From 6f5cd03286b547d74b12a2eda400f48771feab50 Mon Sep 17 00:00:00 2001 From: Cahl-Dee <1673298+Cahl-Dee@users.noreply.github.com> Date: Wed, 21 Oct 2026 13:30:46 -0500 Subject: [PATCH 1/5] docs(thegrid): list every instrument from /v1/models --- fern/customization/custom-llm/thegrid.mdx | 34 +++++++++++++++++++---- 1 file changed, 29 insertions(+), 5 deletions(-) diff --git a/fern/customization/custom-llm/thegrid.mdx b/fern/customization/custom-llm/thegrid.mdx index 2bc804f14..1dd4a0577 100644 --- a/fern/customization/custom-llm/thegrid.mdx +++ b/fern/customization/custom-llm/thegrid.mdx @@ -54,14 +54,38 @@ Setting `metadataSendMode` to `off` keeps Vapi call metadata out of requests to ## Choose an instrument -`GET https://api.thegrid.ai/v1/models` lists available instrument IDs. Check [instrument specifications](https://thegrid.ai/instruments) and [pricing](https://thegrid.ai/pricing) for current details. Examples include: +`GET https://api.thegrid.ai/v1/models` lists available instrument IDs. Check [instrument specifications](https://thegrid.ai/instruments) and [pricing](https://thegrid.ai/pricing) for current details. Current instruments: + +{/* grid-models:start (generated from GET /v1/models) */} + +**Capability tiers** + +| Instrument | Use it for | +| --- | --- | +| `text-standard` | Price-optimized, high-throughput text for high-volume, low-stakes work. | +| `text-prime` | The production default for everyday text generation. | +| `text-max` | Frontier-tier text for high-stakes, long-context work. | +| `agent-standard` | Price-optimized, high-throughput agents for orchestration glue, routing, tool selection, and high-volume single-purpose agents. | +| `agent-prime` | The production default for daily agent work, production agent loops, multi-step tool chains, and planning. | +| `agent-max` | Frontier-tier agents for autonomous work, deep tool chains, long-horizon research, and high-stakes automation. | +| `code-standard` | Price-optimized, high-throughput code for linting, batch edits, and high-volume code tasks where cost matters more than time to first token. | +| `code-prime` | The production default for daily coding work. | +| `code-max` | Frontier-tier code for changes that span a whole codebase. | + +**Latest-model aliases.** Each one routes to the newest qualifying model from that lab, so the underlying model can change. | Instrument | Use it for | | --- | --- | -| `text-standard` | General conversation. The usual starting point. | -| `text-prime`, `text-max` | More demanding questions; compare current speed and price. | -| `agent-standard`, `agent-max` | Multi-step tool use. | -| `code-standard`, `code-prime` | Assistants that read or write code. | +| `bytedance-pro-latest` | Lab latest market for ByteDance Pro supply. | +| `claude-opus-latest` | Lab latest market for Claude Opus frontier supply. | +| `deepseek-pro-latest` | Lab latest market for DeepSeek Pro supply. | +| `gemini-pro-latest` | Lab latest market for Gemini Pro frontier supply. | +| `glm-latest` | Lab latest market for GLM supply. | +| `gpt-sol-latest` | Lab latest market for GPT frontier supply. | +| `kimi-latest` | Lab latest market for Kimi supply. | +| `minimax-latest` | Lab latest market for MiniMax supply. | + +{/* grid-models:end */} ## Set `maxTokens` for spoken replies From 032c16bf0087fb6e5feb320d7467d2eed1b5f0b8 Mon Sep 17 00:00:00 2001 From: Cahl-Dee <1673298+Cahl-Dee@users.noreply.github.com> Date: Wed, 21 Oct 2026 13:30:47 -0500 Subject: [PATCH 2/5] docs(thegrid): use Cortex instrument descriptions in the instrument table --- fern/customization/custom-llm/thegrid.mdx | 46 +++++++++++------------ 1 file changed, 23 insertions(+), 23 deletions(-) diff --git a/fern/customization/custom-llm/thegrid.mdx b/fern/customization/custom-llm/thegrid.mdx index 1dd4a0577..791de4298 100644 --- a/fern/customization/custom-llm/thegrid.mdx +++ b/fern/customization/custom-llm/thegrid.mdx @@ -56,34 +56,34 @@ Setting `metadataSendMode` to `off` keeps