@mastra/mcp-docs-server 1.1.35-alpha.2 → 1.1.35-alpha.21

package/.docs/guides/deployment/inngest.md

@@ -21,27 +21,29 @@ Install the required packages:
 **npm**:
 
 ```bash
-npm install @mastra/inngest@latest inngest @inngest/realtime
+npm install @mastra/inngest@latest inngest
 ```
 
 **pnpm**:
 
 ```bash
-pnpm add @mastra/inngest@latest inngest @inngest/realtime
+pnpm add @mastra/inngest@latest inngest
 ```
 
 **Yarn**:
 
 ```bash
-yarn add @mastra/inngest@latest inngest @inngest/realtime
+yarn add @mastra/inngest@latest inngest
 ```
 
 **Bun**:
 
 ```bash
-bun add @mastra/inngest@latest inngest @inngest/realtime
+bun add @mastra/inngest@latest inngest
 ```
 
+> **Note:** Requires `inngest@^4` and Inngest Dev Server `v1.18.0` or later. Realtime is built into the SDK in v4, so `@inngest/realtime` and `realtimeMiddleware` are no longer used.
+
 ## Building an Inngest workflow
 
 This guide walks through creating a workflow with Inngest and Mastra, demonstrating a counter application that increments a value until it reaches 10.
@@ -54,13 +56,11 @@ In development:
 
 ```ts
 import { Inngest } from 'inngest'
-import { realtimeMiddleware } from '@inngest/realtime/middleware'
 
 export const inngest = new Inngest({
   id: 'mastra',
   baseUrl: 'http://localhost:8288',
   isDev: true,
-  middleware: [realtimeMiddleware()],
 })
 ```
 
@@ -68,14 +68,35 @@ In production:
 
 ```ts
 import { Inngest } from 'inngest'
-import { realtimeMiddleware } from '@inngest/realtime/middleware'
 
 export const inngest = new Inngest({
   id: 'mastra',
-  middleware: [realtimeMiddleware()],
 })
 ```
 
+#### Selecting dev or cloud mode with `INNGEST_DEV`
+
+The Inngest SDK runs in one of two modes: dev or cloud. From v4 onward, the SDK defaults to cloud mode and requires `INNGEST_EVENT_KEY` and `INNGEST_SIGNING_KEY`. The examples above set the mode in code with `isDev: true`. As an alternative, set the [`INNGEST_DEV` environment variable](https://www.inngest.com/docs/sdk/environment-variables#inngest-dev) so the same client code works across environments:
+
+- `INNGEST_DEV=1`: force dev mode. The SDK talks to a local Inngest Dev Server and disables signature verification.
+- `INNGEST_DEV=0`: force cloud mode. The SDK talks to Inngest Cloud and requires event and signing keys.
+- `INNGEST_DEV=<url>`: force dev mode and point the SDK at the Dev Server at `<url>`, for example `http://localhost:8288`.
+- Unset: defaults to cloud mode.
+
+When `INNGEST_DEV` is set, you can drop `isDev` and `baseUrl` from the client:
+
+```ts
+import { Inngest } from 'inngest'
+
+export const inngest = new Inngest({
+  id: 'mastra',
+})
+```
+
+> **Warning:** Do not set `INNGEST_DEV` in production. It disables signature verification, which is required to securely receive events from Inngest Cloud.
+
+The `isDev` option on `new Inngest()` overrides `INNGEST_DEV` when both are set.
+
 ### Creating steps
 
 Define the individual steps that will compose your workflow:

package/.docs/guides/guide/web-search.md

@@ -17,7 +17,7 @@ Some LLM providers include built-in web search capabilities that can be used dir
 
 1. Install dependencies
 
-   **Open AI**:
+   **OpenAI**:
 
    **npm**:
 
@@ -119,7 +119,7 @@ Some LLM providers include built-in web search capabilities that can be used dir
 
 2. Create a new file `src/mastra/agents/searchAgent.ts` and define your agent:
 
-   **Open AI**:
+   **OpenAI**:
 
    ```ts
    import { Agent } from '@mastra/core/agent'
@@ -128,7 +128,7 @@ Some LLM providers include built-in web search capabilities that can be used dir
      id: 'search-agent',
      name: 'Search Agent',
      instructions: 'You are a search agent that can search the web for information.',
-     model: 'openai/gpt-5.4',
+     model: 'openai/gpt-5.5',
    })
    ```
 
@@ -147,7 +147,7 @@ Some LLM providers include built-in web search capabilities that can be used dir
 
 3. Setup the tool:
 
-   **Open AI**:
+   **OpenAI**:
 
