@mastra/mcp-docs-server 1.2.14 → 1.2.15-alpha.10

package/.docs/docs/workflows/{stored-workflows.md → dynamic-workflows.md}

@@ -1,22 +1,22 @@
 > Discover all available pages from the documentation index: https://mastra.ai/llms.txt
 
-# Stored workflows
+# Dynamic workflows
 
 > **Beta:** This feature is in beta. Breaking changes may occur without a major version bump until the API is stable.
 
-Stored workflows are workflow definitions expressed as data instead of code. A definition is a JSON document that describes the workflow's schemas and step graph. Mastra validates the definition and registers it as a runnable workflow, then persists it in storage so it survives process restarts.
+Dynamic workflows are workflow definitions expressed as data instead of code. A definition is a JSON document that describes the workflow's schemas and step graph. Mastra validates the definition and registers it as a runnable workflow, then persists it in storage so it survives process restarts.
 
-Because a definition contains no JavaScript closures, anything that can produce JSON can author a workflow: an HTTP client, an LLM, a visual editor, or your own tooling. Once registered, a stored workflow runs through the same execution API as a code-defined workflow.
+Because a definition contains no JavaScript closures, anything that can produce JSON can author a workflow: an HTTP client, an LLM, a visual editor, or your own tooling. Once registered, a dynamic workflow runs through the same execution API as a code-defined workflow.
 
-## When to use stored workflows
+## When to use dynamic workflows
 
-Use stored workflows when users, agents, visual editors, or external systems need to create workflows without changing application code or deploying again.
+Use dynamic workflows when users, agents, visual editors, or external systems need to create workflows without changing application code or deploying again.
 
-Keep defining workflows with [`createWorkflow()`](https://mastra.ai/docs/workflows/overview) when the workflow belongs in your application source or needs custom step functions. Stored workflows can invoke agents, tools, and workflows that are already registered on the `Mastra` instance.
+Keep defining workflows with [`createWorkflow()`](https://mastra.ai/docs/workflows/overview) when the workflow belongs in your application source or needs custom step functions. Dynamic workflows can invoke agents, tools, and workflows that are already registered on the `Mastra` instance.
 
 ## Quickstart
 
-The following example registers a tool and invokes it from a stored workflow. It then runs the workflow. `LibSQLStore` persists the definition in `mastra.db`, so Mastra can restore it after a restart.
+The following example registers a tool and invokes it from a dynamic workflow. It then runs the workflow. `LibSQLStore` persists the definition in `mastra.db`, so Mastra can restore it after a restart.
 
 ```typescript
 import { Mastra } from '@mastra/core/mastra'
@@ -46,7 +46,7 @@ const mastra = new Mastra({
   tools: { 'create-greeting': greetingTool },
 })
 
-await mastra.addStoredWorkflow({
+await mastra.addDynamicWorkflow({
   id: 'greeting-workflow',
   description: 'Create a greeting for the supplied name',
   inputSchema: {
@@ -83,9 +83,9 @@ if (result.status === 'success') {
 }
 ```
 
-The workflow prints `Hello, Ada!`. Calling [`addStoredWorkflow()`](https://mastra.ai/reference/core/addStoredWorkflow) validates the definition before it changes storage or the live workflow registry.
+The workflow prints `Hello, Ada!`. Calling [`addDynamicWorkflow()`](https://mastra.ai/reference/core/addDynamicWorkflow) validates the definition before it changes storage or the live workflow registry.
 
-The definition uses JSON Schema because it must survive a JSON round trip. The `graph` describes which registered components to invoke and how data moves between them. See the [stored workflow definition reference](https://mastra.ai/reference/workflows/stored-workflow-definition) for every field and graph entry.
+The definition uses JSON Schema because it must survive a JSON round trip. The `graph` describes which registered components to invoke and how data moves between them. See the [dynamic workflow definition reference](https://mastra.ai/reference/workflows/dynamic-workflow-definition) for every field and graph entry.
 
 ## Build and update definitions
 
@@ -93,54 +93,54 @@ A definition can come from any source that produces JSON. For example, an API ro
 
 ```typescript
 const definition = await request.json()
-await mastra.addStoredWorkflow(definition)
+await mastra.addDynamicWorkflow(definition)
 ```
 
 ### Register dependencies first
 
-Register referenced components on the same `Mastra` instance before adding the stored workflow. Agent and nested workflow entries use their intrinsic IDs. A tool entry uses its key from the `Mastra` `tools` object, so the quickstart registers the tool under `create-greeting` before referencing that key with `toolId`.
+Register referenced components on the same `Mastra` instance before adding the dynamic workflow. Agent and nested workflow entries use their intrinsic IDs. A tool entry uses its key from the `Mastra` `tools` object, so the quickstart registers the tool under `create-greeting` before referencing that key with `toolId`.
 
