5.5-pro", + "variant": "above_272k_tokens", + "input": 60, + "output": 270, + "cached_input": 6 + }, + { + "provider": "OpenAI", + "model": "gpt-5.5-pro", + "variant": "batches", + "input": 15, + "output": 90 + }, + { + "provider": "OpenAI", + "model": "gpt-5.5-pro", + "variant": "flex", + "input": 15, + "output": 90 + }, + { + "provider": "OpenAI", + "model": "gpt-5.5-pro-2026-04-23", + "variant": "", + "input": 30, + "output": 180, + "cached_input": 3 + }, + { + "provider": "OpenAI", + "model": "gpt-5.5-pro-2026-04-23", + "variant": "above_272k_tokens", + "input": 60, + "output": 270, + "cached_input": 6 + }, + { + "provider": "OpenAI", + "model": "gpt-5.5-pro-2026-04-23", + "variant": "batches", + "input": 15, + "output": 90 + }, + { + "provider": "OpenAI", + "model": "gpt-5.5-pro-2026-04-23", + "variant": "flex", + "input": 15, + "output": 90 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6", + "variant": "", + "input": 5, + "output": 30, + "cached_input": 0.5 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6", + "variant": "above_272k_tokens", + "input": 10, + "output": 45, + "cached_input": 1 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6", + "variant": "above_272k_tokens_flex", + "input": 5, + "output": 22.5, + "cached_input": 0.5 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6", + "variant": "batches", + "input": 2.5, + "output": 15 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6", + "variant": "flex", + "input": 2.5, + "output": 15, + "cached_input": 0.25 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6", + "variant": "priority", + "input": 10, + "output": 60, + "cached_input": 1 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6-luna", + "variant": "", + "input": 0.2, + "output": 1.2, + "cached_input": 0.02 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6-luna", + "variant": "above_272k_tokens", + "input": 0.4, + "output": 1.8, + "cached_input": 0.04 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6-luna", + "variant": "above_272k_tokens_flex", + "input": 0.2, + "output": 0.9, + "cached_input": 0.02 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6-luna", + "variant": "batches", + "input": 0.1, + "output": 0.6 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6-luna", + "variant": "flex", + "input": 0.1, + "output": 0.6, + "cached_input": 0.01 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6-luna", + "variant": "priority", + "input": 0.4, + "output": 2.4, + "cached_input": 0.04 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6-sol", + "variant": "", + "input": 5, + "output": 30, + "cached_input": 0.5 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6-sol", + "variant": "above_272k_tokens", + "input": 10, + "output": 45, + "cached_input": 1 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6-sol", + "variant": "above_272k_tokens_flex", + "input": 5, + "output": 22.5, + "cached_input": 0.5 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6-sol", + "variant": "batches", + "input": 2.5, + "output": 15 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6-sol", + "variant": "flex", + "input": 2.5, + "output": 15, + "cached_input": 0.25 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6-sol", + "variant": "priority", + "input": 10, + "output": 60, + "cached_input": 1 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6-terra", + "variant": "", + "input": 2, + "output": 12, + "cached_input": 0.2 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6-terra", + "variant": "above_272k_tokens", + "input": 4, + "output": 18, + "cached_input": 0.4 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6-terra", + "variant": "above_272k_tokens_flex", + "input": 2, + "output": 9, + "cached_input": 0.2 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6-terra", + "variant": "batches", + "input": 1, + "output": 6 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6-terra", + "variant": "flex", + "input": 1, + "output": 6, + "cached_input": 0.1 + }, + { + "provider": "OpenAI", + "model": "gpt-5.6-terra", + "variant": "priority", + "input": 4, + "output": 24, + "cached_input": 0.4 + }, + { + "provider": "OpenAI", + "model": "gpt-audio", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "OpenAI", + "model": "gpt-audio-1.5", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "OpenAI", + "model": "gpt-audio-2025-08-28", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "OpenAI", + "model": "gpt-audio-mini", + "variant": "", + "input": 0.6, + "output": 2.4 + }, + { + "provider": "OpenAI", + "model": "gpt-audio-mini-2025-10-06", + "variant": "", + "input": 0.6, + "output": 2.4 + }, + { + "provider": "OpenAI", + "model": "gpt-audio-mini-2025-12-15", + "variant": "", + "input": 0.6, + "output": 2.4 + }, + { + "provider": "OpenAI", + "model": "gpt-image-1", + "variant": "", + "input": 5, + "cached_input": 1.25 + }, + { + "provider": "OpenAI", + "model": "gpt-image-1-mini", + "variant": "", + "input": 2, + "cached_input": 0.2 + }, + { + "provider": "OpenAI", + "model": "gpt-image-1.5", + "variant": "", + "input": 5, + "output": 10, + "cached_input": 1.25 + }, + { + "provider": "OpenAI", + "model": "gpt-image-1.5-2025-12-16", + "variant": "", + "input": 5, + "output": 10, + "cached_input": 1.25 + }, + { + "provider": "OpenAI", + "model": "gpt-image-2", + "variant": "", + "input": 5, + "output": 10, + "cached_input": 1.25 + }, + { + "provider": "OpenAI", + "model": "gpt-image-2-2026-04-21", + "variant": "", + "input": 5, + "output": 10, + "cached_input": 1.25 + }, + { + "provider": "OpenAI", + "model": "gpt-realtime", + "variant": "", + "input": 4, + "output": 16, + "cached_input": 0.4 + }, + { + "provider": "OpenAI", + "model": "gpt-realtime-1.5", + "variant": "", + "input": 4, + "output": 16, + "cached_input": 0.4 + }, + { + "provider": "OpenAI", + "model": "gpt-realtime-2", + "variant": "", + "input": 4, + "output": 16, + "cached_input": 0.4 + }, + { + "provider": "OpenAI", + "model": "gpt-realtime-2.1", + "variant": "", + "input": 4, + "output": 24, + "cached_input": 0.4 + }, + { + "provider": "OpenAI", + "model": "gpt-realtime-2.1-mini", + "variant": "", + "input": 0.6, + "output": 2.4, + "cached_input": 0.06 + }, + { + "provider": "OpenAI", + "model": "gpt-realtime-2025-08-28", + "variant": "", + "input": 4, + "output": 16, + "cached_input": 0.4 + }, + { + "provider": "OpenAI", + "model": "gpt-realtime-mini", + "variant": "", + "input": 0.6, + "output": 2.4 + }, + { + "provider": "OpenAI", + "model": "gpt-realtime-mini-2025-10-06", + "variant": "", + "input": 0.6, + "output": 2.4, + "cached_input": 0.06 + }, + { + "provider": "OpenAI", + "model": "gpt-realtime-mini-2025-12-15", + "variant": "", + "input": 0.6, + "output": 2.4, + "cached_input": 0.06 + }, + { + "provider": "OpenAI", + "model": "o1", + "variant": "", + "input": 15, + "output": 60, + "cached_input": 7.5 + }, + { + "provider": "OpenAI", + "model": "o1-2024-12-17", + "variant": "", + "input": 15, + "output": 60, + "cached_input": 7.5 + }, + { + "provider": "OpenAI", + "model": "o1-pro", + "variant": "", + "input": 150, + "output": 600 + }, + { + "provider": "OpenAI", + "model": "o1-pro", + "variant": "batches", + "input": 75, + "output": 300 + }, + { + "provider": "OpenAI", + "model": "o1-pro-2025-03-19", + "variant": "", + "input": 150, + "output": 600 + }, + { + "provider": "OpenAI", + "model": "o1-pro-2025-03-19", + "variant": "batches", + "input": 75, + "output": 300 + }, + { + "provider": "OpenAI", + "model": "o3", + "variant": "", + "input": 2, + "output": 8, + "cached_input": 0.5 + }, + { + "provider": "OpenAI", + "model": "o3", + "variant": "flex", + "input": 1, + "output": 4, + "cached_input": 0.25 + }, + { + "provider": "OpenAI", + "model": "o3", + "variant": "priority", + "input": 3.5, + "output": 14, + "cached_input": 0.875 + }, + { + "provider": "OpenAI", + "model": "o3-2025-04-16", + "variant": "", + "input": 2, + "output": 8, + "cached_input": 0.5 + }, + { + "provider": "OpenAI", + "model": "o3-deep-research", + "variant": "", + "input": 10, + "output": 40, + "cached_input": 2.5 + }, + { + "provider": "OpenAI", + "model": "o3-deep-research", + "variant": "batches", + "input": 5, + "output": 20 + }, + { + "provider": "OpenAI", + "model": "o3-deep-research-2025-06-26", + "variant": "", + "input": 10, + "output": 40, + "cached_input": 2.5 + }, + { + "provider": "OpenAI", + "model": "o3-deep-research-2025-06-26", + "variant": "batches", + "input": 5, + "output": 20 + }, + { + "provider": "OpenAI", + "model": "o3-mini", + "variant": "", + "input": 1.1, + "output": 4.4, + "cached_input": 0.55 + }, + { + "provider": "OpenAI", + "model": "o3-mini-2025-01-31", + "variant": "", + "input": 1.1, + "output": 4.4, + "cached_input": 0.55 + }, + { + "provider": "OpenAI", + "model": "o3-pro", + "variant": "", + "input": 20, + "output": 80 + }, + { + "provider": "OpenAI", + "model": "o3-pro", + "variant": "batches", + "input": 10, + "output": 40 + }, + { + "provider": "OpenAI", + "model": "o3-pro-2025-06-10", + "variant": "", + "input": 20, + "output": 80 + }, + { + "provider": "OpenAI", + "model": "o3-pro-2025-06-10", + "variant": "batches", + "input": 10, + "output": 40 + }, + { + "provider": "OpenAI", + "model": "o4-mini", + "variant": "", + "input": 1.1, + "output": 4.4, + "cached_input": 0.275 + }, + { + "provider": "OpenAI", + "model": "o4-mini", + "variant": "flex", + "input": 0.55, + "output": 2.2, + "cached_input": 0.1375 + }, + { + "provider": "OpenAI", + "model": "o4-mini", + "variant": "priority", + "input": 2, + "output": 8, + "cached_input": 0.5 + }, + { + "provider": "OpenAI", + "model": "o4-mini-2025-04-16", + "variant": "", + "input": 1.1, + "output": 4.4, + "cached_input": 0.275 + }, + { + "provider": "OpenAI", + "model": "o4-mini-deep-research", + "variant": "", + "input": 2, + "output": 8, + "cached_input": 0.5 + }, + { + "provider": "OpenAI", + "model": "o4-mini-deep-research", + "variant": "batches", + "input": 1, + "output": 4 + }, + { + "provider": "OpenAI", + "model": "o4-mini-deep-research-2025-06-26", + "variant": "", + "input": 2, + "output": 8, + "cached_input": 0.5 + }, + { + "provider": "OpenAI", + "model": "o4-mini-deep-research-2025-06-26", + "variant": "batches", + "input": 1, + "output": 4 + }, + { + "provider": "OpenAI", + "model": "text-embedding-3-large", + "variant": "", + "input": 0.13, + "output": 0 + }, + { + "provider": "OpenAI", + "model": "text-embedding-3-large", + "variant": "batches", + "input": 0.065, + "output": 0 + }, + { + "provider": "OpenAI", + "model": "text-embedding-3-small", + "variant": "", + "input": 0.02, + "output": 0 + }, + { + "provider": "OpenAI", + "model": "text-embedding-3-small", + "variant": "batches", + "input": 0.01, + "output": 0 + }, + { + "provider": "OpenAI", + "model": "text-embedding-ada-002", + "variant": "", + "input": 0.1, + "output": 0 + }, + { + "provider": "OpenAI", + "model": "text-embedding-ada-002-v2", + "variant": "", + "input": 0.1, + "output": 0 + }, + { + "provider": "OpenAI", + "model": "text-embedding-ada-002-v2", + "variant": "batches", + "input": 0.05, + "output": 0 + }, + { + "provider": "OpenRouter", + "model": "anthropic/claude-3-haiku", + "variant": "", + "input": 0.25, + "output": 1.25 + }, + { + "provider": "OpenRouter", + "model": "anthropic/claude-3.5-sonnet", + "variant": "", + "input": 3, + "output": 15 + }, + { + "provider": "OpenRouter", + "model": "anthropic/claude-3.7-sonnet", + "variant": "", + "input": 3, + "output": 15 + }, + { + "provider": "OpenRouter", + "model": "anthropic/claude-haiku-4.5", + "variant": "", + "input": 1, + "output": 5, + "cached_input": 0.1 + }, + { + "provider": "OpenRouter", + "model": "anthropic/claude-opus-4", + "variant": "", + "input": 15, + "output": 75, + "cached_input": 1.5 + }, + { + "provider": "OpenRouter", + "model": "anthropic/claude-opus-4.1", + "variant": "", + "input": 15, + "output": 75, + "cached_input": 1.5 + }, + { + "provider": "OpenRouter", + "model": "anthropic/claude-opus-4.5", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "OpenRouter", + "model": "anthropic/claude-opus-4.6", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "OpenRouter", + "model": "anthropic/claude-opus-4.7", + "variant": "", + "input": 5, + "output": 25, + "cached_input": 0.5 + }, + { + "provider": "OpenRouter", + "model": "anthropic/claude-sonnet-4", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "OpenRouter", + "model": "anthropic/claude-sonnet-4", + "variant": "above_200k_tokens", + "input": 6, + "output": 22.5, + "cached_input": 0.6 + }, + { + "provider": "OpenRouter", + "model": "anthropic/claude-sonnet-4.5", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "OpenRouter", + "model": "anthropic/claude-sonnet-4.5", + "variant": "above_200k_tokens", + "input": 6, + "output": 22.5, + "cached_input": 0.6 + }, + { + "provider": "OpenRouter", + "model": "anthropic/claude-sonnet-4.6", + "variant": "", + "input": 3, + "output": 15, + "cached_input": 0.3 + }, + { + "provider": "OpenRouter", + "model": "anthropic/claude-sonnet-4.6", + "variant": "above_200k_tokens", + "input": 6, + "output": 22.5, + "cached_input": 0.6 + }, + { + "provider": "OpenRouter", + "model": "bytedance/ui-tars-1.5-7b", + "variant": "", + "input": 0.1, + "output": 0.2 + }, + { + "provider": "OpenRouter", + "model": "deepseek/deepseek-chat", + "variant": "", + "input": 0.14, + "output": 0.28 + }, + { + "provider": "OpenRouter", + "model": "deepseek/deepseek-chat-v3-0324", + "variant": "", + "input": 0.14, + "output": 0.28 + }, + { + "provider": "OpenRouter", + "model": "deepseek/deepseek-chat-v3.1", + "variant": "", + "input": 0.2, + "output": 0.8 + }, + { + "provider": "OpenRouter", + "model": "deepseek/deepseek-chat-v3.1", + "variant": "cache_hit", + "input": 0.02 + }, + { + "provider": "OpenRouter", + "model": "deepseek/deepseek-r1", + "variant": "", + "input": 0.55, + "output": 2.19 + }, + { + "provider": "OpenRouter", + "model": "deepseek/deepseek-r1", + "variant": "cache_hit", + "input": 0.14 + }, + { + "provider": "OpenRouter", + "model": "deepseek/deepseek-r1-0528", + "variant": "", + "input": 0.5, + "output": 2.15 + }, + { + "provider": "OpenRouter", + "model": "deepseek/deepseek-r1-0528", + "variant": "cache_hit", + "input": 0.14 + }, + { + "provider": "OpenRouter", + "model": "deepseek/deepseek-v3.2", + "variant": "", + "input": 0.28, + "output": 0.4 + }, + { + "provider": "OpenRouter", + "model": "deepseek/deepseek-v3.2", + "variant": "cache_hit", + "input": 0.028 + }, + { + "provider": "OpenRouter", + "model": "deepseek/deepseek-v3.2-exp", + "variant": "", + "input": 0.2, + "output": 0.4 + }, + { + "provider": "OpenRouter", + "model": "deepseek/deepseek-v3.2-exp", + "variant": "cache_hit", + "input": 0.02 + }, + { + "provider": "OpenRouter", + "model": "google/gemini-2.0-flash-001", + "variant": "", + "input": 0.1, + "output": 0.4 + }, + { + "provider": "OpenRouter", + "model": "google/gemini-2.5-flash", + "variant": "", + "input": 0.3, + "output": 2.5 + }, + { + "provider": "OpenRouter", + "model": "google/gemini-2.5-pro", + "variant": "", + "input": 1.25, + "output": 10 + }, + { + "provider": "OpenRouter", + "model": "google/gemini-3-flash-preview", + "variant": "", + "input": 0.5, + "output": 3, + "cached_input": 0.05 + }, + { + "provider": "OpenRouter", + "model": "google/gemini-3-pro-preview", + "variant": "", + "input": 2, + "output": 12, + "cached_input": 0.2 + }, + { + "provider": "OpenRouter", + "model": "google/gemini-3-pro-preview", + "variant": "above_200k_tokens", + "input": 4, + "output": 18, + "cached_input": 0.4 + }, + { + "provider": "OpenRouter", + "model": "google/gemini-3-pro-preview", + "variant": "batches", + "input": 1, + "output": 6 + }, + { + "provider": "OpenRouter", + "model": "google/gemini-3.1-flash-lite", + "variant": "", + "input": 0.25, + "output": 1.5, + "cached_input": 0.025 + }, + { + "provider": "OpenRouter", + "model": "google/gemini-3.1-flash-lite-preview", + "variant": "", + "input": 0.25, + "output": 1.5, + "cached_input": 0.025 + }, + { + "provider": "OpenRouter", + "model": "google/gemini-3.1-pro-preview", + "variant": "", + "input": 2, + "output": 12, + "cached_input": 0.2 + }, + { + "provider": "OpenRouter", + "model": "google/gemini-3.1-pro-preview", + "variant": "above_200k_tokens", + "input": 4, + "output": 18, + "cached_input": 0.4 + }, + { + "provider": "OpenRouter", + "model": "gryphe/mythomax-l2-13b", + "variant": "", + "input": 1.875, + "output": 1.875 + }, + { + "provider": "OpenRouter", + "model": "mancer/weaver", + "variant": "", + "input": 5.625, + "output": 5.625 + }, + { + "provider": "OpenRouter", + "model": "meta-llama/llama-3-70b-instruct", + "variant": "", + "input": 0.59, + "output": 0.79 + }, + { + "provider": "OpenRouter", + "model": "minimax/minimax-m2", + "variant": "", + "input": 0.255, + "output": 1.02 + }, + { + "provider": "OpenRouter", + "model": "minimax/minimax-m2.1", + "variant": "", + "input": 0.27, + "output": 1.2, + "cached_input": 0 + }, + { + "provider": "OpenRouter", + "model": "minimax/minimax-m2.5", + "variant": "", + "input": 0.3, + "output": 1.1, + "cached_input": 0.15 + }, + { + "provider": "OpenRouter", + "model": "mistralai/devstral-2512", + "variant": "", + "input": 0.15, + "output": 0.6 + }, + { + "provider": "OpenRouter", + "model": "mistralai/ministral-14b-2512", + "variant": "", + "input": 0.2, + "output": 0.2 + }, + { + "provider": "OpenRouter", + "model": "mistralai/ministral-3b-2512", + "variant": "", + "input": 0.1, + "output": 0.1 + }, + { + "provider": "OpenRouter", + "model": "mistralai/ministral-8b-2512", + "variant": "", + "input": 0.15, + "output": 0.15 + }, + { + "provider": "OpenRouter", + "model": "mistralai/mistral-7b-instruct", + "variant": "", + "input": 0.13, + "output": 0.13 + }, + { + "provider": "OpenRouter", + "model": "mistralai/mistral-large", + "variant": "", + "input": 8, + "output": 24 + }, + { + "provider": "OpenRouter", + "model": "mistralai/mistral-large-2512", + "variant": "", + "input": 0.5, + "output": 1.5 + }, + { + "provider": "OpenRouter", + "model": "mistralai/mistral-small-3.1-24b-instruct", + "variant": "", + "input": 0.1, + "output": 0.3 + }, + { + "provider": "OpenRouter", + "model": "mistralai/mistral-small-3.2-24b-instruct", + "variant": "", + "input": 0.1, + "output": 0.3 + }, + { + "provider": "OpenRouter", + "model": "mistralai/mixtral-8x22b-instruct", + "variant": "", + "input": 0.65, + "output": 0.65 + }, + { + "provider": "OpenRouter", + "model": "moonshotai/kimi-k2.5", + "variant": "", + "input": 0.6, + "output": 3, + "cached_input": 0.1 + }, + { + "provider": "OpenRouter", + "model": "openai/gpt-3.5-turbo", + "variant": "", + "input": 1.5, + "output": 2 + }, + { + "provider": "OpenRouter", + "model": "openai/gpt-3.5-turbo-16k", + "variant": "", + "input": 3, + "output": 4 + }, + { + "provider": "OpenRouter", + "model": "openai/gpt-4", + "variant": "", + "input": 30, + "output": 60 + }, + { + "provider": "OpenRouter", + "model": "openai/gpt-4.1", + "variant": "", + "input": 2, + "output": 8, + "cached_input": 0.5 + }, + { + "provider": "OpenRouter", + "model": "openai/gpt-4.1-mini", + "variant": "", + "input": 0.4, + "output": 1.6, + "cached_input": 0.1 + }, + { + "provider": "OpenRouter", + "model": "openai/gpt-4.1-nano", + "variant": "", + "input": 0.1, + "output": 0.4, + "cached_input": 0.025 + }, + { + "provider": "OpenRouter", + "model": "openai/gpt-4o", + "variant": "", + "input": 2.5, + "output": 10 + }, + { + "provider": "OpenRouter", + "model": "openai/gpt-4o-2024-05-13", + "variant": "", + "input": 5, + "output": 15 + }, + { + "provider": "OpenRouter", + "model": "openai/gpt-5", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "OpenRouter", + "model": "openai/gpt-5-chat", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "OpenRouter", + "model": "openai/gpt-5-codex", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "OpenRouter", + "model": "openai/gpt-5-mini", + "variant": "", + "input": 0.25, + "output": 2, + "cached_input": 0.025 + }, + { + "provider": "OpenRouter", + "model": "openai/gpt-5-nano", + "variant": "", + "input": 0.05, + "output": 0.4, + "cached_input": 0.005 + }, + { + "provider": "OpenRouter", + "model": "openai/gpt-5.1-codex-max", + "variant": "", + "input": 1.25, + "output": 10, + "cached_input": 0.125 + }, + { + "provider": "OpenRouter", + "model": "openai/gpt-5.2", + "variant": "", + "input": 1.75, + "output": 14, + "cached_input": 0.175 + }, + { + "provider": "OpenRouter", + "model": "openai/gpt-5.2-chat", + "variant": "", + "input": 1.75, + "output": 14, + "cached_input": 0.175 + }, + { + "provider": "OpenRouter", + "model": "openai/gpt-5.2-codex", + "variant": "", + "input": 1.75, + "output": 14, + "cached_input": 0.175 + }, + { + "provider": "OpenRouter", + "model": "openai/gpt-5.2-pro", + "variant": "", + "input": 21, + "output": 168 + }, + { + "provider": "OpenRouter", + "model": "openai/gpt-oss-120b", + "variant": "", + "input": 0.18, + "output": 0.8 + }, + { + "provider": "OpenRouter", + "model": "openai/gpt-oss-20b", + "variant": "", + "input": 0.02, + "output": 0.1 + }, + { + "provider": "OpenRouter", + "model": "openai/o1", + "variant": "", + "input": 15, + "output": 60, + "cached_input": 7.5 + }, + { + "provider": "OpenRouter", + "model": "openai/o3-mini", + "variant": "", + "input": 1.1, + "output": 4.4 + }, + { + "provider": "OpenRouter", + "model": "openai/o3-mini-high", + "variant": "", + "input": 1.1, + "output": 4.4 + }, + { + "provider": "OpenRouter", + "model": "qwen/qwen-2.5-coder-32b-instruct", + "variant": "", + "input": 0.18, + "output": 0.18 + }, + { + "provider": "OpenRouter", + "model": "qwen/qwen-vl-plus", + "variant": "", + "input": 0.21, + "output": 0.63 + }, + { + "provider": "OpenRouter", + "model": "qwen/qwen3-235b-a22b-2507", + "variant": "", + "input": 0.071, + "output": 0.1 + }, + { + "provider": "OpenRouter", + "model": "qwen/qwen3-235b-a22b-thinking-2507", + "variant": "", + "input": 0.11, + "output": 0.6 + }, + { + "provider": "OpenRouter", + "model": "qwen/qwen3-coder", + "variant": "", + "input": 0.22, + "output": 0.95 + }, + { + "provider": "OpenRouter", + "model": "qwen/qwen3-coder-plus", + "variant": "", + "input": 1, + "output": 5 + }, + { + "provider": "OpenRouter", + "model": "qwen/qwen3.5-122b-a10b", + "variant": "", + "input": 0.4, + "output": 2 + }, + { + "provider": "OpenRouter", + "model": "qwen/qwen3.5-27b", + "variant": "", + "input": 0.3, + "output": 2.4 + }, + { + "provider": "OpenRouter", + "model": "qwen/qwen3.5-35b-a3b", + "variant": "", + "input": 0.25, + "output": 2 + }, + { + "provider": "OpenRouter", + "model": "qwen/qwen3.5-397b-a17b", + "variant": "", + "input": 0.6, + "output": 3.6 + }, + { + "provider": "OpenRouter", + "model": "qwen/qwen3.5-flash-02-23", + "variant": "", + "input": 