    ```ts
    import { openai } from '@ai-sdk/openai'
@@ -157,7 +157,7 @@ Some LLM providers include built-in web search capabilities that can be used dir
      id: 'search-agent',
      name: 'Search Agent',
      instructions: 'You are a search agent that can search the web for information.',
-     model: 'openai/gpt-5.4',
+     model: 'openai/gpt-5.5',
      tools: {
        webSearch: openai.tools.webSearch(),
      },
@@ -241,7 +241,7 @@ For more control over search behavior, you can integrate external search APIs as
      id: 'search-agent',
      name: 'Search Agent',
      instructions: 'You are a search agent that can search the web for information.',
-     model: 'openai/gpt-5.4',
+     model: 'openai/gpt-5.5',
    })
    ```
 
@@ -293,7 +293,7 @@ For more control over search behavior, you can integrate external search APIs as
      id: 'search-agent',
      name: 'Search Agent',
      instructions: 'You are a search agent that can search the web for information.',
-     model: 'openai/gpt-5.4',
+     model: 'openai/gpt-5.5',
      tools: {
        webSearch,
      },

package/.docs/guides/migrations/mastra-cloud.md

@@ -235,8 +235,8 @@ export const mastra = new Mastra({
 import { Mastra } from '@mastra/core/mastra'
 import {
   Observability,
-  DefaultExporter,
-  CloudExporter,
+  MastraStorageExporter,
+  MastraPlatformExporter,
   SensitiveDataFilter,
 } from '@mastra/observability'
 
@@ -245,7 +245,7 @@ export const mastra = new Mastra({
     configs: {
       default: {
         serviceName: 'my-app',
-        exporters: [new DefaultExporter(), new CloudExporter()],
+        exporters: [new MastraStorageExporter(), new MastraPlatformExporter()],
         spanOutputProcessors: [new SensitiveDataFilter()],
       },
     },
@@ -253,8 +253,8 @@ export const mastra = new Mastra({
 })
 ```
 
-- `DefaultExporter` persists traces to your storage backend for [Studio](https://mastra.ai/docs/studio/observability).
-- `CloudExporter` Sends observability data to hosted Mastra Studio when `MASTRA_CLOUD_ACCESS_TOKEN` is set.
+- `MastraStorageExporter` persists observability events to Mastra Storage for [Studio](https://mastra.ai/docs/studio/observability).
+- `MastraPlatformExporter` sends observability events to Mastra Platform when `MASTRA_CLOUD_ACCESS_TOKEN` is set.
 - `SensitiveDataFilter` redacts passwords, tokens, and keys from span data before export.
 
 See the [observability overview](https://mastra.ai/docs/observability/overview) for the full configuration, including composite storage with DuckDB for metrics.
@@ -295,7 +295,7 @@ MASTRA_PROJECT_ID="<staging-id>" mastra studio deploy --env-file .env.staging --
 MASTRA_PROJECT_ID="<production-id>" mastra studio deploy --env-file .env.production --yes
 ```
 
-Each environment ends up with its own Studio URL and its own observability data. Send `MASTRA_CLOUD_ACCESS_TOKEN` and `MASTRA_PROJECT_ID` per environment so `CloudExporter` routes traces to the correct project.
+Each environment ends up with its own Studio URL and its own observability data. Send `MASTRA_CLOUD_ACCESS_TOKEN` and `MASTRA_PROJECT_ID` per environment so `MastraPlatformExporter` routes traces to the correct project.
 
 ## Deploy Server (optional)
 

package/.docs/guides/migrations/upgrade-to-v1/tracing.md

@@ -4,7 +4,9 @@ The observability system has been restructured in v1 with a dedicated `@mastra/o
 
 > **Observability data stops flowing on upgrade:** If you upgrade Mastra packages to v1 without migrating your `telemetry:` config to `observability:`, the old config is ignored at runtime. Your service will start cleanly with no error, but **no traces, logs, or metrics will be sent anywhere**. If you were sending data to Mastra Cloud, the dashboard will go empty.
 >
-> Complete this migration in the same change that bumps your Mastra packages, and verify traces appear in [Mastra Studio](https://mastra.ai/docs/studio/observability) before considering the upgrade complete. If you previously hosted on Mastra Cloud, also follow the [Mastra Cloud migration guide](https://mastra.ai/guides/migrations/mastra-cloud) — the new platform requires a new access token and a Studio project before `CloudExporter` can route data to it.
+> Complete this migration in the same change that bumps your Mastra packages, and verify traces appear in [Mastra Studio](https://mastra.ai/docs/studio/observability) before considering the upgrade complete. If you previously hosted on Mastra Cloud, also follow the [Mastra Cloud migration guide](https://mastra.ai/guides/migrations/mastra-cloud) — the new platform requires a new access token and a Studio project before `MastraPlatformExporter` can route data to it.
+
+> **Exporter rename:** `MastraPlatformExporter` (sends data to Mastra Platform) replaces the previous `CloudExporter`, and `MastraStorageExporter` (persists data to Mastra Storage) replaces the previous `DefaultExporter`. The original classes still ship from `@mastra/observability` and behave identically, but they are deprecated. New code should use `MastraPlatformExporter` and `MastraStorageExporter`; existing imports of `CloudExporter`/`DefaultExporter` continue to work until they are removed in a future major version.
 