-Use a `mapping` entry when one step's output doesn't match the next step's input. Mapping entries can read data from the workflow input and previous step results, along with workflow state and request context. The [definition reference](https://mastra.ai/reference/workflows/stored-workflow-definition) lists the supported mapping descriptors.
+Use a `mapping` entry when one step's output doesn't match the next step's input. Mapping entries can read data from the workflow input and previous step results, along with workflow state and request context. The [definition reference](https://mastra.ai/reference/workflows/dynamic-workflow-definition) lists the supported mapping descriptors.
 
 ### Replace a workflow
 
 Add a new definition with the same `id` to replace the persisted definition and live registration:
 
 ```typescript
-await mastra.addStoredWorkflow(updatedDefinition)
+await mastra.addDynamicWorkflow(updatedDefinition)
 ```
 
 New runs use the updated graph. Runs that already started continue with their original graph.
 
 ### Add nested workflows together
 
-When a root workflow references helper workflows that aren't registered yet, add the full set with [`addStoredWorkflows()`](https://mastra.ai/reference/core/addStoredWorkflows):
+When a root workflow references helper workflows that aren't registered yet, add the full set with [`addDynamicWorkflows()`](https://mastra.ai/reference/core/addDynamicWorkflows):
 
 ```typescript
-await mastra.addStoredWorkflows([rootDefinition, helperDefinition])
+await mastra.addDynamicWorkflows([rootDefinition, helperDefinition])
 ```
 
 Mastra validates the bundle as a unit and determines the registration order from the dependencies. If validation fails, none of the definitions are registered.
 
 ### Manage definitions over HTTP
 
-Applications don't need direct access to the `Mastra` instance to manage stored workflows. Use one of these interfaces:
+Applications don't need direct access to the `Mastra` instance to manage dynamic workflows. Use one of these interfaces:
 
-- [Client SDK workflows API](https://mastra.ai/reference/client-js/workflows): Call `upsertStoredWorkflow()` from a JavaScript or TypeScript client.
+- [Client SDK workflows API](https://mastra.ai/reference/client-js/workflows): Call `upsertDynamicWorkflow()` from a JavaScript or TypeScript client.
 - [Server routes](https://mastra.ai/reference/server/routes): Send definitions to `POST /api/stored/workflows`.
 
-On authenticated servers, stored-workflow management requires the `stored-workflows:read` and `stored-workflows:write` permissions. Running the registered workflow requires `workflows:execute`.
+On authenticated servers, dynamic-workflow management requires the `stored-workflows:read` and `stored-workflows:write` permissions. Running the registered workflow requires `workflows:execute`.
 
 ### Persist definitions
 
 Stored definitions use the `workflowDefinitions` storage domain. On startup, Mastra loads active definitions from storage and registers them in dependency order.
 
-Without a storage adapter that supports this domain, `addStoredWorkflow()` still registers the workflow in memory, but the definition is lost when the process restarts. See the [storage reference](https://mastra.ai/reference/storage/overview) for adapter support.
+Without a storage adapter that supports this domain, `addDynamicWorkflow()` still registers the workflow in memory, but the definition is lost when the process restarts. See the [storage reference](https://mastra.ai/reference/storage/overview) for adapter support.
 
 ## Related
 
-- [Stored workflow definition](https://mastra.ai/reference/workflows/stored-workflow-definition)
-- [`Mastra.addStoredWorkflow()`](https://mastra.ai/reference/core/addStoredWorkflow)
-- [`Mastra.addStoredWorkflows()`](https://mastra.ai/reference/core/addStoredWorkflows)
+- [Dynamic workflow definition](https://mastra.ai/reference/workflows/dynamic-workflow-definition)
+- [`Mastra.addDynamicWorkflow()`](https://mastra.ai/reference/core/addDynamicWorkflow)
+- [`Mastra.addDynamicWorkflows()`](https://mastra.ai/reference/core/addDynamicWorkflows)
 - [Client SDK workflows API](https://mastra.ai/reference/client-js/workflows)
 - [Server routes](https://mastra.ai/reference/server/routes)

package/.docs/docs/workflows/snapshots.md

@@ -81,13 +81,14 @@ Each snapshot includes the `runId`, input, step status (`success`, `suspended`,
 
 ## How snapshots are saved and retrieved
 
-Snapshots are saved to the configured storage system. By default, they use libSQL, but you can configure Upstash or PostgreSQL instead. Each snapshot is saved in the `workflow_snapshots` table and identified by the workflow's `runId`.
+Snapshots are saved to the configured storage system. By default, they use libSQL, but you can configure Upstash, PostgreSQL, or OracleDB instead. Each snapshot is saved in the `workflow_snapshots` table and identified by the workflow's `runId`.
 