0.1, + "output": 0.4 + }, + { + "provider": "OpenRouter", + "model": "qwen/qwen3.5-plus-02-15", + "variant": "", + "input": 0.4, + "output": 2.4 + }, + { + "provider": "OpenRouter", + "model": "qwen/qwen3.5-plus-02-15", + "variant": "above_256k_tokens", + "input": 0.5, + "output": 3 + }, + { + "provider": "OpenRouter", + "model": "qwen/qwen3.6-plus", + "variant": "", + "input": 0.325, + "output": 1.95 + }, + { + "provider": "OpenRouter", + "model": "switchpoint/router", + "variant": "", + "input": 0.85, + "output": 3.4 + }, + { + "provider": "OpenRouter", + "model": "undi95/remm-slerp-l2-13b", + "variant": "", + "input": 1.875, + "output": 1.875 + }, + { + "provider": "OpenRouter", + "model": "x-ai/grok-4", + "variant": "", + "input": 3, + "output": 15 + }, + { + "provider": "OpenRouter", + "model": "xiaomi/mimo-v2-flash", + "variant": "", + "input": 0.1, + "output": 0.3, + "cached_input": 0.01 + }, + { + "provider": "OpenRouter", + "model": "xiaomi/mimo-v2.5", + "variant": "", + "input": 0.4, + "output": 2, + "cached_input": 0.08 + }, + { + "provider": "OpenRouter", + "model": "xiaomi/mimo-v2.5-pro", + "variant": "", + "input": 1, + "output": 3, + "cached_input": 0.2 + }, + { + "provider": "OpenRouter", + "model": "z-ai/glm-4.6", + "variant": "", + "input": 0.4, + "output": 1.75 + }, + { + "provider": "OpenRouter", + "model": "z-ai/glm-4.6:exacto", + "variant": "", + "input": 0.45, + "output": 1.9 + }, + { + "provider": "OpenRouter", + "model": "z-ai/glm-4.7", + "variant": "", + "input": 0.4, + "output": 1.5, + "cached_input": 0 + }, + { + "provider": "OpenRouter", + "model": "z-ai/glm-4.7-flash", + "variant": "", + "input": 0.07, + "output": 0.4, + "cached_input": 0 + }, + { + "provider": "OpenRouter", + "model": "z-ai/glm-5", + "variant": "", + "input": 0.8, + "output": 2.56 + }, + { + "provider": "OpenRouter", + "model": "z-ai/glm-5.1", + "variant": "", + "input": 1.05, + "output": 3.5, + "cached_input": 0.525 + }, + { + "provider": "Posit", + "model": "claude-fable-5", + "variant": "", + "input": 11, + "output": 55, + "cached_input": 1.1 + }, + { + "provider": "Posit", + "model": "claude-haiku-4-5", + "variant": "", + "input": 1.1, + "output": 5.5, + "cached_input": 0.11 + }, + { + "provider": "Posit", + "model": "claude-opus-4-5", + "variant": "", + "input": 5.5, + "output": 27.5, + "cached_input": 0.55 + }, + { + "provider": "Posit", + "model": "claude-opus-4-6", + "variant": "", + "input": 5.5, + "output": 27.5, + "cached_input": 0.55 + }, + { + "provider": "Posit", + "model": "claude-opus-4-7", + "variant": "", + "input": 5.5, + "output": 27.5, + "cached_input": 0.55 + }, + { + "provider": "Posit", + "model": "claude-opus-4-8", + "variant": "", + "input": 5.5, + "output": 27.5, + "cached_input": 0.55 + }, + { + "provider": "Posit", + "model": "claude-sonnet-4-5", + "variant": "", + "input": 3.3, + "output": 16.5, + "cached_input": 0.33 + }, + { + "provider": "Posit", + "model": "claude-sonnet-4-5", + "variant": "above_200k_tokens", + "input": 6.6, + "output": 24.75, + "cached_input": 0.66 + }, + { + "provider": "Posit", + "model": "claude-sonnet-4-6", + "variant": "", + "input": 3.3, + "output": 16.5, + "cached_input": 0.33 + }, + { + "provider": "Posit", + "model": "google/gemma-4-26B-A4B-it", + "variant": "", + "input": 0.3, + "output": 1.5, + "cached_input": 0.03 + } + ] +} diff --git a/chatlas/types/anthropic/_submit.py b/chatlas/types/anthropic/_submit.py index 626dd08c..04abb2c7 100644 --- a/chatlas/types/anthropic/_submit.py +++ b/chatlas/types/anthropic/_submit.py @@ -58,8 +58,6 @@ class SubmitInputArgs(TypedDict, total=False): "claude-opus-4-5-20251101", "claude-sonnet-4-5", "claude-sonnet-4-5-20250929", - "claude-opus-4-1", - "claude-opus-4-1-20250805", ], str, ] From 607011b41af00439541a7a54e5c0b2000651d929 Mon Sep 17 00:00:00 2001 From: Carson Date: Fri, 7 Aug 2026 19:10:57 -0500 Subject: [PATCH 11/14] docs(changelog): note Anthropic document_index citation fix --- CHANGELOG.md | 1 + 1 file changed, 1 insertion(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index 32cc74e2..3430e5b3 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -38,6 +38,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 * `register_mcp_tools_stdio_async()` and `register_mcp_tools_http_stream_async()` no longer fail when an MCP server leaves some tool annotations unset. * `ContentCitation`, `ContentToolRequestFetch`, and `ContentToolResponseFetch` now actually render, instead of silently vanishing due to a markdown link-reference parsing