@mastra/mcp-docs-server 1.1.5 → 1.1.6-alpha.0

package/.docs/models/index.md

@@ -0,0 +1,286 @@
+# Model Providers
+
+Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 2436 models from 81 providers through a single API.
+
+## Features
+
+- **One API for any model** - Access any model without having to install and manage additional provider dependencies.
+
+- **Access the newest AI** - Use new models the moment they're released, no matter which provider they come from. Avoid vendor lock-in with Mastra's provider-agnostic interface.
+
+- [**Mix and match models**](#mix-and-match-models) - Use different models for different tasks. For example, run GPT-4o-mini for large-context processing, then switch to Claude Opus 4.1 for reasoning tasks.
+
+- [**Model fallbacks**](#model-fallbacks) - If a provider experiences an outage, Mastra can automatically switch to another provider at the application level, minimizing latency compared to API gateways.
+
+## Basic usage
+
+Whether you're using OpenAI, Anthropic, Google, or a gateway like OpenRouter, specify the model as `"provider/model-name"` and Mastra handles the rest.
+
+Mastra reads the relevant environment variable (e.g. `ANTHROPIC_API_KEY`) and routes requests to the provider. If an API key is missing, you'll get a clear runtime error showing exactly which variable to set.
+
+**OpenAI**:
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+
+const agent = new Agent({
+  id: "my-agent",
+  name: "My Agent",
+  instructions: "You are a helpful assistant",
+  model: "openai/gpt-5"
+})
+```
+
+**Anthropic**:
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+
+const agent = new Agent({
+  id: "my-agent",
+  name: "My Agent",
+  instructions: "You are a helpful assistant",
+  model: "anthropic/claude-4-5-sonnet"
+})
+```
+
+**Google Gemini**:
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+
+const agent = new Agent({
+  id: "my-agent",
+  name: "My Agent",
+  instructions: "You are a helpful assistant",
+  model: "google/gemini-2.5-flash"
+})
+```
+
+**xAI**:
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+
+const agent = new Agent({
+  id: "my-agent",
+  name: "My Agent",
+  instructions: "You are a helpful assistant",
+  model: "xai/grok-4"
+})
+```
+
+**OpenRouter**:
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+
+const agent = new Agent({
+  id: "my-agent",
+  name: "My Agent",
+  instructions: "You are a helpful assistant",
+  model: "openrouter/anthropic/claude-haiku-4-5"
+})
+```
+
+## Model directory
+
+Browse the directory of available models using the navigation on the left, or explore below.
+
+- [Gateways](https://mastra.ai/models/gateways)
+- [Providers](https://mastra.ai/models/providers)
+
+You can also discover models directly in your editor. Mastra provides full autocomplete for the `model` field - just start typing, and your IDE will show available options.
+
+Alternatively, browse and test models in [Studio](https://mastra.ai/docs/getting-started/studio) UI.
+
+> **Info:** In development, we auto-refresh your local model list every hour, ensuring your TypeScript autocomplete and Studio stay up-to-date with the latest models. To disable, set `MASTRA_AUTO_REFRESH_PROVIDERS=false`. Auto-refresh is disabled by default in production.
+
+## Mix and match models
+
+Some models are faster but less capable, while others offer larger context windows or stronger reasoning skills. Use different models from the same provider, or mix and match across providers to fit each task.
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+
+// Use a cost-effective model for document processing
+const documentProcessor = new Agent({
+  id: "document-processor",
+  name: "Document Processor",
+  instructions: "Extract and summarize key information from documents",
+  model: "openai/gpt-4o-mini"
+})
+
+// Use a powerful reasoning model for complex analysis
+const reasoningAgent = new Agent({
+  id: "reasoning-agent",
+  name: "Reasoning Agent",
+  instructions: "Analyze data and provide strategic recommendations",
+  model: "anthropic/claude-opus-4-1"
+})
+```
+
+## Dynamic model selection
+
+Since models are just strings, you can select them dynamically based on [request context](https://mastra.ai/docs/server/request-context), variables, or any other logic.