 Read more about:
 
 - [libSQL Storage](https://mastra.ai/reference/storage/libsql)
 - [Upstash Storage](https://mastra.ai/reference/storage/upstash)
 - [PostgreSQL Storage](https://mastra.ai/reference/storage/postgresql)
+- [OracleDB Storage](https://mastra.ai/reference/storage/oracledb)
 
 ### Saving snapshots
 
@@ -141,6 +142,7 @@ export const mastra = new Mastra({
 
 - [libSQL Storage](https://mastra.ai/reference/storage/libsql)
 - [PostgreSQL Storage](https://mastra.ai/reference/storage/postgresql)
+- [OracleDB Storage](https://mastra.ai/reference/storage/oracledb)
 - [MongoDB Storage](https://mastra.ai/reference/storage/mongodb)
 - [Upstash Storage](https://mastra.ai/reference/storage/upstash)
 - [Cloudflare D1](https://mastra.ai/reference/storage/cloudflare-d1)

package/.docs/guides/build-your-ui/ai-sdk-ui.md

@@ -393,16 +393,17 @@ Use Custom UI when you want to:
 
 Mastra streams data to the frontend as "parts" within messages. Each part has a `type` that determines how to render it. The `@mastra/ai-sdk` package transforms Mastra streams into AI SDK-compatible [UI Message DataParts](https://ai-sdk.dev/docs/reference/ai-sdk-core/ui-message#datauipart).
 
-| Data Part Type       | Source                  | Description                                                                        |
-| -------------------- | ----------------------- | ---------------------------------------------------------------------------------- |
-| `tool-{toolKey}`     | AI SDK built-in         | Tool invocation with states: `input-available`, `output-available`, `output-error` |
-| `data-workflow`      | `workflowRoute()`       | Workflow execution state snapshots with step status and final outputs              |
-| `data-workflow-step` | `workflowRoute()`       | Workflow step delta with the full payload for the changed step                     |
-| `data-network`       | `networkRoute()`        | Agent network execution with ordered steps and outputs                             |
-| `data-tool-agent`    | Nested agent in tool    | Agent output streamed from within a tool's `execute()`                             |
-| `data-tool-workflow` | Nested workflow in tool | Workflow output streamed from within a tool's `execute()`                          |
-| `data-tool-network`  | Nested network in tool  | Network output streamed from within a tool's `execute()`                           |
-| `data-{custom}`      | `writer.custom()`       | Custom events for progress indicators, status updates, etc.                        |
+| Data Part Type         | Source                  | Description                                                                        |
+| ---------------------- | ----------------------- | ---------------------------------------------------------------------------------- |
+| `tool-{toolKey}`       | AI SDK built-in         | Tool invocation with states: `input-available`, `output-available`, `output-error` |
+| `data-workflow`        | `workflowRoute()`       | Workflow execution state snapshots with step status and final outputs              |
+| `data-workflow-step`   | `workflowRoute()`       | Workflow step delta with the full payload for the changed step                     |
+| `data-network`         | `networkRoute()`        | Agent network execution with ordered steps and outputs                             |
+| `data-tool-agent`      | Nested agent in tool    | Compact nested-agent snapshot while the current step is still running              |
+| `data-tool-agent-step` | Nested agent in tool    | Full nested-agent step payload emitted when a nested step finishes                 |
+| `data-tool-workflow`   | Nested workflow in tool | Workflow output streamed from within a tool's `execute()`                          |
+| `data-tool-network`    | Nested network in tool  | Network output streamed from within a tool's `execute()`                           |
+| `data-{custom}`        | `writer.custom()`       | Custom events for progress indicators, status updates, etc.                        |
 
 ### Rendering tool outputs
 
@@ -1256,7 +1257,7 @@ For a complete implementation, see the [workflow-suspend-resume example](https:/
 
 ### Nested agent streams in tools
 
-Tools can call agents internally and stream the agent's output back to the UI. This creates `data-tool-agent` parts that can be rendered alongside the tool's final output.
+Tools can call agents internally and stream the agent's output back to the UI. This creates compact `data-tool-agent` snapshots while the nested step is still running, `data-tool-agent-step` parts when a nested step finishes, and one full `data-tool-agent` snapshot when the nested run finishes.
 