Vapi call metadata out of requests to `GET https://api.thegrid.ai/v1/models` lists available instrument IDs. Check [instrument specifications](https://thegrid.ai/instruments) and [pricing](https://thegrid.ai/pricing) for current details. Current instruments: -{/* grid-models:start (generated from GET /v1/models) */} +{/* grid-models:start (generated: IDs from GET /v1/models) */} **Capability tiers** -| Instrument | Use it for | +| Instrument | Description | | --- | --- | -| `text-standard` | Price-optimized, high-throughput text for high-volume, low-stakes work. | -| `text-prime` | The production default for everyday text generation. | -| `text-max` | Frontier-tier text for high-stakes, long-context work. | -| `agent-standard` | Price-optimized, high-throughput agents for orchestration glue, routing, tool selection, and high-volume single-purpose agents. | -| `agent-prime` | The production default for daily agent work, production agent loops, multi-step tool chains, and planning. | -| `agent-max` | Frontier-tier agents for autonomous work, deep tool chains, long-horizon research, and high-stakes automation. | -| `code-standard` | Price-optimized, high-throughput code for linting, batch edits, and high-volume code tasks where cost matters more than time to first token. | -| `code-prime` | The production default for daily coding work. | -| `code-max` | Frontier-tier code for changes that span a whole codebase. | - -**Latest-model aliases.** Each one routes to the newest qualifying model from that lab, so the underlying model can change. - -| Instrument | Use it for | +| `text-standard` | Price-optimized models with low-latency, high-throughput and shorter maximum outputs | +| `text-prime` | Reliable models for everyday text generation, editing, and analysis across diverse workflows | +| `text-max` | Frontier models for deep reasoning, long context, and complex workflows | +| `agent-standard` | Price-optimized models for fast tool calls, simple agent loops, high-throughput automation, and orchestration | +| `agent-prime` | Reliable models for dependable agentic applications, multi-step tool use, and reasoning workflows | +| `agent-max` | Frontier models for autonomous research, deep multi-step tool chains, and complex long-horizon tasks | +| `code-standard` | Price-optimized models for rapid autocomplete, linting, high-frequency suggestions, and batch edits | +| `code-prime` | Reliable models for everyday software tasks, code completion, review, and standard debugging | +| `code-max` | Frontier models for complex research, architectural decisions, debugging, and multi-file development | + +**Latest-model aliases.** Each follows the newest release from that lab, with fallbacks to previous versions. + +| Instrument | Description | | --- | --- | -| `bytedance-pro-latest` | Lab latest market for ByteDance Pro supply. | -| `claude-opus-latest` | Lab latest market for Claude Opus frontier supply. | -| `deepseek-pro-latest` | Lab latest market for DeepSeek Pro supply. | -| `gemini-pro-latest` | Lab latest market for Gemini Pro frontier supply. | -| `glm-latest` | Lab latest market for GLM supply. | -| `gpt-sol-latest` | Lab latest market for GPT frontier supply. | -| `kimi-latest` | Lab latest market for Kimi supply. | -| `minimax-latest` | Lab latest market for MiniMax supply. | +| `bytedance-pro-latest` | Latest ByteDance Pro model release with fallbacks to previous versions for reliability | +| `claude-opus-latest` | Latest Claude Opus model release with fallbacks to previous versions for reliability | +| `deepseek-pro-latest` | Latest Deepseek Pro model release with fallbacks to previous versions for reliability | +| `gemini-pro-latest` | Latest Gemini Pro model release with fallbacks to previous versions for reliability | +| `glm-latest` | Latest GLM model release with fallbacks to previous versions for reliability | +| `gpt-sol-latest` | Latest OpenAI GPT Sol model release with fallbacks to previous versions for