 ## Migration paths
 
@@ -38,8 +40,8 @@ export const mastra = new Mastra({
 import { Mastra } from '@mastra/core'
 import {
   Observability,
-  DefaultExporter,
-  CloudExporter,
+  MastraStorageExporter,
+  MastraPlatformExporter,
   SensitiveDataFilter,
 } from '@mastra/observability'
 
@@ -49,8 +51,8 @@ export const mastra = new Mastra({
       default: {
         serviceName: 'mastra',
         exporters: [
-          new DefaultExporter(), // Persists traces to storage for Studio
-          new CloudExporter(), // Sends observability data to hosted Mastra Studio (if MASTRA_CLOUD_ACCESS_TOKEN is set)
+          new MastraStorageExporter(), // Persists observability events to Mastra Storage
+          new MastraPlatformExporter(), // Sends observability events to Mastra Platform (if MASTRA_CLOUD_ACCESS_TOKEN is set)
         ],
         spanOutputProcessors: [
           new SensitiveDataFilter(), // Redacts sensitive data like passwords, tokens, keys
@@ -61,7 +63,7 @@ export const mastra = new Mastra({
 })
 ```
 
-This configuration includes `DefaultExporter`, `CloudExporter`, and `SensitiveDataFilter` processor. See the [observability tracing documentation](https://mastra.ai/docs/observability/tracing/overview) for full configuration options.
+This configuration includes `MastraStorageExporter`, `MastraPlatformExporter`, and `SensitiveDataFilter` processor. See the [observability tracing documentation](https://mastra.ai/docs/observability/tracing/overview) for full configuration options.
 
 #### After (v1 with custom configuration)
 
@@ -122,7 +124,7 @@ Key changes:
 
 1. Install `@mastra/observability` package
 2. Replace `telemetry:` with `observability: new Observability()`
-3. Use explicit `configs:` with `DefaultExporter`, `CloudExporter`, and `SensitiveDataFilter`
+3. Use explicit `configs:` with `MastraStorageExporter`, `MastraPlatformExporter`, and `SensitiveDataFilter`
 4. Export types change from string literals (`'otlp'`) to exporter class instances (`new OtelExporter()`)
 
 See the [exporters documentation](https://mastra.ai/docs/observability/tracing/overview) for all available exporters.
@@ -149,8 +151,8 @@ export const mastra = new Mastra({
 import { Mastra } from '@mastra/core'
 import {
   Observability,
-  DefaultExporter,
-  CloudExporter,
+  MastraStorageExporter,
+  MastraPlatformExporter,
   SensitiveDataFilter,
 } from '@mastra/observability'
 
@@ -159,7 +161,7 @@ export const mastra = new Mastra({
     configs: {
       default: {
         serviceName: 'mastra',
-        exporters: [new DefaultExporter(), new CloudExporter()],
+        exporters: [new MastraStorageExporter(), new MastraPlatformExporter()],
         spanOutputProcessors: [new SensitiveDataFilter()],
       },
     },
@@ -171,7 +173,7 @@ Key changes:
 
 1. Install `@mastra/observability` package
 2. Import `Observability`, exporters, and processors from `@mastra/observability`
-3. Use explicit `configs` with `DefaultExporter`, `CloudExporter`, and `SensitiveDataFilter`
+3. Use explicit `configs` with `MastraStorageExporter`, `MastraPlatformExporter`, and `SensitiveDataFilter`
 
 ## Changed
 
@@ -219,8 +221,8 @@ To migrate, use `new Observability()` with explicit exporters and processors.
 ```diff
 + import {
 +   Observability,
-+   DefaultExporter,
-+   CloudExporter,
++   MastraStorageExporter,
++   MastraPlatformExporter,
 +   SensitiveDataFilter,
 + } from '@mastra/observability';
 