 The pattern uses:
 
@@ -1315,13 +1316,13 @@ export const forecastAgent = new Agent({
 
 **Frontend**:
 
-Handle `data-tool-agent` parts to display the nested agent's streamed output.
+Handle `data-tool-agent` parts for the live snapshot and `data-tool-agent-step` parts for the completed nested step payload.
 
 ```typescript
 import { useChat } from '@ai-sdk/react'
 import { DefaultChatTransport } from 'ai'
 import { useState } from 'react'
-import type { AgentDataPart } from '@mastra/ai-sdk'
+import type { AgentDataPart, AgentStepDataPart } from '@mastra/ai-sdk'
 
 export function NestedAgentChat() {
   const [input, setInput] = useState('')
@@ -1361,6 +1362,15 @@ export function NestedAgentChat() {
                 </div>
               )
             }
+            if (part.type === 'data-tool-agent-step') {
+              const { data } = part as AgentStepDataPart
+              return (
+                <div key={index} className="nested-agent-step">
+                  <strong>Completed nested step {data.stepIndex + 1}</strong>
+                  {data.step.text && <p>{data.step.text}</p>}
+                </div>
+              )
+            }
             return null
           })}
         </div>
@@ -1373,7 +1383,8 @@ export function NestedAgentChat() {
 Key points:
 
 - Piping `fullStream` to `context.writer` creates `data-tool-agent` parts
-- The `AgentDataPart` has `id` (on the part) and `data.text` (the agent's streamed text)
+- Read `data-tool-agent-step` when you need the full payload for the nested step that just finished
+- The `AgentDataPart` has `id` (on the part) and `data.text` (the current nested-agent text snapshot)
 - The tool still returns its own output after the stream completes
 
 For a complete implementation, see the [tool-nested-streams example](https://github.com/mastra-ai/ui-dojo/blob/main/src/pages/ai-sdk/tool-nested-streams.tsx) in UI Dojo.

package/.docs/guides/getting-started/quickstart.md

@@ -27,7 +27,7 @@ npm create mastra@latest
 **pnpm**:
 
 ```bash
-pnpm create mastra
+pnpm create mastra@latest
 ```
 
 **Yarn**:

package/.docs/guides/rag/overview.md

@@ -67,7 +67,7 @@ The basic building block of RAG is document processing. Documents can be chunked
 
 ## Vector storage
 
-Mastra supports multiple vector stores for embedding persistence and similarity search, including pgvector, Pinecone, Qdrant, and MongoDB. See the [vector database doc](https://mastra.ai/guides/rag/vector-databases).
+Mastra supports multiple vector stores for embedding persistence and similarity search, including pgvector, OracleDB, Pinecone, Qdrant, and MongoDB. See the [vector database doc](https://mastra.ai/guides/rag/vector-databases).
 
 ## More resources
 

package/.docs/guides/rag/retrieval.md

@@ -436,6 +436,23 @@ export const ragAgent = new Agent({
 })
 ```
 
+**OracleDB**:
+
+```ts
+import { ORACLEDB_PROMPT } from '@mastra/oracledb'
+
+export const ragAgent = new Agent({
+  id: 'rag-agent',
+  name: 'RAG Agent',
+  model: 'openai/gpt-5.6-sol',
+  instructions: `
+  Process queries using the provided context. Structure responses to be concise and relevant.
+  ${ORACLEDB_PROMPT}
+  `,
+  tools: { vectorQueryTool },
+})
+```
+
 **S3Vectors**:
 
 ```ts

package/.docs/guides/rag/vector-databases.md

@@ -78,6 +78,35 @@ await store.upsert({
 
 PostgreSQL with the pgvector extension is a good solution for teams already using PostgreSQL who want to minimize infrastructure complexity. For detailed setup instructions and best practices, see the [official pgvector repository](https://github.com/pgvector/pgvector).
 
+**OracleDB**:
+
+```ts
+import { OracleVector } from '@mastra/oracledb'
+
+const store = new OracleVector({
+  id: 'oracle-vector',
+  user: process.env.ORACLE_DATABASE_USER,
+  password: process.env.ORACLE_DATABASE_PASSWORD,
+  connectString: process.env.ORACLE_DATABASE_CONNECT_STRING,
+})
+
+await store.createIndex({
+  indexName: 'myCollection',
+  dimension: 1536,
+  indexConfig: { type: 'none' },
+})
+
+await store.upsert({
+  indexName: 'myCollection',
+  vectors: embeddings,
+  metadata: chunks.map(chunk => ({ text: chunk.text })),
+})
+```
+
+### Using Oracle Database Vector Search
+
+OracleDB stores embeddings in native `VECTOR` columns and metadata in Oracle JSON. Exact search is the default; HNSW and IVF indexes can be configured for tuned deployments.
+
 **Pinecone**:
 