reliability | +| `kimi-latest` | Latest Kimi model release with fallbacks to previous versions for reliability | +| `minimax-latest` | Latest Minimax model release with fallbacks to previous versions for reliability | {/* grid-models:end */} From 94093bed3bf112e69eb3257efcfa075f2a491549 Mon Sep 17 00:00:00 2001 From: Cahl-Dee <1673298+Cahl-Dee@users.noreply.github.com> Date: Wed, 21 Oct 2026 13:30:47 -0500 Subject: [PATCH 3/5] docs(thegrid): add a model settings checklist --- fern/customization/custom-llm/thegrid.mdx | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/fern/customization/custom-llm/thegrid.mdx b/fern/customization/custom-llm/thegrid.mdx index 791de4298..836024660 100644 --- a/fern/customization/custom-llm/thegrid.mdx +++ b/fern/customization/custom-llm/thegrid.mdx @@ -93,6 +93,20 @@ Vapi uses `250` for `maxTokens` when it is omitted and sends the value to The Gr The `600` value in the example is a starting point. Test your chosen instrument with representative spoken turns and raise the limit if replies are truncated. Keep the system prompt explicit about brevity. +## Check the other model settings + +In the dashboard, open **Assistant → Model** and choose **Custom LLM**. Check each setting against The Grid's values. `GET https://api.thegrid.ai/v1/models` returns the current numbers for every instrument. + +| Setting | What to set | +| --- | --- | +| **Model** | The exact instrument ID, such as `text-prime`. Don't use the display name. | +| **Custom LLM URL** | `https://api.thegrid.ai/v1` | +| **Max Tokens** | At or below the instrument's `max_completion_tokens`. Vapi's default of `250` suits short spoken replies. | +| **Request Timeout** | Above the instrument's `grid.ttft_max_seconds`, the longest time its providers can take to start streaming and still meet the specification. Vapi's default is 20 seconds. | +| **Metadata Send Mode** | **Off — send only messages**, to keep Vapi call metadata out of requests to The Grid. | + +Limits differ between instruments and change over time, so read them from `GET /v1/models` instead of copying numbers into your configuration. + ## Tool calling The Grid's API supports OpenAI-style function calling. To configure Vapi tools, see the [tool calling integration guide](/customization/tool-calling-integration). Test a tool call with your chosen instrument before relying on it. From d29d1f785c78b8a5c363d626704b28e01e72538e Mon Sep 17 00:00:00 2001 From: Cahl-Dee <1673298+Cahl-Dee@users.noreply.github.com> Date: Wed, 21 Oct 2026 13:30:47 -0500 Subject: [PATCH 4/5] docs(thegrid): use text-prime in the example assistant --- fern/customization/custom-llm/thegrid.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fern/customization/custom-llm/thegrid.mdx b/fern/customization/custom-llm/thegrid.mdx index 836024660..21e499c0c 100644 --- a/fern/customization/custom-llm/thegrid.mdx +++ b/fern/customization/custom-llm/thegrid.mdx @@ -37,7 +37,7 @@ Send this body to `POST https://api.vapi.ai/assistant` with the same Vapi privat "model": { "provider": "custom-llm", "url": "https://api.thegrid.ai/v1", - "model": "text-standard", + "model": "text-prime", "metadataSendMode": "off", "maxTokens": 600, "messages": [ From 5f21ed185b7d90a164602b7c84a35d118d3fc410 Mon Sep 17 00:00:00 2001 From: Stephen Smith Date: Wed, 21 Oct 2026 12:58:57 -0700 Subject: [PATCH 5/5] Editorial pass on The Grid instruments --- fern/customization/custom-llm/thegrid.mdx | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) diff --git a/fern/customization/custom-llm/thegrid.mdx b/fern/customization/custom-llm/thegrid.mdx index 21e499c0c..38a359cc8 100644 --- a/fern/customization/custom-llm/thegrid.mdx +++ b/fern/customization/custom-llm/thegrid.mdx @@ -56,13 +56,11 @@ Setting `metadataSendMode` to `off` keeps Vapi call metadata out of requests to `GET https://api.thegrid.ai/v1/models` lists available instrument IDs. Check [instrument specifications](https://thegrid.ai/instruments) and [pricing](https://thegrid.ai/pricing) for