+
+```typescript
+const agent = new Agent({
+  id: "dynamic-assistant",
+  name: "Dynamic Assistant",
+  model: ({ requestContext }) => {
+    const provider = requestContext.get("provider-id");
+    const model = requestContext.get("model-id");
+    return `${provider}/${model}`;
+  },
+});
+```
+
+This enables powerful patterns:
+
+- A/B testing - Compare model performance in production.
+- User-selectable models - Let users choose their preferred model in your app.
+- Multi-tenant applications - Each customer can bring their own API keys and model preferences.
+
+## Provider-specific options
+
+Different model providers expose their own configuration options. With OpenAI, you might adjust the `reasoningEffort`. With Anthropic, you might tune `cacheControl`. Mastra lets you set these specific `providerOptions` either at the agent level or per message.
+
+```typescript
+// Agent level (apply to all future messages)
+const planner = new Agent({
+  id: "planner",
+  name: "Planner",
+  instructions: {
+    role: "system",
+    content: "You are a helpful assistant.",
+    providerOptions: {
+      openai: { reasoningEffort: "low" }
+    }
+  },
+  model: "openai/o3-pro",
+});
+
+const lowEffort =
+  await planner.generate("Plan a simple 3 item dinner menu");
+
+// Message level (apply only to this message)
+const highEffort = await planner.generate([
+  {
+    role: "user",
+    content: "Plan a simple 3 item dinner menu for a celiac",
+    providerOptions: {
+      openai: { reasoningEffort: "high" }
+    }
+  }
+]);
+```
+
+## Custom headers
+
+If you need to specify custom headers, such as an organization ID or other provider-specific fields, use this syntax.
+
+```typescript
+const agent = new Agent({
+  id: "custom-agent",
+  name: "Custom Agent",
+  model: {
+    id: "openai/gpt-4-turbo",
+    apiKey: process.env.OPENAI_API_KEY,
+    headers: {
+      "OpenAI-Organization": "org-abc123"
+    }
+  }
+});
+```
+
+> **Info:** Configuration differs by provider. See the provider pages in the left navigation for details on custom headers.
+
+## Model fallbacks
+
+Relying on a single model creates a single point of failure for your application. Model fallbacks provide automatic failover between models and providers. If the primary model becomes unavailable, requests are retried against the next configured fallback until one succeeds.
+
+```typescript
+import { Agent } from '@mastra/core/agent';
+
+const agent = new Agent({
+  id: 'resilient-assistant',
+  name: 'Resilient Assistant',
+  instructions: 'You are a helpful assistant.',
+  model: [
+    {
+      model: "openai/gpt-5",
+      maxRetries: 3,
+    },
+    {
+      model: "anthropic/claude-4-5-sonnet",
+      maxRetries: 2,
+    },
+    {
+      model: "google/gemini-2.5-pro",
+      maxRetries: 2,
+    },
+  ],
+});
+```
+
+Mastra tries your primary model first. If it encounters a 500 error, rate limit, or timeout, it automatically switches to your first fallback. If that fails too, it moves to the next. Each model gets its own retry count before moving on.
+
+Your users never experience the disruption - the response comes back with the same format, just from a different model. The error context is preserved as the system moves through your fallback chain, ensuring clean error propagation while maintaining streaming compatibility.
+
+## Use local models with Mastra
+
+Mastra also supports local models like `gpt-oss`, `Qwen3`, `DeepSeek` and many more that you run on your own hardware. The application running your local model needs to provide an OpenAI-compatible API server for Mastra to connect to. We recommend using [LMStudio](https://lmstudio.ai/) (see [Running the LMStudio server](https://lmstudio.ai/docs/developer/core/server)).
+
+For a custom provider the `id` (`${providerId}/${modelId}`) is required but it will only be used for display purposes. The `modelId` needs to be the actual model you want to use. An example would be: `custom/my-qwen3-model`.
+
+For the `url` it's **important** that you use the base URL of the OpenAI-compatible endpoint with Mastra's `model` setting and not the individual chat endpoints.