 ```ts
@@ -410,6 +439,18 @@ Index names must:
 - Example: `my_index_123` is valid
 - Example: `my-index` is not valid (contains hyphen)
 
+**OracleDB**:
+
+Index names are logical Mastra names. OracleDB maps each logical index to a physical Oracle table internally.
+
+Logical index names must:
+
+- Be non-empty
+- Be 512 characters or fewer
+- Be stable for the lifetime of the vector index
+- Example: `my_collection_123` is valid
+- Example: `customer-support/docs:v1` is valid and is mapped to a safe Oracle table name
+
 **Pinecone**:
 
 Index names must:

package/.docs/guides/voice/realtime-voice.md

@@ -378,12 +378,38 @@ Tracing is on by default. Pass `observability: false` to `createLiveKitWorker` t
 
 ## Deployment
 
-The worker is a separate process from your Mastra server. Deploy it as a long-running Node service with the production command:
+The worker is a separate process from your Mastra server, so `mastra build` needs to emit it as its own entry. Add it to [`bundler.entries`](https://mastra.ai/reference/configuration):
+
+```typescript
+import { Mastra } from '@mastra/core'
+
+export const mastra = new Mastra({
+  bundler: {
+    entries: { 'voice-worker': './voice-worker.ts' },
+    // Keep LiveKit's native modules out of the bundle. `mastra build` only applies
+    // this default when you set no other bundler options, so set it explicitly here.
+    externals: true,
+  },
+})
+```
+
+`mastra build` now writes both processes into `.mastra/output`, sharing one `package.json` and one dependency install:
+
+```text
+.mastra/output/
+  index.mjs         # Mastra server
+  voice-worker.mjs  # LiveKit worker
+```
+
+Deploy that directory as a single artifact and start each process with its own command:
 
 ```bash
-node dist/voice-worker.js start
+node .mastra/output/index.mjs             # server
+node .mastra/output/voice-worker.mjs start # worker
 ```
 
+The worker needs the same environment variables as the server, plus `LIVEKIT_URL`, `LIVEKIT_API_KEY`, and `LIVEKIT_API_SECRET`.
+
 LiveKit's guidance on sizing, graceful shutdown, and hosting applies unchanged. See [Deploying agents](https://docs.livekit.io/agents/ops/deployment/). Workers connect outbound to LiveKit, so they don't need inbound ports.
 
 ## How it works

package/.docs/models/gateways/neon.md

@@ -2,21 +2,21 @@
 
 # ![Neon logo](https://models.dev/logos/neon.svg)Neon
 
-Neon aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 36 models through Mastra's model router.
+Neon aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 42 models through Mastra's model router.
 
 Learn more in the [Neon documentation](https://neon.com/docs).
 
 ## Usage
 
 ```typescript
-import { Agent } from '@mastra/core/agent'
+import { Agent } from "@mastra/core/agent";
 
 const agent = new Agent({
-  id: 'my-agent',
-  name: 'My Agent',
-  instructions: 'You are a helpful assistant',
-  model: 'neon/claude-haiku-4-5',
-})
+  id: "my-agent",
+  name: "My Agent",
+  instructions: "You are a helpful assistant",
+  model: "neon/claude-fable-5"
+});
 ```
 
 > **Info:** Mastra uses the OpenAI-compatible `/chat/completions` endpoint. Some provider-specific features may not be available. Check the [Neon documentation](https://neon.com/docs) for details.
@@ -33,37 +33,43 @@ NEON_AI_GATEWAY_TOKEN=your-gateway-key
 
