@mastra/mcp-docs-server 1.1.35-alpha.8 → 1.1.36-alpha.1

package/.docs/models/providers/claudinio.md

@@ -0,0 +1,71 @@
+# ![Claudinio logo](https://models.dev/logos/claudinio.svg)Claudinio
+
+Access 1 Claudinio model through Mastra's model router. Authentication is handled automatically using the `CLAUDINIO_API_KEY` environment variable.
+
+Learn more in the [Claudinio documentation](https://claudin.io).
+
+```bash
+CLAUDINIO_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: "claudinio/claudinio"
+});
+
+// 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 [Claudinio documentation](https://claudin.io) for details.
+
+## Models
+
+| Model                 | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
+| --------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
+| `claudinio/claudinio` | 256K    |       |           |       |       |       | $0.50      | $2          |
+
+## Advanced configuration
+
+### Custom headers
+
+```typescript
+const agent = new Agent({
+  id: "custom-agent",
+  name: "custom-agent",
+  model: {
+    url: "https://api.claudin.io/v1",
+    id: "claudinio/claudinio",
+    apiKey: process.env.CLAUDINIO_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
+      ? "claudinio/claudinio"
+      : "claudinio/claudinio";
+  }
+});
+```

package/.docs/models/providers/databricks.md

@@ -0,0 +1,96 @@
+# ![Databricks logo](https://models.dev/logos/databricks.svg)Databricks
+
+Access 25 Databricks models through Mastra's model router. Authentication is handled automatically using the `DATABRICKS_TOKEN` environment variable. Configure `DATABRICKS_HOST` as well.
+
+Learn more in the [Databricks documentation](https://docs.databricks.com/aws/en/machine-learning/foundation-models/).
+
+```bash
+DATABRICKS_HOST=your-value
+DATABRICKS_TOKEN=your-api-token
+```
+
+```typescript
+import { Agent } from "@mastra/core/agent";
+
+const agent = new Agent({
+  id: "my-agent",
+  name: "My Agent",
+  instructions: "You are a helpful assistant",
+  model: "databricks/databricks-claude-haiku-4-5"
+});
+
+// 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 [Databricks documentation](https://docs.databricks.com/aws/en/machine-learning/foundation-models/) for details.
+
+## Models
+
+| Model                                         | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
+| --------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
+| `databricks/databricks-claude-haiku-4-5`      | 200K    |       |           |       |       |       | $1         | $5          |
+| `databricks/databricks-claude-opus-4-1`       | 200K    |       |           |       |       |       | $15        | $75         |
+| `databricks/databricks-claude-opus-4-5`       | 200K    |       |           |       |       |       | $5         | $25         |
+| `databricks/databricks-claude-opus-4-6`       | 1.0M    |       |           |       |       |       | $5         | $25         |
+| `databricks/databricks-claude-opus-4-7`       | 1.0M    |       |           |       |       |       | $5         | $25         |
+| `databricks/databricks-claude-sonnet-4`       | 200K    |       |           |       |       |       | $3         | $15         |
+| `databricks/databricks-claude-sonnet-4-5`     | 200K    |       |           |       |       |       | $3         | $15         |
+| `databricks/databricks-claude-sonnet-4-6`     | 1.0M    |       |           |       |       |       | $3         | $15         |
+| `databricks/databricks-gemini-2-5-flash`      | 1.0M    |       |           |       |       |       | $0.30      | $3          |
+| `databricks/databricks-gemini-2-5-pro`        | 1.0M    |       |           |       |       |       | $1         | $10         |
+| `databricks/databricks-gemini-3-1-flash-lite` | 1.0M    |       |           |       |       |       | $0.25      | $2          |
+| `databricks/databricks-gemini-3-1-pro`        | 1.0M    |       |           |       |       |       | $2         | $12         |
+| `databricks/databricks-gemini-3-flash`        | 1.0M    |       |           |       |       |       | $0.50      | $3          |
+| `databricks/databricks-gemini-3-pro`          | 1.0M    |       |           |       |       |       | $2         | $12         |
+| `databricks/databricks-gpt-5`                 | 400K    |       |           |       |       |       | $1         | $10         |
+| `databricks/databricks-gpt-5-1`               | 400K    |       |           |       |       |       | $1         | $10         |
+| `databricks/databricks-gpt-5-2`               | 400K    |       |           |       |       |       | $2         | $14         |
+| `databricks/databricks-gpt-5-4`               | 1.1M    |       |           |       |       |       | $3         | $15         |
+| `databricks/databricks-gpt-5-4-mini`          | 400K    |       |           |       |       |       | $0.75      | $5          |
+| `databricks/databricks-gpt-5-4-nano`          | 400K    |       |           |       |       |       | $0.20      | $1          |
+| `databricks/databricks-gpt-5-5`               | 1.1M    |       |           |       |       |       | $5         | $30         |
+| `databricks/databricks-gpt-5-mini`            | 400K    |       |           |       |       |       | $0.25      | $2          |
+| `databricks/databricks-gpt-5-nano`            | 400K    |       |           |       |       |       | $0.05      | $0.40       |
+| `databricks/databricks-gpt-oss-120b`          | 131K    |       |           |       |       |       | $0.07      | $0.28       |
+| `databricks/databricks-gpt-oss-20b`           | 131K    |       |           |       |       |       | $0.05      | $0.20       |
+
+## Advanced configuration
+
+### Custom headers
+
+```typescript
+const agent = new Agent({
+  id: "custom-agent",
+  name: "custom-agent",
+  model: {
+    url: "https://${DATABRICKS_HOST}/ai-gateway/mlflow/v1",
+    id: "databricks/databricks-claude-haiku-4-5",
+    apiKey: process.env.DATABRICKS_TOKEN,
+    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
+      ? "databricks/databricks-gpt-oss-20b"
+      : "databricks/databricks-claude-haiku-4-5";
+  }
+});
+```