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+
+const agent = new Agent({
+  id: "my-agent",
+  name: "My Agent",
+  instructions: "You are a helpful assistant",
+  model: {
+    id: "custom/my-qwen3-model",
+    url: "http://your-custom-openai-compatible-endpoint.com/v1"
+  }
+})
+```
+
+### Example: LMStudio
+
+After starting the LMStudio server, the local server is available at `http://localhost:1234` and it provides endpoints like `/v1/models`, `/v1/chat/completions`, etc. The `url` will be `http://localhost:1234/v1`. For the `id` you can use (`lmstudio/${modelId}`) which will be displayed in the LMStudio interface.
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+
+const agent = new Agent({
+  id: "my-agent",
+  name: "My Agent",
+  instructions: "You are a helpful assistant",
+  model: {
+    id: "lmstudio/qwen/qwen3-30b-a3b-2507",
+    url: "http://localhost:1234/v1"
+  }
+})
+```
+
+## Use AI SDK with Mastra
+
+Mastra supports AI SDK provider modules, should you need to use them directly.
+
+```typescript
+import { groq } from '@ai-sdk/groq';
+import { Agent } from "@mastra/core/agent";
+
+const agent = new Agent({
+  id: "my-agent",
+  name: "My Agent",
+  model: groq('gemma2-9b-it')
+})
+```
+
+You can use an AI SDK model (e.g. `groq('gemma2-9b-it')`) anywhere that accepts a `"provider/model"` string, including within model router fallbacks and [scorers](https://mastra.ai/docs/evals/overview).

package/.docs/models/providers/302ai.md

@@ -0,0 +1,134 @@
+# ![302.AI logo](https://models.dev/logos/302ai.svg)302.AI
+
+Access 64 302.AI models through Mastra's model router. Authentication is handled automatically using the `302AI_API_KEY` environment variable.
+
+Learn more in the [302.AI documentation](https://doc.302.ai).
+
+```bash
+302AI_API_KEY=your-api-key
+```
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+
+const agent = new Agent({
+  id: "my-agent",
+  name: "My Agent",
+  instructions: "You are a helpful assistant",
+  model: "302ai/MiniMax-M1"
+});
+
+// Generate a response
+const response = await agent.generate("Hello!");
+
+// Stream a response
+const stream = await agent.stream("Tell me a story");
+for await (const chunk of stream) {
+  console.log(chunk);
+}
+```
+
+> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [302.AI documentation](https://doc.302.ai) for details.
+
+## Models
+
+| Model                                         | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
+| --------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
+| `302ai/chatgpt-4o-latest`                     | 128K    |       |           |       |       |       | $5         | $15         |
+| `302ai/claude-haiku-4-5-20251001`             | 200K    |       |           |       |       |       | $1         | $5          |
+| `302ai/claude-opus-4-1-20250805`              | 200K    |       |           |       |       |       | $15        | $75         |
+| `302ai/claude-opus-4-1-20250805-thinking`     | 200K    |       |           |       |       |       | $15        | $75         |
+| `302ai/claude-opus-4-5-20251101`              | 200K    |       |           |       |       |       | $5         | $25         |
+| `302ai/claude-opus-4-5-20251101-thinking`     | 200K    |       |           |       |       |       | $5         | $25         |
+| `302ai/claude-sonnet-4-5-20250929`            | 200K    |       |           |       |       |       | $3         | $15         |
+| `302ai/claude-sonnet-4-5-20250929-thinking`   | 200K    |       |           |       |       |       | $3         | $15         |
+| `302ai/deepseek-chat`                         | 128K    |       |           |       |       |       | $0.29      | $0.43       |
+| `302ai/deepseek-reasoner`                     | 128K    |       |           |       |       |       | $0.29      | $0.43       |
+| `302ai/deepseek-v3.2`                         | 128K    |       |           |       |       |       | $0.29      | $0.43       |
+| `302ai/deepseek-v3.2-thinking`                | 128K    |       |           |       |       |       | $0.29      | $0.43       |