 | Model                         |
 | ----------------------------- |
+| `claude-fable-5`              |
 | `claude-haiku-4-5`            |
 | `claude-opus-4-1`             |
 | `claude-opus-4-5`             |
 | `claude-opus-4-6`             |
 | `claude-opus-4-7`             |
 | `claude-opus-4-8`             |
-| `claude-sonnet-4`             |
+| `claude-opus-5`               |
 | `claude-sonnet-4-5`           |
 | `claude-sonnet-4-6`           |
-| `gemini-2-5-flash`            |
-| `gemini-2-5-pro`              |
+| `claude-sonnet-5`             |
 | `gemini-3-1-flash-lite`       |
 | `gemini-3-1-pro`              |
 | `gemini-3-5-flash`            |
+| `gemini-3-5-flash-lite`       |
+| `gemini-3-6-flash`            |
 | `gemini-3-flash`              |
-| `gemini-3-pro`                |
 | `gemma-3-12b`                 |
+| `glm-5-2`                     |
 | `gpt-5`                       |
 | `gpt-5-1`                     |
-| `gpt-5-1-codex-max`           |
-| `gpt-5-1-codex-mini`          |
 | `gpt-5-2`                     |
-| `gpt-5-2-codex`               |
 | `gpt-5-3-codex`               |
 | `gpt-5-4`                     |
 | `gpt-5-4-mini`                |
 | `gpt-5-4-nano`                |
+| `gpt-5-5`                     |
+| `gpt-5-5-pro`                 |
+| `gpt-5-6-luna`                |
+| `gpt-5-6-sol`                 |
+| `gpt-5-6-terra`               |
 | `gpt-5-mini`                  |
 | `gpt-5-nano`                  |
 | `gpt-oss-120b`                |
 | `gpt-oss-20b`                 |
+| `inkling`                     |
+| `kimi-k3`                     |
 | `llama-4-maverick`            |
 | `meta-llama-3-1-8b-instruct`  |
 | `meta-llama-3-3-70b-instruct` |

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

@@ -2,7 +2,7 @@
 
 # Netlify
 
-Netlify AI Gateway provides unified access to multiple providers with built-in caching and observability. Access 67 models through Mastra's model router.
+Netlify AI Gateway provides unified access to multiple providers with built-in caching and observability. Access 66 models through Mastra's model router.
 
 Learn more in the [Netlify documentation](https://docs.netlify.com/build/ai-gateway/overview/).
 
@@ -84,7 +84,6 @@ ANTHROPIC_API_KEY=ant-...
 | `openai/gpt-5.2-2025-12-11`                 |
 | `openai/gpt-5.2-pro`                        |
 | `openai/gpt-5.2-pro-2025-12-11`             |
-| `openai/gpt-5.3-chat-latest`                |
 | `openai/gpt-5.3-codex`                      |
 | `openai/gpt-5.4`                            |
 | `openai/gpt-5.4-2026-03-05`                 |

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

@@ -2,7 +2,7 @@
 
 # ![OpenRouter logo](https://models.dev/logos/openrouter.svg)OpenRouter
 
-OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 337 models through Mastra's model router.
+OpenRouter aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 339 models through Mastra's model router.
 
 Learn more in the [OpenRouter documentation](https://openrouter.ai/models).
 
@@ -139,7 +139,8 @@ ANTHROPIC_API_KEY=ant-...
 | `inception/mercury-2`                                      |
 | `inclusionai/ling-2.6-1t`                                  |
 | `inclusionai/ling-2.6-flash`                               |
-| `inclusionai/ling-3.0-flash:free`                          |
+| `inclusionai/ling-3.0-flash`                               |
+| `inclusionai/ling-3.0-tiny:free`                           |
 | `inclusionai/ring-2.6-1t`                                  |
 | `kwaipilot/kat-coder-air-v2.5`                             |
 | `kwaipilot/kat-coder-pro-v2`                               |
@@ -155,6 +156,7 @@ ANTHROPIC_API_KEY=ant-...
 | `meta-llama/llama-4-scout`                                 |
 | `meta-llama/llama-guard-4-12b`                             |
 | `meta/muse-spark-1.1`                                      |
+| `meta/muse-spark-1.2`                                      |
 | `microsoft/phi-4`                                          |
 | `microsoft/wizardlm-2-8x22b`                               |
 | `minimax/minimax-01`                                       |

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

@@ -2,7 +2,7 @@
 
 # ![Vercel logo](https://models.dev/logos/vercel.svg)Vercel
 
-Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 315 models through Mastra's model router.
+Vercel aggregates models from multiple providers with enhanced features like rate limiting and failover. Access 322 models through Mastra's model router.
 
 Learn more in the [Vercel documentation](https://ai-sdk.dev/providers/ai-sdk-providers).
 