@@ -232,7 +234,7 @@ To migrate, use `new Observability()` with explicit exporters and processors.
 +     configs: {
 +       default: {
 +         serviceName: 'mastra',
-+         exporters: [new DefaultExporter(), new CloudExporter()],
++         exporters: [new MastraStorageExporter(), new MastraPlatformExporter()],
 +         spanOutputProcessors: [new SensitiveDataFilter()],
 +       },
 +     },
@@ -320,8 +322,8 @@ Simply remove the `instrumentation.mjs` file and configure observability in your
 // src/mastra/index.ts
 import {
   Observability,
-  DefaultExporter,
-  CloudExporter,
+  MastraStorageExporter,
+  MastraPlatformExporter,
   SensitiveDataFilter,
 } from '@mastra/observability'
 
@@ -330,7 +332,7 @@ export const mastra = new Mastra({
     configs: {
       default: {
         serviceName: 'mastra',
-        exporters: [new DefaultExporter(), new CloudExporter()],
+        exporters: [new MastraStorageExporter(), new MastraPlatformExporter()],
         spanOutputProcessors: [new SensitiveDataFilter()],
       },
     },

package/.docs/models/gateways/azure-openai.md

@@ -13,7 +13,7 @@ const agent = new Agent({
   id: "my-agent",
   name: "My Agent",
   instructions: "You are a helpful assistant",
-  model: "azure-openai/my-gpt4-deployment"  // Use your Azure deployment name (autocompleted in dev mode)
+  model: "azure-openai/my-gpt-5-4-deployment"  // Use your Azure deployment name (autocompleted in dev mode)
 });
 
 // Generate a response
@@ -34,9 +34,9 @@ Azure model IDs follow this pattern: `azure-openai/your-deployment-name`
 
 The deployment name is **specific to your Azure account** and chosen when you create a deployment in Azure Portal. Common examples:
 
-- `azure-openai/my-gpt4-deployment`
-- `azure-openai/production-gpt-35-turbo`
-- `azure-openai/staging-gpt-4o`
+- `azure-openai/my-gpt-5-4-deployment`
+- `azure-openai/production-gpt-5-4`
+- `azure-openai/staging-gpt-5-4-mini`
 
 ## Setup
 
@@ -44,7 +44,7 @@ Create deployments in [Azure OpenAI Studio](https://oai.azure.com/). The resourc
 
 ## Configuration
 
-Instantiate the gateway and pass it to Mastra. Three configuration modes are available.
+Instantiate the gateway and pass it to Mastra. The common configuration modes are shown below.
 
