@mastra/mcp-docs-server 1.2.13-alpha.8 → 1.2.13

package/.docs/models/providers/groq.md

@@ -17,7 +17,7 @@ const agent = new Agent({
   id: "my-agent",
   name: "My Agent",
   instructions: "You are a helpful assistant",
-  model: "groq/canopylabs/orpheus-arabic-saudi"
+  model: "groq/allam-2-7b"
 });
 
 // Generate a response
@@ -32,23 +32,23 @@ for await (const chunk of stream) {
 
 ## Models
 
-| Model                                            | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
-| ------------------------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
-| `groq/canopylabs/orpheus-arabic-saudi`           | 4K      |       |           |       |       |       | —          | —           |
-| `groq/canopylabs/orpheus-v1-english`             | 4K      |       |           |       |       |       | —          | —           |
-| `groq/groq/compound`                             | 131K    |       |           |       |       |       | —          | —           |
-| `groq/groq/compound-mini`                        | 131K    |       |           |       |       |       | —          | —           |
-| `groq/llama-3.1-8b-instant`                      | 131K    |       |           |       |       |       | $0.05      | $0.08       |
-| `groq/llama-3.3-70b-versatile`                   | 131K    |       |           |       |       |       | $0.59      | $0.79       |
-| `groq/meta-llama/llama-4-scout-17b-16e-instruct` | 131K    |       |           |       |       |       | $0.11      | $0.34       |
-| `groq/meta-llama/llama-prompt-guard-2-22m`       | 512     |       |           |       |       |       | $0.03      | $0.03       |
-| `groq/meta-llama/llama-prompt-guard-2-86m`       | 512     |       |           |       |       |       | $0.04      | $0.04       |
-| `groq/openai/gpt-oss-120b`                       | 131K    |       |           |       |       |       | $0.15      | $0.60       |
-| `groq/openai/gpt-oss-20b`                        | 131K    |       |           |       |       |       | $0.07      | $0.30       |
-| `groq/openai/gpt-oss-safeguard-20b`              | 131K    |       |           |       |       |       | $0.07      | $0.30       |
-| `groq/qwen/qwen3-32b`                            | 131K    |       |           |       |       |       | $0.29      | $0.59       |
-| `groq/whisper-large-v3`                          | —       |       |           |       |       |       | —          | —           |
-| `groq/whisper-large-v3-turbo`                    | —       |       |           |       |       |       | —          | —           |
+| Model                                      | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
+| ------------------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
+| `groq/allam-2-7b`                          | 4K      |       |           |       |       |       | —          | —           |
+| `groq/canopylabs/orpheus-arabic-saudi`     | 4K      |       |           |       |       |       | —          | —           |
+| `groq/canopylabs/orpheus-v1-english`       | 4K      |       |           |       |       |       | —          | —           |
+| `groq/groq/compound`                       | 131K    |       |           |       |       |       | —          | —           |
+| `groq/groq/compound-mini`                  | 131K    |       |           |       |       |       | —          | —           |
+| `groq/llama-3.1-8b-instant`                | 131K    |       |           |       |       |       | $0.05      | $0.08       |
+| `groq/llama-3.3-70b-versatile`             | 131K    |       |           |       |       |       | $0.59      | $0.79       |
+| `groq/meta-llama/llama-prompt-guard-2-22m` | 512     |       |           |       |       |       | $0.03      | $0.03       |
+| `groq/meta-llama/llama-prompt-guard-2-86m` | 512     |       |           |       |       |       | $0.04      | $0.04       |
+| `groq/openai/gpt-oss-120b`                 | 131K    |       |           |       |       |       | $0.15      | $0.60       |
+| `groq/openai/gpt-oss-20b`                  | 131K    |       |           |       |       |       | $0.07      | $0.30       |
+| `groq/openai/gpt-oss-safeguard-20b`        | 131K    |       |           |       |       |       | $0.07      | $0.30       |
+| `groq/qwen/qwen3.6-27b`                    | 131K    |       |           |       |       |       | $0.60      | $3          |
+| `groq/whisper-large-v3`                    | —       |       |           |       |       |       | —          | —           |
+| `groq/whisper-large-v3-turbo`              | —       |       |           |       |       |       | —          | —           |
 