@@ -88,7 +88,6 @@ ANTHROPIC_API_KEY=ant-...
 | `anthropic/claude-opus-4.8`              |
 | `anthropic/claude-opus-4.8-fast`         |
 | `anthropic/claude-opus-5`                |
-| `anthropic/claude-opus-5-fast`           |
 | `anthropic/claude-sonnet-4`              |
 | `anthropic/claude-sonnet-4.5`            |
 | `anthropic/claude-sonnet-4.6`            |
@@ -110,6 +109,7 @@ ANTHROPIC_API_KEY=ant-...
 | `bytedance/seed-1.8`                     |
 | `bytedance/seedance-2.0`                 |
 | `bytedance/seedance-2.0-fast`            |
+| `bytedance/seedance-2.5`                 |
 | `bytedance/seedance-v1.0-pro`            |
 | `bytedance/seedance-v1.0-pro-fast`       |
 | `bytedance/seedance-v1.5-pro`            |
@@ -131,6 +131,10 @@ ANTHROPIC_API_KEY=ant-...
 | `deepseek/deepseek-v4-flash`             |
 | `deepseek/deepseek-v4-flash-0731`        |
 | `deepseek/deepseek-v4-pro`               |
+| `fish-audio/s1`                          |
+| `fish-audio/s2-pro`                      |
+| `fish-audio/s2.1-pro`                    |
+| `fish-audio/transcribe-1`                |
 | `google/gemini-2.5-flash`                |
 | `google/gemini-2.5-flash-image`          |
 | `google/gemini-2.5-flash-lite`           |
@@ -162,7 +166,8 @@ ANTHROPIC_API_KEY=ant-...
 | `google/veo-3.1-lite-generate-001`       |
 | `inception/mercury-2`                    |
 | `inception/mercury-coder-small`          |
-| `inclusionai/ling-3.0-flash-free`        |
+| `inclusionai/ling-3.0-flash`             |
+| `inclusionai/ling-3.0-tiny-free`         |
 | `interfaze/interfaze-beta`               |
 | `klingai/kling-v2.5-turbo-i2v`           |
 | `klingai/kling-v2.5-turbo-t2v`           |
@@ -182,6 +187,8 @@ ANTHROPIC_API_KEY=ant-...
 | `meta/llama-4-maverick`                  |
 | `meta/llama-4-scout`                     |
 | `meta/muse-spark-1.1`                    |
+| `meta/muse-spark-1.2`                    |
+| `meta/muse-spark-1.2-contributor`        |
 | `minimax/minimax-h3`                     |
 | `minimax/minimax-m2`                     |
 | `minimax/minimax-m2.1`                   |

package/.docs/models/index.md

@@ -2,7 +2,7 @@
 
 # Model Providers
 
-Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 5336 models from 168 providers through a single API.
+Mastra provides a unified interface for working with LLMs across multiple providers, giving you access to 5457 models from 168 providers through a single API.
 
 ## Features
 

package/.docs/models/providers/anthropic.md

@@ -2,7 +2,7 @@
 
 # ![Anthropic logo](https://models.dev/logos/anthropic.svg)Anthropic
 
-Access 15 Anthropic models through Mastra's model router. Authentication is handled automatically using the `ANTHROPIC_API_KEY` environment variable.
+Access 13 Anthropic models through Mastra's model router. Authentication is handled automatically using the `ANTHROPIC_API_KEY` environment variable.
 
 Learn more in the [Anthropic documentation](https://docs.anthropic.com/en/docs/about-claude/models).
 
@@ -123,7 +123,7 @@ const response = await agent.generate("Hello!", {
 
 **inferenceGeo** (`"us" | "global" | undefined`)
 
-**fallbacks** (`{ model: string; max_tokens?: number | undefined; thinking?: Record<string, unknown> | undefined; output_config?: Record<string, unknown> | undefined; speed?: "fast" | "standard" | undefined; }[] | undefined`)
+**fallbacks** (`"default" | { model: string; max_tokens?: number | undefined; thinking?: Record<string, unknown> | undefined; output_config?: Record<string, unknown> | undefined; speed?: "fast" | "standard" | undefined; }[] | undefined`)
 
 **anthropicBeta** (`string[] | undefined`)
 

package/.docs/models/providers/cortecs.md

@@ -2,7 +2,7 @@
 
 # ![Cortecs logo](https://models.dev/logos/cortecs.svg)Cortecs
 
-Access 105 Cortecs models through Mastra's model router. Authentication is handled automatically using the `CORTECS_API_KEY` environment variable.
+Access 106 Cortecs models through Mastra's model router. Authentication is handled automatically using the `CORTECS_API_KEY` environment variable.
 
 Learn more in the [Cortecs documentation](https://cortecs.ai).
 