 ### Static Deployments
 
@@ -59,7 +59,7 @@ export const mastra = new Mastra({
     new AzureOpenAIGateway({
       resourceName: "my-openai-resource",
       apiKey: process.env.AZURE_API_KEY!,
-      deployments: ["gpt-4-prod", "gpt-35-turbo-dev"],
+      deployments: ["gpt-5-4-prod", "gpt-5-4-mini-dev"],
     }),
   ],
 });
@@ -111,7 +111,7 @@ export const mastra = new Mastra({
         type: "entraId",
         credential: new DefaultAzureCredential(),
       },
-      deployments: ["gpt-4-prod", "gpt-35-turbo-dev"],
+      deployments: ["gpt-5-4-prod", "gpt-5-4-mini-dev"],
     }),
   ],
 });
@@ -145,23 +145,94 @@ export const mastra = new Mastra({
 });
 ```
 
+### Azure Responses API
+
+Azure OpenAI supports the Responses API through the `v1` API path used by the AI SDK Azure provider. Set `useResponsesAPI: true` when your Azure resource and deployment support that route. The gateway then uses `apiVersion: "v1"` and `useDeploymentBasedUrls: false` by default.
+
+```typescript
+import { Mastra } from "@mastra/core";
+import { AzureOpenAIGateway } from "@mastra/core/llm";
+
+export const mastra = new Mastra({
+  gateways: [
+    new AzureOpenAIGateway({
+      resourceName: "my-openai-resource",
+      apiKey: process.env.AZURE_API_KEY!,
+      useResponsesAPI: true,
+      deployments: ["my-gpt-5-4-deployment"],
+    }),
+  ],
+});
+```
+
+Keep `useResponsesAPI` omitted or set it to `false` for the existing Azure chat completions route. That path keeps `apiVersion: "2024-04-01-preview"` and deployment-based URLs by default for compatibility.
+
+You can still configure `apiVersion` and `useDeploymentBasedUrls` directly. For example, set `useDeploymentBasedUrls: false` to use the Azure `v1` URL shape with the chat model constructor; the gateway defaults `apiVersion` to `"v1"` for that route. Passing `apiVersion: "v1"` by itself keeps the existing deployment-based URL default for compatibility.
+
+Do not combine `useResponsesAPI: true` with `useDeploymentBasedUrls: true`; the gateway rejects that configuration because Responses API support uses the Azure `v1` route.
+
+Use `apiVersion: "v1"` for the GA `v1` route. Microsoft currently exposes preview `v1` features through feature-specific headers, such as `"aoai-evals": "preview"`, or through preview/alpha API paths. The gateway still accepts `apiVersion: "preview"` with `useDeploymentBasedUrls: false` for Azure provider configurations that require the preview query value. Date-based API versions are only for the legacy deployment-based route, so the gateway rejects them when `useResponsesAPI` is `true` or `useDeploymentBasedUrls` is `false`.
+
+The same API key and Microsoft Entra ID authentication modes work with the `v1` route.
+
+### Azure Responses WebSocket transport
+
+Azure OpenAI also supports WebSocket mode on the Responses API. Use it for agent or tool loops with many model-tool round trips. Keep the standard HTTP transport for single-shot requests and short conversations.
+
+WebSocket transport requires `useResponsesAPI: true`, because Azure exposes it on the `v1` Responses path. Then opt in per stream request with `providerOptions.azure.transport: "websocket"`.
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+
+const agent = new Agent({
+  id: "azure-ws-agent",
+  name: "Azure WebSocket Agent",
+  instructions: "Use tools when they are useful.",
+  model: "azure-openai/my-gpt-5-4-deployment",
+});
+
+const stream = await agent.stream("Find and improve the slow function.", {
+  providerOptions: {
+    azure: {
+      transport: "websocket",
+      store: false,
+      websocket: {
+        closeOnFinish: false,
+      },
+    },
+  },
+});
+
+for await (const chunk of stream.textStream) {
+  process.stdout.write(chunk);
+}
+
+stream.transport?.close();
+```
+
+Set `closeOnFinish: false` when you want to keep the socket open across follow-up turns. Azure keeps one response chain in connection-local memory, so continuing from the most recent `previous_response_id` can reduce continuation latency. The connection runs one response at a time and does not multiplex parallel runs.
+
+Do not send overlapping follow-up requests with `previous_response_id` on the same WebSocket transport. Mastra rejects overlapping continuation requests because Azure only keeps one in-flight response per connection. Wait for the active stream to finish before continuing the response chain.
+
 ## Configuration Reference
 
-| Option                      | Type              | Required | Description                                                           |
-| --------------------------- | ----------------- | -------- | --------------------------------------------------------------------- |
-| `resourceName`              | `string`          | Yes      | Azure OpenAI resource name                                            |
-| `apiKey`                    | `string`          | Yes\*    | API key from "Keys and Endpoint"                                      |
-| `authentication`            | `object`          | No       | Microsoft Entra ID authentication                                     |
-| `authentication.type`       | `"entraId"`       | Yes\*    | Authentication mode                                                   |
-| `authentication.credential` | `TokenCredential` | Yes\*    | Azure SDK-compatible credential for `entraId` authentication mode     |
-| `authentication.scope`      | `string`          | No       | Token scope (default: `https://cognitiveservices.azure.com/.default`) |
-| `apiVersion`                | `string`          | No       | API version (default: `2024-04-01-preview`)                           |
-| `deployments`               | `string[]`        | No       | Deployment names for static mode                                      |