+| `302ai/doubao-seed-1-6-thinking-250715`       | 256K    |       |           |       |       |       | $0.12      | $1          |
+| `302ai/doubao-seed-1-6-vision-250815`         | 256K    |       |           |       |       |       | $0.11      | $1          |
+| `302ai/doubao-seed-1-8-251215`                | 224K    |       |           |       |       |       | $0.11      | $0.29       |
+| `302ai/doubao-seed-code-preview-251028`       | 256K    |       |           |       |       |       | $0.17      | $1          |
+| `302ai/gemini-2.0-flash-lite`                 | 2.0M    |       |           |       |       |       | $0.07      | $0.30       |
+| `302ai/gemini-2.5-flash`                      | 1.0M    |       |           |       |       |       | $0.30      | $3          |
+| `302ai/gemini-2.5-flash-image`                | 33K     |       |           |       |       |       | $0.30      | $30         |
+| `302ai/gemini-2.5-flash-lite-preview-09-2025` | 1.0M    |       |           |       |       |       | $0.10      | $0.40       |
+| `302ai/gemini-2.5-flash-nothink`              | 1.0M    |       |           |       |       |       | $0.30      | $3          |
+| `302ai/gemini-2.5-flash-preview-09-2025`      | 1.0M    |       |           |       |       |       | $0.30      | $3          |
+| `302ai/gemini-2.5-pro`                        | 1.0M    |       |           |       |       |       | $1         | $10         |
+| `302ai/gemini-3-flash-preview`                | 1.0M    |       |           |       |       |       | $0.50      | $3          |
+| `302ai/gemini-3-pro-image-preview`            | 33K     |       |           |       |       |       | $2         | $120        |
+| `302ai/gemini-3-pro-preview`                  | 1.0M    |       |           |       |       |       | $2         | $12         |
+| `302ai/glm-4.5`                               | 128K    |       |           |       |       |       | $0.29      | $1          |
+| `302ai/glm-4.5v`                              | 64K     |       |           |       |       |       | $0.29      | $0.86       |
+| `302ai/glm-4.6`                               | 200K    |       |           |       |       |       | $0.29      | $1          |
+| `302ai/glm-4.6v`                              | 128K    |       |           |       |       |       | $0.14      | $0.43       |
+| `302ai/glm-4.7`                               | 200K    |       |           |       |       |       | $0.29      | $1          |
+| `302ai/gpt-4.1`                               | 1.0M    |       |           |       |       |       | $2         | $8          |
+| `302ai/gpt-4.1-mini`                          | 1.0M    |       |           |       |       |       | $0.40      | $2          |
+| `302ai/gpt-4.1-nano`                          | 1.0M    |       |           |       |       |       | $0.10      | $0.40       |
+| `302ai/gpt-4o`                                | 128K    |       |           |       |       |       | $3         | $10         |
+| `302ai/gpt-5`                                 | 400K    |       |           |       |       |       | $1         | $10         |
+| `302ai/gpt-5-mini`                            | 400K    |       |           |       |       |       | $0.25      | $2          |
+| `302ai/gpt-5-pro`                             | 400K    |       |           |       |       |       | $15        | $120        |
+| `302ai/gpt-5-thinking`                        | 400K    |       |           |       |       |       | $1         | $10         |
+| `302ai/gpt-5.1`                               | 400K    |       |           |       |       |       | $1         | $10         |
+| `302ai/gpt-5.1-chat-latest`                   | 128K    |       |           |       |       |       | $1         | $10         |
+| `302ai/gpt-5.2`                               | 400K    |       |           |       |       |       | $2         | $14         |
+| `302ai/gpt-5.2-chat-latest`                   | 128K    |       |           |       |       |       | $2         | $14         |
+| `302ai/grok-4-1-fast-non-reasoning`           | 2.0M    |       |           |       |       |       | $0.20      | $0.50       |