@@ -59,6 +59,7 @@ for await (const chunk of stream) {
 | `cortecs/gemini-2.5-pro`                      | 1.0M    |       |           |       |       |       | $1         | $10         |
 | `cortecs/gemini-3.1-flash-lite`               | 1.0M    |       |           |       |       |       | $0.27      | $2          |
 | `cortecs/gemini-3.5-flash`                    | 1.0M    |       |           |       |       |       | $1         | $9          |
+| `cortecs/gemini-3.5-flash-lite`               | 1.0M    |       |           |       |       |       | $0.33      | $3          |
 | `cortecs/gemma-3-27b-it`                      | 131K    |       |           |       |       |       | $0.10      | $0.30       |
 | `cortecs/gemma-4-26b-a4b-it`                  | 262K    |       |           |       |       |       | $0.11      | $0.56       |
 | `cortecs/gemma-4-31b-it`                      | 262K    |       |           |       |       |       | $0.22      | $0.39       |

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

@@ -2,7 +2,7 @@
 
 # ![Deep Infra logo](https://models.dev/logos/deepinfra.svg)Deep Infra
 
-Access 48 Deep Infra models through Mastra's model router. Authentication is handled automatically using the `DEEPINFRA_API_KEY` environment variable.
+Access 51 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).
 
@@ -35,6 +35,8 @@ for await (const chunk of stream) {
 | Model                                                         | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
 | ------------------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
 | `deepinfra/deepseek-ai/DeepSeek-R1-0528`                      | 164K    |       |           |       |       |       | $0.50      | $2          |
+| `deepinfra/deepseek-ai/DeepSeek-V3`                           | 164K    |       |           |       |       |       | $0.32      | $0.89       |
+| `deepinfra/deepseek-ai/DeepSeek-V3.1`                         | 164K    |       |           |       |       |       | $0.25      | $0.95       |
 | `deepinfra/deepseek-ai/DeepSeek-V3.2`                         | 164K    |       |           |       |       |       | $0.26      | $0.38       |
 | `deepinfra/deepseek-ai/DeepSeek-V4-Flash`                     | 1.0M    |       |           |       |       |       | $0.09      | $0.18       |
 | `deepinfra/deepseek-ai/DeepSeek-V4-Flash-0731`                | 1.0M    |       |           |       |       |       | $0.09      | $0.18       |
@@ -46,14 +48,15 @@ for await (const chunk of stream) {
 | `deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8` | 1.0M    |       |           |       |       |       | $0.20      | $0.80       |
 | `deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct`         | 328K    |       |           |       |       |       | $0.10      | $0.30       |
 | `deepinfra/MiniMaxAI/MiniMax-M2.7`                            | 197K    |       |           |       |       |       | $0.25      | $1          |
-| `deepinfra/MiniMaxAI/MiniMax-M3`                              | 524K    |       |           |       |       |       | $0.30      | $1          |
+| `deepinfra/MiniMaxAI/MiniMax-M3`                              | 524K    |       |           |       |       |       | $0.28      | $1          |
 | `deepinfra/moonshotai/Kimi-K2.5`                              | 262K    |       |           |       |       |       | $0.45      | $2          |
 | `deepinfra/moonshotai/Kimi-K2.6`                              | 262K    |       |           |       |       |       | $0.75      | $4          |
-| `deepinfra/moonshotai/Kimi-K2.7-Code`                         | 262K    |       |           |       |       |       | $0.74      | $4          |
+| `deepinfra/moonshotai/Kimi-K2.7-Code`                         | 262K    |       |           |       |       |       | $0.68      | $3          |
 | `deepinfra/moonshotai/Kimi-K3`                                | 1.0M    |       |           |       |       |       | $3         | $14         |
 | `deepinfra/nvidia/Nemotron-3-Nano-30B-A3B`                    | 262K    |       |           |       |       |       | $0.05      | $0.20       |
 | `deepinfra/openai/gpt-oss-120b`                               | 131K    |       |           |       |       |       | $0.04      | $0.17       |
 | `deepinfra/openai/gpt-oss-20b`                                | 131K    |       |           |       |       |       | $0.03      | $0.14       |
+| `deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507`                | 262K    |       |           |       |       |       | $0.09      | $0.55       |
 | `deepinfra/Qwen/Qwen3-32B`                                    | 41K     |       |           |       |       |       | $0.08      | $0.28       |
 | `deepinfra/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo`         | 262K    |       |           |       |       |       | $0.30      | $1          |
 | `deepinfra/Qwen/Qwen3-Max`                                    | 256K    |       |           |       |       |       | $1         | $6          |