-| `management`                | `object`          | No       | Management API credentials                                            |
-| `management.tenantId`       | `string`          | Yes\*    | Azure AD tenant ID                                                    |
-| `management.clientId`       | `string`          | Yes\*    | Service Principal client ID                                           |
-| `management.clientSecret`   | `string`          | Yes\*    | Service Principal secret                                              |
-| `management.subscriptionId` | `string`          | Yes\*    | Azure subscription ID                                                 |
-| `management.resourceGroup`  | `string`          | Yes\*    | Resource group name                                                   |
+| Option                      | Type              | Required | Description                                                                                                                  |
+| --------------------------- | ----------------- | -------- | ---------------------------------------------------------------------------------------------------------------------------- |
+| `resourceName`              | `string`          | Yes      | Azure OpenAI resource name                                                                                                   |
+| `apiKey`                    | `string`          | Yes\*    | API key from "Keys and Endpoint"                                                                                             |
+| `authentication`            | `object`          | No       | Microsoft Entra ID authentication                                                                                            |
+| `authentication.type`       | `"entraId"`       | Yes\*    | Authentication mode                                                                                                          |
+| `authentication.credential` | `TokenCredential` | Yes\*    | Azure SDK-compatible credential for `entraId` authentication mode                                                            |
+| `authentication.scope`      | `string`          | No       | Token scope (default: `https://cognitiveservices.azure.com/.default`)                                                        |
+| `apiVersion`                | `string`          | No       | API version (default: `2024-04-01-preview`, or `v1` when `useResponsesAPI` is `true` or `useDeploymentBasedUrls` is `false`) |
+| `useResponsesAPI`           | `boolean`         | No       | Resolve deployments through the Azure OpenAI Responses API (default: `false`)                                                |
+| `useDeploymentBasedUrls`    | `boolean`         | No       | Use Azure deployment-based URLs (default: `true`, or `false` when `useResponsesAPI` is `true`)                               |
+| `deployments`               | `string[]`        | No       | Deployment names for static mode                                                                                             |
+| `management`                | `object`          | No       | Management API credentials                                                                                                   |
+| `management.tenantId`       | `string`          | Yes\*    | Azure AD tenant ID                                                                                                           |
+| `management.clientId`       | `string`          | Yes\*    | Service Principal client ID                                                                                                  |
+| `management.clientSecret`   | `string`          | Yes\*    | Service Principal secret                                                                                                     |
+| `management.subscriptionId` | `string`          | Yes\*    | Azure subscription ID                                                                                                        |
+| `management.resourceGroup`  | `string`          | Yes\*    | Resource group name                                                                                                          |
 
 \* Provide either `apiKey` or `authentication.type: "entraId"`. Management fields are required if `management` is provided.

package/.docs/models/gateways/netlify.md

@@ -1,6 +1,6 @@
 # Netlify
 
-Netlify AI Gateway provides unified access to multiple providers with built-in caching and observability. Access 66 models through Mastra's model router.
+Netlify AI Gateway provides unified access to multiple providers with built-in caching and observability. Access 68 models through Mastra's model router.
 
 Learn more in the [Netlify documentation](https://docs.netlify.com/build/ai-gateway/overview/).
 
@@ -57,11 +57,13 @@ ANTHROPIC_API_KEY=ant-...
 | `gemini/gemini-3-flash-preview`             |
 | `gemini/gemini-3-pro-image-preview`         |
 | `gemini/gemini-3.1-flash-image-preview`     |
+| `gemini/gemini-3.1-flash-lite`              |
 | `gemini/gemini-3.1-flash-lite-preview`      |
 | `gemini/gemini-3.1-pro-preview`             |
 | `gemini/gemini-3.1-pro-preview-customtools` |
 | `gemini/gemini-flash-latest`                |
 | `gemini/gemini-flash-lite-latest`           |
+| `openai/chat-latest`                        |
 | `openai/gpt-4.1`                            |
 | `openai/gpt-4.1-mini`                       |
 | `openai/gpt-4.1-nano`                       |

package/.docs/models/gateways/openrouter.md

@@ -1,6 +1,6 @@
 # ![OpenRouter logo](https://models.dev/logos/openrouter.svg)OpenRouter
 
-OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 185 models through Mastra's model router.
+OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 189 models through Mastra's model router.
 