quirk. * `ChatAnthropic()` (and `ChatBedrockAnthropic()`) now bill refusal-fallback turns at the correct (serving model's) rate rather than the originally requested model's, mirroring [ellmer's equivalent fix](https://github.com/tidyverse/ellmer/pull/1058). +* `ChatAnthropic()` citations backed by `document_index` (from `tool_web_fetch()` results and document/PDF attachments) now resolve to a source URL, instead of always coming back without one. Anthropic counts that index across every document-shaped block in the whole request, including ones from prior turns, which chatlas wasn't accounting for. (#382) ### Breaking changes From 9c82c0108860af993e7682774c0c084bf5ccf480 Mon Sep 17 00:00:00 2001 From: Carson Date: Fri, 7 Aug 2026 20:06:57 -0500 Subject: [PATCH 12/14] docs(changelog): move entry into fresh UNRELEASED section main's UNRELEASED header was retroactively split into 0.21.0, so this entry needs to live above that split, not inside it. --- CHANGELOG.md | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 3430e5b3..9d71980d 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -10,6 +10,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ## [UNRELEASED] +### Bug fixes + +* `ChatAnthropic()` citations backed by `document_index` (from `tool_web_fetch()` results and document/PDF attachments) now resolve to a source URL, instead of always coming back without one. Anthropic counts that index across every document-shaped block in the whole request, including ones from prior turns, which chatlas wasn't accounting for. (#382) + ## [0.21.0] - 2026-08-04 ### New features @@ -38,7 +42,6 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 * `register_mcp_tools_stdio_async()` and `register_mcp_tools_http_stream_async()` no longer fail when an MCP server leaves some tool annotations unset. * `ContentCitation`, `ContentToolRequestFetch`, and `ContentToolResponseFetch` now actually render, instead of silently vanishing due to a markdown link-reference parsing quirk. * `ChatAnthropic()` (and `ChatBedrockAnthropic()`) now bill refusal-fallback turns at the correct (serving model's) rate rather than the originally requested model's, mirroring [ellmer's equivalent fix](https://github.com/tidyverse/ellmer/pull/1058). -* `ChatAnthropic()` citations backed by `document_index` (from `tool_web_fetch()` results and document/PDF attachments) now resolve to a source URL, instead of always coming back without one. Anthropic counts that index across every document-shaped block in the whole request, including ones from prior turns, which chatlas wasn't accounting for. (#382) ### Breaking changes From 44b8de41811a63e6baa37ac3f772da8b465aca1e Mon Sep 17 00:00:00 2001 From: Carson Date: Fri, 7 Aug 2026 20:17:41 -0500 Subject: [PATCH 13/14] fix(tokens): read prices.json's new ellmer schema ellmer wraps its price list in an object (schema_version, min_ellmer_version, updated_at, data) instead of a bare array. The bot-updated prices.json on this branch already reflects that, but pricing_list still parsed the whole file as the list, so every price lookup raised "string indices must be integers". --- chatlas/_tokens.py | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/chatlas/_tokens.py b/chatlas/_tokens.py index bb152314..6da45ad4 100644 --- a/chatlas/_tokens.py +++ b/chatlas/_tokens.py @@ -123,9 +123,11 @@ class TokenPrice(TypedDict): """The pricing variant (e.g., "flex", "priority", "batches")""" -# Load in pricing pulled from ellmer +# Load in pricing pulled from ellmer. ellmer's prices.json is an object with +# metadata (schema_version, min_ellmer_version, updated_at) wrapping the +# actual price list under "data". f = resources.files("chatlas").joinpath("data/prices.json").read_text(encoding="utf-8") -pricing_list: list[TokenPrice] = orjson.loads(f) +pricing_list: list[TokenPrice] = orjson.loads(f)["data"] def get_price_info(name: str, model: str, variant: str = "") -> TokenPrice | None: From bf48d750e6d8201a47ebb378f34962ea57cef570 Mon Sep 17 00:00:00 2001 From: Carson Date: Fri, 7 Aug 2026 21:06:57 -0500 Subject: [PATCH 14/14] fix(tokens): tolerate price entries with no input cost ellmer's prices.json (see tidyverse/ellmer#968, the same PR that introduced the envelope schema) no longer guarantees an `input` key per row -- output-only models (e.g. Bedrock's TwelveLabs Pegasus video models) omit it. get_token_cost() indexed price["input"] directly, so pricing these models raised KeyError. --- CHANGELOG.md | 1 + chatlas/_tokens.py | 6 +++--- tests/test_tokens.py | 26 +++++++++++++++++++------- 