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

@@ -1,6 +1,6 @@
 # ![Deep Infra logo](https://models.dev/logos/deepinfra.svg)Deep Infra
 
-Access 36 Deep Infra models through Mastra's model router. Authentication is handled automatically using the `DEEPINFRA_API_KEY` environment variable.
+Access 38 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).
 
@@ -62,6 +62,8 @@ for await (const chunk of stream) {
 | `deepinfra/Qwen/Qwen3.5-35B-A3B`                              | 262K    |       |           |       |       |       | $0.20      | $0.95       |
 | `deepinfra/Qwen/Qwen3.5-397B-A17B`                            | 262K    |       |           |       |       |       | $0.54      | $3          |
 | `deepinfra/Qwen/Qwen3.6-35B-A3B`                              | 262K    |       |           |       |       |       | $0.20      | $1          |
+| `deepinfra/xiaomi/mimo-v2.5`                                  | 262K    |       |           |       |       |       | $0.40      | $2          |
+| `deepinfra/xiaomi/mimo-v2.5-pro`                              | 1.0M    |       |           |       |       |       | $1         | $3          |
 | `deepinfra/zai-org/GLM-4.6`                                   | 205K    |       |           |       |       |       | $0.43      | $2          |
 | `deepinfra/zai-org/GLM-4.6V`                                  | 205K    |       |           |       |       |       | $0.30      | $0.90       |
 | `deepinfra/zai-org/GLM-4.7`                                   | 203K    |       |           |       |       |       | $0.43      | $2          |

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 64 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` | —       |       |           |       |       |       | —          | —           |
@@ -62,11 +64,14 @@ for await (const chunk of stream) {
 | `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       |
@@ -87,11 +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     |       |           |       |       |       | —          | —           |

package/.docs/models/providers/firepass.md

@@ -0,0 +1,71 @@
+# ![Fireworks (Firepass) logo](https://models.dev/logos/firepass.svg)Fireworks (Firepass)
+
+Access 1 Fireworks (Firepass) model through Mastra's model router. Authentication is handled automatically using the `FIREPASS_API_KEY` environment variable.
+
+Learn more in the [Fireworks (Firepass) documentation](https://docs.fireworks.ai/firepass).
+
+```bash
+FIREPASS_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: "firepass/accounts/fireworks/routers/kimi-k2p6-turbo"
+});
+
+// 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 [Fireworks (Firepass) documentation](https://docs.fireworks.ai/firepass) for details.
+
+## Models
+
+| Model                                                 | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
+| ----------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
+| `firepass/accounts/fireworks/routers/kimi-k2p6-turbo` | 262K    |       |           |       |       |       | —          | —           |
+
+## Advanced configuration
+
+### Custom headers
+
+```typescript
+const agent = new Agent({
+  id: "custom-agent",
+  name: "custom-agent",
+  model: {
+    url: "https://api.fireworks.ai/inference/v1/",
+    id: "firepass/accounts/fireworks/routers/kimi-k2p6-turbo",
+    apiKey: process.env.FIREPASS_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
+      ? "firepass/accounts/fireworks/routers/kimi-k2p6-turbo"
+      : "firepass/accounts/fireworks/routers/kimi-k2p6-turbo";
+  }
+});
+```

package/.docs/models/providers/google.md

@@ -1,8 +1,8 @@
 # ![Google logo](https://models.dev/logos/google.svg)Google
 
-Access 37 Google models through Mastra's model router. Authentication is handled automatically using the `GOOGLE_GENERATIVE_AI_API_KEY` environment variable.
+Access 38 Google models through Mastra's model router. Authentication is handled automatically using the `GOOGLE_GENERATIVE_AI_API_KEY` environment variable.
 