+| `302ai/grok-4-1-fast-reasoning`               | 2.0M    |       |           |       |       |       | $0.20      | $0.50       |
+| `302ai/grok-4-fast-non-reasoning`             | 2.0M    |       |           |       |       |       | $0.20      | $0.50       |
+| `302ai/grok-4-fast-reasoning`                 | 2.0M    |       |           |       |       |       | $0.20      | $0.50       |
+| `302ai/grok-4.1`                              | 200K    |       |           |       |       |       | $2         | $10         |
+| `302ai/kimi-k2-0905-preview`                  | 262K    |       |           |       |       |       | $0.63      | $3          |
+| `302ai/kimi-k2-thinking`                      | 262K    |       |           |       |       |       | $0.57      | $2          |
+| `302ai/kimi-k2-thinking-turbo`                | 262K    |       |           |       |       |       | $1         | $9          |
+| `302ai/MiniMax-M1`                            | 1.0M    |       |           |       |       |       | $0.13      | $1          |
+| `302ai/MiniMax-M2`                            | 1.0M    |       |           |       |       |       | $0.33      | $1          |
+| `302ai/MiniMax-M2.1`                          | 1.0M    |       |           |       |       |       | $0.30      | $1          |
+| `302ai/ministral-14b-2512`                    | 128K    |       |           |       |       |       | $0.33      | $0.33       |
+| `302ai/mistral-large-2512`                    | 128K    |       |           |       |       |       | $1         | $3          |
+| `302ai/qwen-flash`                            | 1.0M    |       |           |       |       |       | $0.02      | $0.22       |
+| `302ai/qwen-max-latest`                       | 131K    |       |           |       |       |       | $0.34      | $1          |
+| `302ai/qwen-plus`                             | 1.0M    |       |           |       |       |       | $0.12      | $1          |
+| `302ai/qwen3-235b-a22b`                       | 128K    |       |           |       |       |       | $0.29      | $3          |
+| `302ai/qwen3-235b-a22b-instruct-2507`         | 128K    |       |           |       |       |       | $0.29      | $1          |
+| `302ai/qwen3-30b-a3b`                         | 128K    |       |           |       |       |       | $0.11      | $1          |
+| `302ai/qwen3-coder-480b-a35b-instruct`        | 262K    |       |           |       |       |       | $0.86      | $3          |
+| `302ai/qwen3-max-2025-09-23`                  | 258K    |       |           |       |       |       | $0.86      | $3          |
+
+## Advanced Configuration
+
+### Custom Headers
+
+```typescript
+const agent = new Agent({
+  id: "custom-agent",
+  name: "custom-agent",
+  model: {
+    url: "https://api.302.ai/v1",
+    id: "302ai/MiniMax-M1",
+    apiKey: process.env.302AI_API_KEY,
+    headers: {
+      "X-Custom-Header": "value"
+    }
+  }
+});
+```
+
+### Dynamic Model Selection
+
+```typescript
+const agent = new Agent({
+  id: "dynamic-agent",
+  name: "Dynamic Agent",
+  model: ({ requestContext }) => {
+    const useAdvanced = requestContext.task === "complex";
+    return useAdvanced
+      ? "302ai/qwen3-max-2025-09-23"
+      : "302ai/MiniMax-M1";
+  }
+});
+```

package/.docs/models/providers/abacus.md

@@ -0,0 +1,125 @@
+# ![Abacus logo](https://models.dev/logos/abacus.svg)Abacus
+
+Access 55 Abacus models through Mastra's model router. Authentication is handled automatically using the `ABACUS_API_KEY` environment variable.
+
+Learn more in the [Abacus documentation](https://abacus.ai).
+
+```bash
+ABACUS_API_KEY=your-api-key
+```
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+
+const agent = new Agent({
+  id: "my-agent",
+  name: "My Agent",
+  instructions: "You are a helpful assistant",
+  model: "abacus/Qwen/QwQ-32B"
+});
+
+// Generate a response
+const response = await agent.generate("Hello!");
+
+// Stream a response
+const stream = await agent.stream("Tell me a story");
+for await (const chunk of stream) {
+  console.log(chunk);
+}
+```
+
+> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Abacus documentation](https://abacus.ai) for details.