3 files changed, 23 insertions(+), 10 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 9d71980d..1a225752 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -13,6 +13,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0 ### Bug fixes * `ChatAnthropic()` citations backed by `document_index` (from `tool_web_fetch()` results and document/PDF attachments) now resolve to a source URL, instead of always coming back without one. Anthropic counts that index across every document-shaped block in the whole request, including ones from prior turns, which chatlas wasn't accounting for. (#382) +* Token cost lookups (`.get_cost()`, `token_usage()`) no longer crash on models with no input price (e.g. output-only video generation models on Bedrock), and read ellmer's current pricing data format, which now wraps the price list in a versioned envelope rather than a bare array. (#382) ## [0.21.0] - 2026-08-04 diff --git a/chatlas/_tokens.py b/chatlas/_tokens.py index 6da45ad4..85721b47 100644 --- a/chatlas/_tokens.py +++ b/chatlas/_tokens.py @@ -115,8 +115,8 @@ class TokenPrice(TypedDict): """The model name (e.g., "gpt-3.5-turbo", "claude-2", etc.)""" cached_input: NotRequired[float] """The cost per user token in USD per million tokens for cached input""" - input: float - """The cost per user token in USD per million tokens""" + input: NotRequired[float] + """The cost per user token in USD per million tokens (absent for some output-only models, e.g. video generation)""" output: NotRequired[float] """The cost per assistant token in USD per million tokens""" variant: NotRequired[str] @@ -208,7 +208,7 @@ def get_token_cost( price = get_price_info(name, model, variant) if price is None: return None - input_price = tokens[0] * (price["input"] / 1e6) + input_price = tokens[0] * (price.get("input", 0) / 1e6) output_price = tokens[1] * (price.get("output", 0) / 1e6) cached_price = tokens[2] * (price.get("cached_input", 0) / 1e6) return input_price + output_price + cached_price diff --git a/tests/test_tokens.py b/tests/test_tokens.py index a8df11ce..d3c19515 100644 --- a/tests/test_tokens.py +++ b/tests/test_tokens.py @@ -93,6 +93,7 @@ def test_get_token_prices(): assert pricing is not None assert pricing["provider"] == "OpenAI" assert pricing["model"] == "gpt-5.4" + assert "input" in pricing assert isinstance(pricing["input"], (int, float)) # cached_input and output might be optional if "cached_input" in pricing: @@ -112,6 +113,17 @@ def test_get_token_cost(): assert price is None +def test_get_token_cost_handles_missing_input_price(): + """Some models (e.g. output-only video generation) have no `input` price.""" + from chatlas._tokens import pricing_list + + entry = next((p for p in pricing_list if "input" not in p), None) + assert entry is not None, "expected at least one price entry without 'input'" + + cost = get_token_cost(entry["provider"], entry["model"], (10, 50, 0)) + assert cost is not None + + def test_usage_is_none(): tokens_reset() assert token_usage() is None @@ -179,27 +191,27 @@ def test_get_price_info_with_variants(): # Test baseline (empty variant) baseline = get_price_info("OpenAI", "gpt-4o", variant="") assert baseline is not None - assert baseline["input"] == 2.5 - assert baseline["output"] == 10 + assert "input" in baseline and baseline["input"] == 2.5 + assert "output" in baseline and baseline["output"] == 10 assert baseline.get("variant", "") == "" # Test specific variant batches = get_price_info("OpenAI", "gpt-4o", variant="batches") assert batches is not None - assert batches["input"] == 1.25 # 50% discount - assert batches["output"] == 5 + assert "input" in batches and batches["input"] == 1.25 # 50% discount + assert "output" in batches and batches["output"] == 5 assert batches.get("variant") == "batches" priority = get_price_info("OpenAI", "gpt-4o", variant="priority") assert priority is not None - assert priority["input"] == 4.25 # Higher price - assert priority["output"] == 17 + assert "input" in priority and priority["input"] == 4.25 # Higher price + assert "output" in priority and priority["output"] == 17 assert priority.get("variant") == "priority" # Test fallback: non-existent variant should fall back to baseline fallback = get_price_info("OpenAI", "gpt-4o", variant="nonexistent_variant") assert fallback is not None - assert fallback["input"] == 2.5 # Should match baseline + assert "input" in fallback and fallback["input"] == 2.5 # Should match baseline assert fallback.get("variant", "") == "" # Test no fallback when variant not specified and model not found