 Learn more in the [OpenRouter documentation](https://openrouter.ai/models).
 
@@ -172,6 +172,8 @@ ANTHROPIC_API_KEY=ant-...
 | `poolside/laguna-xs.2:free`                                     |
 | `prime-intellect/intellect-3`                                   |
 | `qwen/qwen-2.5-coder-32b-instruct`                              |
+| `qwen/qwen-3.6-27b`                                             |
+| `qwen/qwen-plus`                                                |
 | `qwen/qwen2.5-vl-72b-instruct`                                  |
 | `qwen/qwen3-235b-a22b-07-25`                                    |
 | `qwen/qwen3-235b-a22b-thinking-2507`                            |
@@ -180,6 +182,7 @@ ANTHROPIC_API_KEY=ant-...
 | `qwen/qwen3-coder`                                              |
 | `qwen/qwen3-coder-30b-a3b-instruct`                             |
 | `qwen/qwen3-coder-flash`                                        |
+| `qwen/qwen3-coder-plus`                                         |
 | `qwen/qwen3-coder:exacto`                                       |
 | `qwen/qwen3-max`                                                |
 | `qwen/qwen3-next-80b-a3b-instruct`                              |
@@ -192,6 +195,7 @@ ANTHROPIC_API_KEY=ant-...
 | `sourceful/riverflow-v2-max-preview`                            |
 | `sourceful/riverflow-v2-standard-preview`                       |
 | `stepfun/step-3.5-flash`                                        |
+| `tencent/hy3-preview`                                           |
 | `x-ai/grok-3`                                                   |
 | `x-ai/grok-3-beta`                                              |
 | `x-ai/grok-3-mini`                                              |

package/.docs/models/gateways/vercel.md

@@ -1,6 +1,6 @@
 # ![Vercel logo](https://models.dev/logos/vercel.svg)Vercel
 
-Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 246 models through Mastra's model router.
+Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 247 models through Mastra's model router.
 
 Learn more in the [Vercel documentation](https://ai-sdk.dev/providers/ai-sdk-providers).
 
@@ -113,6 +113,7 @@ ANTHROPIC_API_KEY=ant-...
 | `google/gemini-3-pro-image`                    |
 | `google/gemini-3-pro-preview`                  |
 | `google/gemini-3.1-flash-image-preview`        |
+| `google/gemini-3.1-flash-lite`                 |
 | `google/gemini-3.1-flash-lite-preview`         |
 | `google/gemini-3.1-pro-preview`                |
 | `google/gemini-embedding-001`                  |

package/.docs/models/index.md

@@ -1,6 +1,6 @@
 # Model Providers
 
-Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 3875 models from 107 providers through a single API.
+Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 3888 models from 108 providers through a single API.
 
 ## Features
 

package/.docs/models/providers/deepinfra.md

@@ -1,6 +1,6 @@
 # ![Deep Infra logo](https://models.dev/logos/deepinfra.svg)Deep Infra
 
-Access 35 Deep Infra models through Mastra's model router. Authentication is handled automatically using the `DEEPINFRA_API_KEY` environment variable.
+Access 36 Deep Infra models through Mastra's model router. Authentication is handled automatically using the `DEEPINFRA_API_KEY` environment variable.
 
 Learn more in the [Deep Infra documentation](https://deepinfra.com/models).
 
@@ -36,6 +36,7 @@ for await (const chunk of stream) {
 | `deepinfra/anthropic/claude-4-opus`                           | 200K    |       |           |       |       |       | $17        | $83         |
 | `deepinfra/deepseek-ai/DeepSeek-R1-0528`                      | 164K    |       |           |       |       |       | $0.50      | $2          |
 | `deepinfra/deepseek-ai/DeepSeek-V3.2`                         | 164K    |       |           |       |       |       | $0.26      | $0.38       |
+| `deepinfra/deepseek-ai/DeepSeek-V4-Flash`                     | 1.0M    |       |           |       |       |       | $0.14      | $0.28       |
 | `deepinfra/deepseek-ai/DeepSeek-V4-Pro`                       | 66K     |       |           |       |       |       | $2         | $3          |
 | `deepinfra/google/gemma-4-26B-A4B-it`                         | 256K    |       |           |       |       |       | $0.07      | $0.34       |
 | `deepinfra/google/gemma-4-31B-it`                             | 256K    |       |           |       |       |       | $0.13      | $0.38       |

package/.docs/models/providers/deepseek.md

@@ -87,4 +87,6 @@ const response = await agent.generate("Hello!", {
 
 ### Available Options
 
-**thinking** (`{ type?: "enabled" | "disabled" | undefined; } | undefined`)
+**thinking** (`{ type?: "enabled" | "disabled" | undefined; } | undefined`)
+
+**reasoningEffort** (`"high" | "max" | undefined`)

package/.docs/models/providers/digitalocean.md

@@ -1,6 +1,6 @@
 # ![DigitalOcean logo](https://models.dev/logos/digitalocean.svg)DigitalOcean
 
-Access 63 DigitalOcean models through Mastra's model router. Authentication is handled automatically using the `DIGITALOCEAN_ACCESS_TOKEN` environment variable.
+Access 71 DigitalOcean models through Mastra's model router. Authentication is handled automatically using the `DIGITALOCEAN_ACCESS_TOKEN` environment variable.
 
 Learn more in the [DigitalOcean documentation](https://docs.digitalocean.com/products/gradient-ai-platform/details/models/).
 
@@ -37,6 +37,7 @@ for await (const chunk of stream) {
 | `digitalocean/alibaba-qwen3-32b`                     | 131K    |       |           |       |       |       | $0.25      | $0.55       |
 | `digitalocean/all-mini-lm-l6-v2`                     | 256     |       |           |       |       |       | $0.01      | —           |
 | `digitalocean/anthropic-claude-4.1-opus`             | 200K    |       |           |       |       |       | $15        | $75         |