+
+## Models
+
+| Model                                                      | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
+| ---------------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
+| `abacus/claude-3-7-sonnet-20250219`                        | 200K    |       |           |       |       |       | $3         | $15         |
+| `abacus/claude-haiku-4-5-20251001`                         | 200K    |       |           |       |       |       | $1         | $5          |
+| `abacus/claude-opus-4-1-20250805`                          | 200K    |       |           |       |       |       | $15        | $75         |
+| `abacus/claude-opus-4-20250514`                            | 200K    |       |           |       |       |       | $15        | $75         |
+| `abacus/claude-opus-4-5-20251101`                          | 200K    |       |           |       |       |       | $5         | $25         |
+| `abacus/claude-sonnet-4-20250514`                          | 200K    |       |           |       |       |       | $3         | $15         |
+| `abacus/claude-sonnet-4-5-20250929`                        | 200K    |       |           |       |       |       | $3         | $15         |
+| `abacus/deepseek-ai/DeepSeek-R1`                           | 128K    |       |           |       |       |       | $3         | $7          |
+| `abacus/deepseek-ai/DeepSeek-V3.1-Terminus`                | 128K    |       |           |       |       |       | $0.27      | $1          |
+| `abacus/deepseek-ai/DeepSeek-V3.2`                         | 128K    |       |           |       |       |       | $0.27      | $0.40       |
+| `abacus/deepseek/deepseek-v3.1`                            | 128K    |       |           |       |       |       | $0.14      | $0.28       |
+| `abacus/gemini-2.0-flash-001`                              | 1.0M    |       |           |       |       |       | $0.10      | $0.40       |
+| `abacus/gemini-2.0-pro-exp-02-05`                          | 2.0M    |       |           |       |       |       | —          | —           |
+| `abacus/gemini-2.5-flash`                                  | 1.0M    |       |           |       |       |       | $0.30      | $3          |
+| `abacus/gemini-2.5-pro`                                    | 1.0M    |       |           |       |       |       | $1         | $10         |
+| `abacus/gemini-3-flash-preview`                            | 1.0M    |       |           |       |       |       | $0.50      | $3          |
+| `abacus/gemini-3-pro-preview`                              | 1.0M    |       |           |       |       |       | $2         | $12         |
+| `abacus/gpt-4.1`                                           | 1.0M    |       |           |       |       |       | $2         | $8          |
+| `abacus/gpt-4.1-mini`                                      | 1.0M    |       |           |       |       |       | $0.40      | $2          |
+| `abacus/gpt-4.1-nano`                                      | 1.0M    |       |           |       |       |       | $0.10      | $0.40       |
+| `abacus/gpt-4o-2024-11-20`                                 | 128K    |       |           |       |       |       | $3         | $10         |
+| `abacus/gpt-4o-mini`                                       | 128K    |       |           |       |       |       | $0.15      | $0.60       |
+| `abacus/gpt-5`                                             | 400K    |       |           |       |       |       | $1         | $10         |
+| `abacus/gpt-5-mini`                                        | 400K    |       |           |       |       |       | $0.25      | $2          |
+| `abacus/gpt-5-nano`                                        | 400K    |       |           |       |       |       | $0.05      | $0.40       |
+| `abacus/gpt-5.1`                                           | 400K    |       |           |       |       |       | $1         | $10         |
+| `abacus/gpt-5.1-chat-latest`                               | 400K    |       |           |       |       |       | $1         | $10         |
+| `abacus/gpt-5.2`                                           | 400K    |       |           |       |       |       | $2         | $14         |
+| `abacus/gpt-5.2-chat-latest`                               | 400K    |       |           |       |       |       | $2         | $12         |
+| `abacus/grok-4-0709`                                       | 256K    |       |           |       |       |       | $3         | $15         |