-Learn more in the [Google documentation](https://ai.google.dev/gemini-api/docs/pricing).
+Learn more in the [Google documentation](https://ai.google.dev/gemini-api/docs/models).
 
 ```bash
 GOOGLE_GENERATIVE_AI_API_KEY=your-api-key
@@ -53,7 +53,8 @@ for await (const chunk of stream) {
 | `google/gemini-2.5-pro-preview-tts`                 | 8K      |       |           |       |       |       | $1         | $20         |
 | `google/gemini-3-flash-preview`                     | 1.0M    |       |           |       |       |       | $0.50      | $3          |
 | `google/gemini-3-pro-preview`                       | 1.0M    |       |           |       |       |       | $2         | $12         |
-| `google/gemini-3.1-flash-image-preview`             | 131K    |       |           |       |       |       | $0.25      | $60         |
+| `google/gemini-3.1-flash-image-preview`             | 131K    |       |           |       |       |       | $0.50      | $60         |
+| `google/gemini-3.1-flash-lite`                      | 1.0M    |       |           |       |       |       | $0.25      | $2          |
 | `google/gemini-3.1-flash-lite-preview`              | 1.0M    |       |           |       |       |       | $0.25      | $2          |
 | `google/gemini-3.1-pro-preview`                     | 1.0M    |       |           |       |       |       | $2         | $12         |
 | `google/gemini-3.1-pro-preview-customtools`         | 1.0M    |       |           |       |       |       | $2         | $12         |

package/.docs/models/providers/kilo.md

@@ -1,6 +1,6 @@
 # ![Kilo Gateway logo](https://models.dev/logos/kilo.svg)Kilo Gateway
 
-Access 355 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
+Access 357 Kilo Gateway models through Mastra's model router. Authentication is handled automatically using the `KILO_API_KEY` environment variable.
 
 Learn more in the [Kilo Gateway documentation](https://kilo.ai).
 
@@ -50,7 +50,6 @@ for await (const chunk of stream) {
 | `kilo/alfredpros/codellama-7b-instruct-solidity`          | 4K      |       |           |       |       |       | $0.80      | $1          |
 | `kilo/alibaba/tongyi-deepresearch-30b-a3b`                | 131K    |       |           |       |       |       | $0.09      | $0.45       |
 | `kilo/allenai/olmo-3-32b-think`                           | 66K     |       |           |       |       |       | $0.15      | $0.50       |
-| `kilo/allenai/olmo-3.1-32b-instruct`                      | 66K     |       |           |       |       |       | $0.20      | $0.60       |
 | `kilo/alpindale/goliath-120b`                             | 6K      |       |           |       |       |       | $4         | $8          |
 | `kilo/amazon/nova-2-lite-v1`                              | 1.0M    |       |           |       |       |       | $0.30      | $3          |
 | `kilo/amazon/nova-lite-v1`                                | 300K    |       |           |       |       |       | $0.06      | $0.24       |
@@ -79,6 +78,7 @@ for await (const chunk of stream) {
 | `kilo/arcee-ai/trinity-large-thinking`                    | 262K    |       |           |       |       |       | $0.22      | $0.85       |
 | `kilo/arcee-ai/trinity-mini`                              | 131K    |       |           |       |       |       | $0.04      | $0.15       |
 | `kilo/arcee-ai/virtuoso-large`                            | 131K    |       |           |       |       |       | $0.75      | $1          |
+| `kilo/baidu/cobuddy:free`                                 | 131K    |       |           |       |       |       | —          | —           |
 | `kilo/baidu/ernie-4.5-21b-a3b`                            | 120K    |       |           |       |       |       | $0.07      | $0.28       |
 | `kilo/baidu/ernie-4.5-21b-a3b-thinking`                   | 131K    |       |           |       |       |       | $0.07      | $0.28       |
 | `kilo/baidu/ernie-4.5-300b-a47b`                          | 123K    |       |           |       |       |       | $0.28      | $1          |
@@ -161,6 +161,7 @@ for await (const chunk of stream) {
 | `kilo/meta-llama/llama-guard-3-8b`                        | 131K    |       |           |       |       |       | $0.02      | $0.06       |
 | `kilo/meta-llama/llama-guard-4-12b`                       | 164K    |       |           |       |       |       | $0.18      | $0.18       |
 | `kilo/microsoft/phi-4`                                    | 16K     |       |           |       |       |       | $0.06      | $0.14       |