current details. Current instruments: -{/* grid-models:start (generated: IDs from GET /v1/models) */} - -**Capability tiers** +### Capability tiers | Instrument | Description | | --- | --- | -| `text-standard` | Price-optimized models with low-latency, high-throughput and shorter maximum outputs | +| `text-standard` | Price-optimized models with low latency, high throughput, and shorter maximum outputs | | `text-prime` | Reliable models for everyday text generation, editing, and analysis across diverse workflows | | `text-max` | Frontier models for deep reasoning, long context, and complex workflows | | `agent-standard` | Price-optimized models for fast tool calls, simple agent loops, high-throughput automation, and orchestration | @@ -72,20 +70,20 @@ Setting `metadataSendMode` to `off` keeps Vapi call metadata out of requests to | `code-prime` | Reliable models for everyday software tasks, code completion, review, and standard debugging | | `code-max` | Frontier models for complex research, architectural decisions, debugging, and multi-file development | -**Latest-model aliases.** Each follows the newest release from that lab, with fallbacks to previous versions. +### Latest-model aliases + +Each alias follows the newest model release from one lab, with fallbacks to previous versions. | Instrument | Description | | --- | --- | | `bytedance-pro-latest` | Latest ByteDance Pro model release with fallbacks to previous versions for reliability | | `claude-opus-latest` | Latest Claude Opus model release with fallbacks to previous versions for reliability | -| `deepseek-pro-latest` | Latest Deepseek Pro model release with fallbacks to previous versions for reliability | +| `deepseek-pro-latest` | Latest DeepSeek Pro model release with fallbacks to previous versions for reliability | | `gemini-pro-latest` | Latest Gemini Pro model release with fallbacks to previous versions for reliability | | `glm-latest` | Latest GLM model release with fallbacks to previous versions for reliability | | `gpt-sol-latest` | Latest OpenAI GPT Sol model release with fallbacks to previous versions for reliability | | `kimi-latest` | Latest Kimi model release with fallbacks to previous versions for reliability | -| `minimax-latest` | Latest Minimax model release with fallbacks to previous versions for reliability | - -{/* grid-models:end */} +| `minimax-latest` | Latest MiniMax model release with fallbacks to previous versions for reliability | ## Set `maxTokens` for spoken replies @@ -95,7 +93,7 @@ The `600` value in the example is a starting point. Test your chosen instrument ## Check the other model settings -In the dashboard, open **Assistant → Model** and choose **Custom LLM**. Check each setting against The Grid's values. `GET https://api.thegrid.ai/v1/models` returns the current numbers for every instrument. +In the [Vapi Dashboard](https://dashboard.vapi.ai), open your assistant, select the **Model** card, and choose **Custom LLM** in the panel that opens. Check each setting against The Grid's values. [`GET https://api.thegrid.ai/v1/models`](https://api.thegrid.ai/v1/models) returns the current numbers for every instrument. | Setting | What to set | | --- | --- | @@ -105,7 +103,7 @@ In the dashboard, open **Assistant → Model** and choose **Custom LLM**. Check | **Request Timeout** | Above the instrument's `grid.ttft_max_seconds`, the longest time its providers can take to start streaming and still meet the specification. Vapi's default is 20 seconds. | | **Metadata Send Mode** | **Off — send only messages**, to keep Vapi call metadata out of requests to The Grid. | -Limits differ between instruments and change over time, so read them from `GET /v1/models` instead of copying numbers into your configuration. +Limits differ between instruments and change over time, so read them from [`GET https://api.thegrid.ai/v1/models`](https://api.thegrid.ai/v1/models) instead of copying numbers into your configuration. ## Tool calling