+| `abacus/grok-4-1-fast-non-reasoning`                       | 2.0M    |       |           |       |       |       | $0.20      | $0.50       |
+| `abacus/grok-4-fast-non-reasoning`                         | 2.0M    |       |           |       |       |       | $0.20      | $0.50       |
+| `abacus/grok-code-fast-1`                                  | 256K    |       |           |       |       |       | $0.20      | $2          |
+| `abacus/kimi-k2-turbo-preview`                             | 256K    |       |           |       |       |       | $0.15      | $8          |
+| `abacus/llama-3.3-70b-versatile`                           | 128K    |       |           |       |       |       | $0.59      | $0.79       |
+| `abacus/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8` | 1.0M    |       |           |       |       |       | $0.14      | $0.59       |
+| `abacus/meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo`     | 128K    |       |           |       |       |       | $4         | $4          |
+| `abacus/meta-llama/Meta-Llama-3.1-70B-Instruct`            | 128K    |       |           |       |       |       | $0.40      | $0.40       |
+| `abacus/meta-llama/Meta-Llama-3.1-8B-Instruct`             | 128K    |       |           |       |       |       | $0.02      | $0.05       |
+| `abacus/o3`                                                | 200K    |       |           |       |       |       | $2         | $8          |
+| `abacus/o3-mini`                                           | 200K    |       |           |       |       |       | $1         | $4          |
+| `abacus/o3-pro`                                            | 200K    |       |           |       |       |       | $20        | $80         |
+| `abacus/o4-mini`                                           | 200K    |       |           |       |       |       | $1         | $4          |
+| `abacus/openai/gpt-oss-120b`                               | 128K    |       |           |       |       |       | $0.08      | $0.44       |
+| `abacus/qwen-2.5-coder-32b`                                | 128K    |       |           |       |       |       | $0.79      | $0.79       |
+| `abacus/Qwen/Qwen2.5-72B-Instruct`                         | 128K    |       |           |       |       |       | $0.11      | $0.38       |
+| `abacus/Qwen/Qwen3-235B-A22B-Instruct-2507`                | 262K    |       |           |       |       |       | $0.13      | $0.60       |
+| `abacus/Qwen/Qwen3-32B`                                    | 128K    |       |           |       |       |       | $0.09      | $0.29       |
+| `abacus/Qwen/qwen3-coder-480b-a35b-instruct`               | 262K    |       |           |       |       |       | $0.29      | $1          |
+| `abacus/Qwen/QwQ-32B`                                      | 33K     |       |           |       |       |       | $0.40      | $0.40       |
+| `abacus/qwen3-max`                                         | 131K    |       |           |       |       |       | $1         | $6          |
+| `abacus/route-llm`                                         | 128K    |       |           |       |       |       | $0.50      | $2          |
+| `abacus/zai-org/glm-4.5`                                   | 128K    |       |           |       |       |       | $0.60      | $2          |
+| `abacus/zai-org/glm-4.6`                                   | 128K    |       |           |       |       |       | $0.60      | $2          |
+| `abacus/zai-org/glm-4.7`                                   | 128K    |       |           |       |       |       | $0.70      | $3          |
+
+## Advanced Configuration
+
+### Custom Headers
+
+```typescript
+const agent = new Agent({
+  id: "custom-agent",
+  name: "custom-agent",
+  model: {
+    url: "https://routellm.abacus.ai/v1",
+    id: "abacus/Qwen/QwQ-32B",
+    apiKey: process.env.ABACUS_API_KEY,
+    headers: {
+      "X-Custom-Header": "value"
+    }
+  }
+});
+```
+
+### Dynamic Model Selection
+
+```typescript
+const agent = new Agent({
+  id: "dynamic-agent",
+  name: "Dynamic Agent",
+  model: ({ requestContext }) => {
+    const useAdvanced = requestContext.task === "complex";
+    return useAdvanced
+      ? "abacus/zai-org/glm-4.7"
+      : "abacus/Qwen/QwQ-32B";
+  }
+});
+```

package/.docs/models/providers/agentrouter.md

@@ -0,0 +1,90 @@
+# ![AgentRouter logo](https://models.dev/logos/agentrouter.svg)AgentRouter
+
+Access 20 AgentRouter models through Mastra's model router. Authentication is handled automatically using the `AGENTROUTER_API_KEY` environment variable.
+
+Learn more in the [AgentRouter documentation](https://docs.agentrouter.org).