+| `kilo/microsoft/phi-4-mini-instruct`                      | 128K    |       |           |       |       |       | $0.08      | $0.35       |
 | `kilo/microsoft/wizardlm-2-8x22b`                         | 66K     |       |           |       |       |       | $0.62      | $0.62       |
 | `kilo/minimax/minimax-01`                                 | 1.0M    |       |           |       |       |       | $0.20      | $1          |
 | `kilo/minimax/minimax-m1`                                 | 1.0M    |       |           |       |       |       | $0.40      | $2          |
@@ -182,6 +183,7 @@ for await (const chunk of stream) {
 | `kilo/mistralai/mistral-large-2411`                       | 131K    |       |           |       |       |       | $2         | $6          |
 | `kilo/mistralai/mistral-large-2512`                       | 262K    |       |           |       |       |       | $0.50      | $2          |
 | `kilo/mistralai/mistral-medium-3`                         | 131K    |       |           |       |       |       | $0.40      | $2          |
+| `kilo/mistralai/mistral-medium-3-5`                       | 262K    |       |           |       |       |       | $2         | $8          |
 | `kilo/mistralai/mistral-medium-3.1`                       | 131K    |       |           |       |       |       | $0.40      | $2          |
 | `kilo/mistralai/mistral-nemo`                             | 131K    |       |           |       |       |       | $0.02      | $0.04       |
 | `kilo/mistralai/mistral-saba`                             | 33K     |       |           |       |       |       | $0.20      | $0.60       |
@@ -197,7 +199,7 @@ for await (const chunk of stream) {
 | `kilo/moonshotai/kimi-k2-0905`                            | 131K    |       |           |       |       |       | $0.40      | $2          |
 | `kilo/moonshotai/kimi-k2-thinking`                        | 131K    |       |           |       |       |       | $0.47      | $2          |
 | `kilo/moonshotai/kimi-k2.5`                               | 262K    |       |           |       |       |       | $0.45      | $2          |
-| `kilo/moonshotai/kimi-k2.6`                               | 262K    |       |           |       |       |       | $0.95      | $4          |
+| `kilo/moonshotai/kimi-k2.6`                               | 262K    |       |           |       |       |       | $0.75      | $4          |
 | `kilo/morph/morph-v3-fast`                                | 82K     |       |           |       |       |       | $0.80      | $1          |
 | `kilo/morph/morph-v3-large`                               | 262K    |       |           |       |       |       | $0.90      | $2          |
 | `kilo/nex-agi/deepseek-v3.1-nex-n1`                       | 131K    |       |           |       |       |       | $0.27      | $1          |
@@ -212,7 +214,6 @@ for await (const chunk of stream) {
 | `kilo/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free` | 256K    |       |           |       |       |       | —          | —           |
 | `kilo/nvidia/nemotron-3-super-120b-a12b`                  | 262K    |       |           |       |       |       | $0.10      | $0.50       |
 | `kilo/nvidia/nemotron-3-super-120b-a12b:free`             | 262K    |       |           |       |       |       | —          | —           |
-| `kilo/nvidia/nemotron-nano-12b-v2-vl`                     | 131K    |       |           |       |       |       | $0.20      | $0.60       |
 | `kilo/nvidia/nemotron-nano-9b-v2`                         | 131K    |       |           |       |       |       | $0.04      | $0.16       |
 | `kilo/openai/gpt-3.5-turbo`                               | 16K     |       |           |       |       |       | $0.50      | $2          |
 | `kilo/openai/gpt-3.5-turbo-0613`                          | 4K      |       |           |       |       |       | $1         | $2          |
@@ -263,6 +264,7 @@ for await (const chunk of stream) {
 | `kilo/openai/gpt-5.5-pro`                                 | 1.1M    |       |           |       |       |       | $30        | $180        |
 | `kilo/openai/gpt-audio`                                   | 128K    |       |           |       |       |       | $3         | $10         |
 | `kilo/openai/gpt-audio-mini`                              | 128K    |       |           |       |       |       | $0.60      | $2          |
+| `kilo/openai/gpt-chat-latest`                             | 400K    |       |           |       |       |       | $5         | $30         |