+| `digitalocean/anthropic-claude-4.5-haiku`            | 200K    |       |           |       |       |       | $1         | $5          |
 | `digitalocean/anthropic-claude-4.5-sonnet`           | 1.0M    |       |           |       |       |       | $3         | $15         |
 | `digitalocean/anthropic-claude-4.6-sonnet`           | 1.0M    |       |           |       |       |       | $3         | $15         |
 | `digitalocean/anthropic-claude-haiku-4.5`            | 200K    |       |           |       |       |       | $1         | $5          |
@@ -50,6 +51,7 @@ for await (const chunk of stream) {
 | `digitalocean/bge-reranker-v2-m3`                    | 8K      |       |           |       |       |       | $0.01      | —           |
 | `digitalocean/deepseek-3.2`                          | 128K    |       |           |       |       |       | $0.50      | $2          |
 | `digitalocean/deepseek-r1-distill-llama-70b`         | 131K    |       |           |       |       |       | $0.99      | $0.99       |
+| `digitalocean/deepseek-v3`                           | 164K    |       |           |       |       |       | —          | —           |
 | `digitalocean/deepseek-v4-pro`                       | 1.0M    |       |           |       |       |       | $2         | $3          |
 | `digitalocean/e5-large-v2`                           | 512     |       |           |       |       |       | $0.02      | —           |
 | `digitalocean/fal-ai/elevenlabs/tts/multilingual-v2` | —       |       |           |       |       |       | —          | —           |
@@ -60,12 +62,16 @@ for await (const chunk of stream) {
 | `digitalocean/glm-5`                                 | 203K    |       |           |       |       |       | $1         | $3          |
 | `digitalocean/gte-large-en-v1.5`                     | 8K      |       |           |       |       |       | $0.09      | —           |
 | `digitalocean/kimi-k2.5`                             | 262K    |       |           |       |       |       | $0.50      | $3          |
+| `digitalocean/kimi-k2.6`                             | 262K    |       |           |       |       |       | $0.95      | $4          |
 | `digitalocean/llama-4-maverick`                      | 1.0M    |       |           |       |       |       | $0.25      | $0.87       |
-| `digitalocean/llama-guard-4-12b`                     | 128K    |       |           |       |       |       | —          | —           |
+| `digitalocean/llama3-8b-instruct`                    | 131K    |       |           |       |       |       | $0.20      | $0.20       |
 | `digitalocean/llama3.3-70b-instruct`                 | 128K    |       |           |       |       |       | $0.65      | $0.65       |
 | `digitalocean/minimax-m2.5`                          | 205K    |       |           |       |       |       | $0.30      | $1          |
+| `digitalocean/ministral-3-8b-instruct-2512`          | 262K    |       |           |       |       |       | —          | —           |
 | `digitalocean/mistral-3-14B`                         | 262K    |       |           |       |       |       | $0.20      | $0.20       |
+| `digitalocean/mistral-7b-instruct-v0.3`              | 33K     |       |           |       |       |       | —          | —           |
 | `digitalocean/multi-qa-mpnet-base-dot-v1`            | 512     |       |           |       |       |       | $0.01      | —           |
+| `digitalocean/nemotron-3-nano-30b`                   | 262K    |       |           |       |       |       | —          | —           |
 | `digitalocean/nemotron-3-nano-omni`                  | 66K     |       |           |       |       |       | $0.50      | $0.90       |
 | `digitalocean/nemotron-nano-12b-v2-vl`               | 128K    |       |           |       |       |       | $0.20      | $0.60       |
 | `digitalocean/nvidia-nemotron-3-super-120b`          | 256K    |       |           |       |       |       | $0.30      | $0.65       |
@@ -86,11 +92,13 @@ for await (const chunk of stream) {
 | `digitalocean/openai-gpt-5.5`                        | 1.0M    |       |           |       |       |       | $5         | $30         |
 | `digitalocean/openai-gpt-image-1`                    | —       |       |           |       |       |       | $5         | $40         |
 | `digitalocean/openai-gpt-image-1.5`                  | —       |       |           |       |       |       | $5         | $10         |
+| `digitalocean/openai-gpt-image-2`                    | —       |       |           |       |       |       | —          | —           |
 | `digitalocean/openai-gpt-oss-120b`                   | 131K    |       |           |       |       |       | $0.10      | $0.70       |
 | `digitalocean/openai-gpt-oss-20b`                    | 131K    |       |           |       |       |       | $0.05      | $0.45       |
 | `digitalocean/openai-o1`                             | 200K    |       |           |       |       |       | $15        | $60         |
 | `digitalocean/openai-o3`                             | 200K    |       |           |       |       |       | $2         | $8          |
 | `digitalocean/openai-o3-mini`                        | 200K    |       |           |       |       |       | $1         | $4          |
+| `digitalocean/qwen-2.5-14b-instruct`                 | 131K    |       |           |       |       |       | —          | —           |
 | `digitalocean/qwen3-coder-flash`                     | 262K    |       |           |       |       |       | $0.45      | $2          |
 | `digitalocean/qwen3-embedding-0.6b`                  | 8K      |       |           |       |       |       | $0.04      | —           |
 | `digitalocean/qwen3-tts-voicedesign`                 | 33K     |       |           |       |       |       | —          | —           |