+
+```bash
+AGENTROUTER_API_KEY=your-api-key
+```
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+
+const agent = new Agent({
+  id: "my-agent",
+  name: "My Agent",
+  instructions: "You are a helpful assistant",
+  model: "agentrouter/claude-3-5-haiku-20241022"
+});
+
+// Generate a response
+const response = await agent.generate("Hello!");
+
+// Stream a response
+const stream = await agent.stream("Tell me a story");
+for await (const chunk of stream) {
+  console.log(chunk);
+}
+```
+
+> **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [AgentRouter documentation](https://docs.agentrouter.org) for details.
+
+## Models
+
+| Model                                             | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
+| ------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
+| `agentrouter/claude-3-5-haiku-20241022`           | 200K    |       |           |       |       |       | $1         | $5          |
+| `agentrouter/claude-3-5-sonnet-20240620`          | 200K    |       |           |       |       |       | $3         | $15         |
+| `agentrouter/claude-3-5-sonnet-20241022`          | 200K    |       |           |       |       |       | $3         | $15         |
+| `agentrouter/claude-3-7-sonnet-20250219`          | 200K    |       |           |       |       |       | $3         | $15         |
+| `agentrouter/claude-3-7-sonnet-20250219-thinking` | 200K    |       |           |       |       |       | $3         | $15         |
+| `agentrouter/claude-haiku-4-5-20251001`           | 200K    |       |           |       |       |       | $2         | $4          |
+| `agentrouter/claude-opus-4-20250514`              | 200K    |       |           |       |       |       | $21        | $105        |
+| `agentrouter/claude-opus-4-20250514-thinking`     | 200K    |       |           |       |       |       | $2         | $10         |
+| `agentrouter/claude-sonnet-4-20250514`            | 200K    |       |           |       |       |       | $3         | $15         |
+| `agentrouter/claude-sonnet-4-20250514-thinking`   | 200K    |       |           |       |       |       | $2         | $10         |
+| `agentrouter/claude-sonnet-4-5-20250929`          | 1.0M    |       |           |       |       |       | $6         | $30         |
+| `agentrouter/deepseek-r1-0528`                    | 128K    |       |           |       |       |       | $0.30      | $0.04       |
+| `agentrouter/deepseek-v3.1`                       | 128K    |       |           |       |       |       | $0.30      | $0.04       |
+| `agentrouter/deepseek-v3.2`                       | 128K    |       |           |       |       |       | $0.30      | $0.04       |
+| `agentrouter/gemini-3-pro-preview`                | 1.0M    |       |           |       |       |       | $2         | $8          |
+| `agentrouter/glm-4.5`                             | 131K    |       |           |       |       |       | $0.00      | —           |
+| `agentrouter/glm-4.6`                             | 205K    |       |           |       |       |       | $0.00      | —           |
+| `agentrouter/gpt-5`                               | 1.3M    |       |           |       |       |       | —          | —           |
+| `agentrouter/gpt-5.1`                             | 400K    |       |           |       |       |       | $2         | $2          |
+| `agentrouter/kimi-k2-thinking`                    | 262K    |       |           |       |       |       | $0.00      | —           |
+
+## Advanced Configuration
+
+### Custom Headers
+
+```typescript
+const agent = new Agent({
+  id: "custom-agent",
+  name: "custom-agent",
+  model: {
+    url: "https://agentrouter.org/v1",
+    id: "agentrouter/claude-3-5-haiku-20241022",
+    apiKey: process.env.AGENTROUTER_API_KEY,
+    headers: {
+      "X-Custom-Header": "value"
+    }
+  }
+});
+```
+
+### Dynamic Model Selection
+
+```typescript
+const agent = new Agent({
+  id: "dynamic-agent",
+  name: "Dynamic Agent",
+  model: ({ requestContext }) => {
+    const useAdvanced = requestContext.task === "complex";
+    return useAdvanced
+      ? "agentrouter/kimi-k2-thinking"
+      : "agentrouter/claude-3-5-haiku-20241022";
+  }
+});
+```