 | `kilo/openai/gpt-oss-120b`                                | 131K    |       |           |       |       |       | $0.04      | $0.19       |
 | `kilo/openai/gpt-oss-20b`                                 | 131K    |       |           |       |       |       | $0.03      | $0.14       |
 | `kilo/openai/gpt-oss-safeguard-20b`                       | 131K    |       |           |       |       |       | $0.07      | $0.30       |

package/.docs/models/providers/llmgateway.md

@@ -1,6 +1,6 @@
 # ![LLM Gateway logo](https://models.dev/logos/llmgateway.svg)LLM Gateway
 
-Access 189 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
+Access 195 LLM Gateway models through Mastra's model router. Authentication is handled automatically using the `LLMGATEWAY_API_KEY` environment variable.
 
 Learn more in the [LLM Gateway documentation](https://llmgateway.io/docs).
 
@@ -66,6 +66,7 @@ for await (const chunk of stream) {
 | `llmgateway/gemini-2.5-flash-lite-preview-09-2025` | 1.0M    |       |           |       |       |       | $0.10      | $0.40       |
 | `llmgateway/gemini-2.5-pro`                        | 1.0M    |       |           |       |       |       | $1         | $10         |
 | `llmgateway/gemini-3-flash-preview`                | 1.0M    |       |           |       |       |       | $0.50      | $3          |
+| `llmgateway/gemini-3.1-flash-lite`                 | 1.0M    |       |           |       |       |       | $0.25      | $2          |
 | `llmgateway/gemini-3.1-flash-lite-preview`         | 1.0M    |       |           |       |       |       | $0.25      | $2          |
 | `llmgateway/gemini-3.1-pro-preview`                | 1.0M    |       |           |       |       |       | $2         | $12         |
 | `llmgateway/gemini-pro-latest`                     | 1.0M    |       |           |       |       |       | $2         | $12         |
@@ -132,6 +133,7 @@ for await (const chunk of stream) {
 | `llmgateway/grok-4-1-fast-reasoning`               | 2.0M    |       |           |       |       |       | $0.20      | $0.50       |
 | `llmgateway/grok-4-20-beta-0309-non-reasoning`     | 2.0M    |       |           |       |       |       | $2         | $6          |
 | `llmgateway/grok-4-20-beta-0309-reasoning`         | 2.0M    |       |           |       |       |       | $2         | $6          |
+| `llmgateway/grok-4-3`                              | 1.0M    |       |           |       |       |       | $1         | $3          |
 | `llmgateway/grok-4-fast`                           | 2.0M    |       |           |       |       |       | $0.20      | $0.50       |
 | `llmgateway/grok-4-fast-non-reasoning`             | 2.0M    |       |           |       |       |       | $0.20      | $0.50       |
 | `llmgateway/grok-4-fast-reasoning`                 | 2.0M    |       |           |       |       |       | $0.20      | $0.50       |
@@ -154,6 +156,10 @@ for await (const chunk of stream) {
 | `llmgateway/llama-4-scout`                         | 33K     |       |           |       |       |       | $0.18      | $0.59       |
 | `llmgateway/llama-4-scout-17b-instruct`            | 8K      |       |           |       |       |       | $0.17      | $0.66       |
 | `llmgateway/mimo-v2-flash`                         | 262K    |       |           |       |       |       | $0.10      | $0.30       |
+| `llmgateway/mimo-v2-omni`                          | 262K    |       |           |       |       |       | $0.40      | $2          |
+| `llmgateway/mimo-v2-pro`                           | 1.0M    |       |           |       |       |       | $1         | $3          |
+| `llmgateway/mimo-v2.5`                             | 1.0M    |       |           |       |       |       | $0.40      | $2          |
+| `llmgateway/mimo-v2.5-pro`                         | 1.0M    |       |           |       |       |       | $1         | $3          |
 | `llmgateway/minimax-m2`                            | 197K    |       |           |       |       |       | $0.30      | $1          |
 | `llmgateway/minimax-m2.1`                          | 205K    |       |           |       |       |       | $0.30      | $1          |
 | `llmgateway/minimax-m2.1-lightning`                | 197K    |       |           |       |       |       | $0.12      | $0.48       |
@@ -213,7 +219,7 @@ for await (const chunk of stream) {
 | `llmgateway/qwen3-vl-plus`                         | 262K    |       |           |       |       |       | $0.20      | $2          |
 | `llmgateway/qwen3.6-35b-a3b`                       | 262K    |       |           |       |       |       | $0.25      | $1          |
 | `llmgateway/qwen3.6-max-preview`                   | 262K    |       |           |       |       |       | $1         | $8          |
-| `llmgateway/qwen3.6-plus`                          | 1.0M    |       |           |       |       |       | $0.28      | $2          |
+| `llmgateway/qwen3.6-plus`                          | 1.0M    |       |           |       |       |       | $0.50      | $3          |
 | `llmgateway/qwen35-397b-a17b`                      | 262K    |       |           |       |       |       | $0.60      | $4          |
 | `llmgateway/qwq-plus`                              | 131K    |       |           |       |       |       | $0.80      | $2          |
 | `llmgateway/seed-1-6-250615`                       | 256K    |       |           |       |       |       | $0.25      | $2          |

package/.docs/models/providers/nebius.md

@@ -1,6 +1,6 @@
 # ![Nebius Token Factory logo](https://models.dev/logos/nebius.svg)Nebius Token Factory
 
-Access 49 Nebius Token Factory models through Mastra's model router. Authentication is handled automatically using the `NEBIUS_API_KEY` environment variable.
+Access 31 Nebius Token Factory models through Mastra's model router. Authentication is handled automatically using the `NEBIUS_API_KEY` environment variable.
 
 Learn more in the [Nebius Token Factory documentation](https://docs.tokenfactory.nebius.com/).
 
@@ -15,7 +15,7 @@ const agent = new Agent({
   id: "my-agent",
   name: "My Agent",
   instructions: "You are a helpful assistant",
-  model: "nebius/BAAI/bge-en-icl"
+  model: "nebius/MiniMaxAI/MiniMax-M2.5"
 });
 
 // Generate a response
@@ -32,57 +32,39 @@ for await (const chunk of stream) {
 
 ## Models
 
-| Model                                               | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
-| --------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
-| `nebius/BAAI/bge-en-icl`                            | 33K     |       |           |       |       |       | $0.01      | —           |
-| `nebius/BAAI/bge-multilingual-gemma2`               | 8K      |       |           |       |       |       | $0.01      | —           |
-| `nebius/black-forest-labs/flux-dev`                 | 77      |       |           |       |       |       | —          | —           |
-| `nebius/black-forest-labs/flux-schnell`             | 77      |       |           |       |       |       | —          | —           |
-| `nebius/deepseek-ai/DeepSeek-R1-0528`               | 128K    |       |           |       |       |       | $0.80      | $2          |
-| `nebius/deepseek-ai/DeepSeek-R1-0528-fast`          | 131K    |       |           |       |       |       | $2         | $6          |
-| `nebius/deepseek-ai/DeepSeek-V3-0324`               | 128K    |       |           |       |       |       | $0.50      | $2          |
-| `nebius/deepseek-ai/DeepSeek-V3-0324-fast`          | 128K    |       |           |       |       |       | $0.75      | $2          |
-| `nebius/deepseek-ai/DeepSeek-V3.2`                  | 163K    |       |           |       |       |       | $0.30      | $0.45       |
-| `nebius/google/gemma-2-2b-it`                       | 8K      |       |           |       |       |       | $0.02      | $0.06       |
-| `nebius/google/gemma-2-9b-it-fast`                  | 8K      |       |           |       |       |       | $0.03      | $0.09       |
-| `nebius/google/gemma-3-27b-it`                      | 110K    |       |           |       |       |       | $0.10      | $0.30       |
-| `nebius/google/gemma-3-27b-it-fast`                 | 110K    |       |           |       |       |       | $0.20      | $0.60       |
-| `nebius/intfloat/e5-mistral-7b-instruct`            | 33K     |       |           |       |       |       | $0.01      | —           |
-| `nebius/meta-llama/Llama-3.3-70B-Instruct`          | 128K    |       |           |       |       |       | $0.13      | $0.40       |
-| `nebius/meta-llama/Llama-3.3-70B-Instruct-fast`     | 128K    |       |           |       |       |       | $0.25      | $0.75       |
-| `nebius/meta-llama/Llama-Guard-3-8B`                | 8K      |       |           |       |       |       | $0.02      | $0.06       |
-| `nebius/meta-llama/Meta-Llama-3.1-8B-Instruct`      | 128K    |       |           |       |       |       | $0.02      | $0.06       |
-| `nebius/meta-llama/Meta-Llama-3.1-8B-Instruct-fast` | 128K    |       |           |       |       |       | $0.03      | $0.09       |
-| `nebius/MiniMaxAI/MiniMax-M2.1`                     | 128K    |       |           |       |       |       | $0.30      | $1          |
-| `nebius/moonshotai/Kimi-K2-Instruct`                | 200K    |       |           |       |       |       | $0.50      | $2          |
-| `nebius/moonshotai/Kimi-K2-Thinking`                | 128K    |       |           |       |       |       | $0.60      | $3          |
-| `nebius/moonshotai/Kimi-K2.5`                       | 256K    |       |           |       |       |       | $0.50      | $3          |
-| `nebius/moonshotai/Kimi-K2.5-fast`                  | 256K    |       |           |       |       |       | $0.50      | $3          |
-| `nebius/NousResearch/Hermes-4-405B`                 | 128K    |       |           |       |       |       | $1         | $3          |
-| `nebius/NousResearch/Hermes-4-70B`                  | 128K    |       |           |       |       |       | $0.13      | $0.40       |
-| `nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1`    | 128K    |       |           |       |       |       | $0.60      | $2          |
-| `nebius/nvidia/nemotron-3-super-120b-a12b`          | 256K    |       |           |       |       |       | $0.30      | $0.90       |
-| `nebius/nvidia/Nemotron-Nano-V2-12b`                | 32K     |       |           |       |       |       | $0.07      | $0.20       |
-| `nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B`      | 32K     |       |           |       |       |       | $0.06      | $0.24       |
-| `nebius/openai/gpt-oss-120b`                        | 128K    |       |           |       |       |       | $0.15      | $0.60       |
-| `nebius/openai/gpt-oss-20b`                         | 128K    |       |           |       |       |       | $0.05      | $0.20       |
-| `nebius/PrimeIntellect/INTELLECT-3`                 | 128K    |       |           |       |       |       | $0.20      | $1          |
-| `nebius/Qwen/Qwen2.5-Coder-7B-fast`                 | 128K    |       |           |       |       |       | $0.03      | $0.09       |
-| `nebius/Qwen/Qwen2.5-VL-72B-Instruct`               | 128K    |       |           |       |       |       | $0.25      | $0.75       |
-| `nebius/Qwen/Qwen3-235B-A22B-Instruct-2507`         | 262K    |       |           |       |       |       | $0.20      | $0.60       |
-| `nebius/Qwen/Qwen3-235B-A22B-Thinking-2507`         | 262K    |       |           |       |       |       | $0.20      | $0.80       |
-| `nebius/Qwen/Qwen3-30B-A3B-Instruct-2507`           | 128K    |       |           |       |       |       | $0.10      | $0.30       |
-| `nebius/Qwen/Qwen3-30B-A3B-Thinking-2507`           | 128K    |       |           |       |       |       | $0.10      | $0.30       |
-| `nebius/Qwen/Qwen3-32B`                             | 128K    |       |           |       |       |       | $0.10      | $0.30       |
-| `nebius/Qwen/Qwen3-32B-fast`                        | 128K    |       |           |       |       |       | $0.20      | $0.60       |
-| `nebius/Qwen/Qwen3-Coder-30B-A3B-Instruct`          | 128K    |       |           |       |       |       | $0.10      | $0.30       |
-| `nebius/Qwen/Qwen3-Coder-480B-A35B-Instruct`        | 262K    |       |           |       |       |       | $0.40      | $2          |
-| `nebius/Qwen/Qwen3-Embedding-8B`                    | 33K     |       |           |       |       |       | $0.01      | —           |
-| `nebius/Qwen/Qwen3-Next-80B-A3B-Thinking`           | 128K    |       |           |       |       |       | $0.15      | $1          |
-| `nebius/zai-org/GLM-4.5`                            | 128K    |       |           |       |       |       | $0.60      | $2          |
-| `nebius/zai-org/GLM-4.5-Air`                        | 128K    |       |           |       |       |       | $0.20      | $1          |
-| `nebius/zai-org/GLM-4.7-FP8`                        | 128K    |       |           |       |       |       | $0.40      | $2          |
-| `nebius/zai-org/GLM-5`                              | 200K    |       |           |       |       |       | $1         | $3          |
+| Model                                            | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
+| ------------------------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
+| `nebius/deepseek-ai/DeepSeek-V3.2`               | 163K    |       |           |       |       |       | $0.30      | $0.45       |
+| `nebius/deepseek-ai/DeepSeek-V3.2-fast`          | 8K      |       |           |       |       |       | $0.40      | $2          |
+| `nebius/deepseek-ai/DeepSeek-V4-Pro`             | 1.0M    |       |           |       |       |       | $2         | $4          |
+| `nebius/google/gemma-2-2b-it`                    | 8K      |       |           |       |       |       | $0.02      | $0.06       |
+| `nebius/google/gemma-3-27b-it`                   | 110K    |       |           |       |       |       | $0.10      | $0.30       |
+| `nebius/meta-llama/Llama-3.3-70B-Instruct`       | 128K    |       |           |       |       |       | $0.13      | $0.40       |
+| `nebius/meta-llama/Meta-Llama-3.1-8B-Instruct`   | 128K    |       |           |       |       |       | $0.02      | $0.06       |
+| `nebius/MiniMaxAI/MiniMax-M2.5`                  | 197K    |       |           |       |       |       | $0.30      | $1          |
+| `nebius/MiniMaxAI/MiniMax-M2.5-fast`             | 8K      |       |           |       |       |       | $0.30      | $1          |
+| `nebius/moonshotai/Kimi-K2.5`                    | 256K    |       |           |       |       |       | $0.50      | $3          |
+| `nebius/moonshotai/Kimi-K2.5-fast`               | 256K    |       |           |       |       |       | $0.50      | $3          |
+| `nebius/NousResearch/Hermes-4-405B`              | 128K    |       |           |       |       |       | $1         | $3          |
+| `nebius/NousResearch/Hermes-4-70B`               | 128K    |       |           |       |       |       | $0.13      | $0.40       |
+| `nebius/nvidia/Llama-3_1-Nemotron-Ultra-253B-v1` | 128K    |       |           |       |       |       | $0.60      | $2          |
+| `nebius/nvidia/Nemotron-3-Nano-Omni`             | 66K     |       |           |       |       |       | $0.06      | $0.24       |
+| `nebius/nvidia/nemotron-3-super-120b-a12b`       | 256K    |       |           |       |       |       | $0.30      | $0.90       |
+| `nebius/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B`   | 32K     |       |           |       |       |       | $0.06      | $0.24       |
+| `nebius/openai/gpt-oss-120b`                     | 128K    |       |           |       |       |       | $0.15      | $0.60       |
+| `nebius/openai/gpt-oss-120b-fast`                | 8K      |       |           |       |       |       | $0.10      | $0.50       |
+| `nebius/PrimeIntellect/INTELLECT-3`              | 128K    |       |           |       |       |       | $0.20      | $1          |
+| `nebius/Qwen/Qwen2.5-VL-72B-Instruct`            | 128K    |       |           |       |       |       | $0.25      | $0.75       |
+| `nebius/Qwen/Qwen3-235B-A22B-Instruct-2507`      | 262K    |       |           |       |       |       | $0.20      | $0.60       |
+| `nebius/Qwen/Qwen3-235B-A22B-Thinking-2507-fast` | 8K      |       |           |       |       |       | $0.50      | $2          |
+| `nebius/Qwen/Qwen3-30B-A3B-Instruct-2507`        | 128K    |       |           |       |       |       | $0.10      | $0.30       |
+| `nebius/Qwen/Qwen3-32B`                          | 128K    |       |           |       |       |       | $0.10      | $0.30       |
+| `nebius/Qwen/Qwen3-Embedding-8B`                 | 33K     |       |           |       |       |       | $0.01      | —           |
+| `nebius/Qwen/Qwen3-Next-80B-A3B-Thinking`        | 128K    |       |           |       |       |       | $0.15      | $1          |
+| `nebius/Qwen/Qwen3-Next-80B-A3B-Thinking-fast`   | 8K      |       |           |       |       |       | $0.15      | $1          |
+| `nebius/Qwen/Qwen3.5-397B-A17B`                  | 262K    |       |           |       |       |       | $0.60      | $4          |
+| `nebius/Qwen/Qwen3.5-397B-A17B-fast`             | 8K      |       |           |       |       |       | $0.60      | $4          |
+| `nebius/zai-org/GLM-5`                           | 200K    |       |           |       |       |       | $1         | $3          |
 
 ## Advanced configuration
 
@@ -94,7 +76,7 @@ const agent = new Agent({
   name: "custom-agent",
   model: {
     url: "https://api.tokenfactory.nebius.com/v1",
-    id: "nebius/BAAI/bge-en-icl",
+    id: "nebius/MiniMaxAI/MiniMax-M2.5",
     apiKey: process.env.NEBIUS_API_KEY,
     headers: {
       "X-Custom-Header": "value"
@@ -113,7 +95,7 @@ const agent = new Agent({
     const useAdvanced = requestContext.task === "complex";
     return useAdvanced
       ? "nebius/zai-org/GLM-5"
-      : "nebius/BAAI/bge-en-icl";
+      : "nebius/MiniMaxAI/MiniMax-M2.5";
   }
 });
 ```