 ## Advanced configuration
 
@@ -60,7 +60,7 @@ const agent = new Agent({
   name: "custom-agent",
   model: {
     url: "https://api.groq.com/openai/v1",
-    id: "groq/canopylabs/orpheus-arabic-saudi",
+    id: "groq/allam-2-7b",
     apiKey: process.env.GROQ_API_KEY,
     headers: {
       "X-Custom-Header": "value"
@@ -79,7 +79,7 @@ const agent = new Agent({
     const useAdvanced = requestContext.task === "complex";
     return useAdvanced
       ? "groq/whisper-large-v3-turbo"
-      : "groq/canopylabs/orpheus-arabic-saudi";
+      : "groq/allam-2-7b";
   }
 });
 ```

package/.docs/models/providers/huggingface.md

@@ -2,7 +2,7 @@
 
 # ![Hugging Face logo](https://models.dev/logos/huggingface.svg)Hugging Face
 
-Access 55 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
+Access 57 Hugging Face models through Mastra's model router. Authentication is handled automatically using the `HF_TOKEN` environment variable.
 
 Learn more in the [Hugging Face documentation](https://huggingface.co).
 
@@ -40,6 +40,7 @@ for await (const chunk of stream) {
 | `huggingface/deepseek-ai/DeepSeek-R1-0528`        | 164K    |       |           |       |       |       | $3         | $5          |
 | `huggingface/deepseek-ai/DeepSeek-V3.2`           | 164K    |       |           |       |       |       | $0.28      | $0.40       |
 | `huggingface/deepseek-ai/DeepSeek-V4-Flash`       | 1.0M    |       |           |       |       |       | $0.14      | $0.28       |
+| `huggingface/deepseek-ai/DeepSeek-V4-Flash-0731`  | 1.0M    |       |           |       |       |       | $0.14      | $0.28       |
 | `huggingface/deepseek-ai/DeepSeek-V4-Pro`         | 1.0M    |       |           |       |       |       | $0.43      | $0.87       |
 | `huggingface/google/gemma-4-26B-A4B-it`           | 262K    |       |           |       |       |       | $0.13      | $0.40       |
 | `huggingface/google/gemma-4-31B-it`               | 262K    |       |           |       |       |       | $0.14      | $0.40       |
@@ -79,6 +80,7 @@ for await (const chunk of stream) {
 | `huggingface/stepfun-ai/Step-3.7-Flash`           | 262K    |       |           |       |       |       | $0.20      | $1          |
 | `huggingface/tencent/Hy3`                         | 262K    |       |           |       |       |       | $0.14      | $0.58       |
 | `huggingface/thinkingmachines/Inkling`            | 1.0M    |       |           |       |       |       | $1         | $4          |
+| `huggingface/thinkingmachines/Inkling-Small`      | 524K    |       |           |       |       |       | $0.50      | $1          |
 | `huggingface/XiaomiMiMo/MiMo-V2-Flash`            | 262K    |       |           |       |       |       | $0.10      | $0.30       |
 | `huggingface/XiaomiMiMo/MiMo-V2.5`                | 262K    |       |           |       |       |       | $0.40      | $2          |
 | `huggingface/XiaomiMiMo/MiMo-V2.5-Pro`            | 1.0M    |       |           |       |       |       | $1         | $3          |

package/.docs/models/providers/hyper.md

@@ -2,7 +2,7 @@
 
 # ![Charm Hyper logo](https://models.dev/logos/hyper.svg)Charm Hyper
 
-Access 23 Charm Hyper models through Mastra's model router. Authentication is handled automatically using the `HYPER_API_KEY` environment variable.
+Access 25 Charm Hyper models through Mastra's model router. Authentication is handled automatically using the `HYPER_API_KEY` environment variable.
 
 Learn more in the [Charm Hyper documentation](https://hyper.charm.land).
 
@@ -37,19 +37,20 @@ for await (const chunk of stream) {
 | Model                                                | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
 | ---------------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
 | `hyper/deepseek-v4-flash`                            | 1.0M    |       |           |       |       |       | $0.20      | $0.40       |
+| `hyper/deepseek-v4-flash-0731`                       | 1.0M    |       |           |       |       |       | $0.15      | $0.30       |
 | `hyper/deepseek-v4-pro`                              | 1.0M    |       |           |       |       |       | $2         | $5          |
-| `hyper/gemma-4-26b-a4b-it`                           | 256K    |       |           |       |       |       | $0.12      | $0.42       |
-| `hyper/glm-5`                                        | 203K    |       |           |       |       |       | $0.88      | $3          |
+| `hyper/gemma-4-26b-a4b-it`                           | 256K    |       |           |       |       |       | $0.13      | $0.42       |
+| `hyper/glm-5`                                        | 203K    |       |           |       |       |       | $0.85      | $3          |
 | `hyper/glm-5.1`                                      | 203K    |       |           |       |       |       | $2         | $5          |
 | `hyper/glm-5.2`                                      | 1.0M    |       |           |       |       |       | $1         | $4          |
-| `hyper/gpt-oss-120b`                                 | 131K    |       |           |       |       |       | $0.18      | $0.61       |
-| `hyper/kimi-k2.5`                                    | 262K    |       |           |       |       |       | $0.53      | $3          |
+| `hyper/gpt-oss-120b`                                 | 131K    |       |           |       |       |       | $0.19      | $0.70       |
+| `hyper/kimi-k2.5`                                    | 262K    |       |           |       |       |       | $0.54      | $3          |
 | `hyper/kimi-k2.6`                                    | 262K    |       |           |       |       |       | $0.95      | $4          |
 | `hyper/kimi-k2.7-code`                               | 256K    |       |           |       |       |       | $0.95      | $4          |
 | `hyper/kimi-k3`                                      | 1.0M    |       |           |       |       |       | $3         | $16         |
 | `hyper/llama-3.3-70b-instruct`                       | 128K    |       |           |       |       |       | $0.51      | $1          |
 | `hyper/llama-4-maverick-17b-128e-instruct-fp8`       | 430K    |       |           |       |       |       | $0.28      | $0.93       |
-| `hyper/minimax-m2.7`                                 | 205K    |       |           |       |       |       | $0.48      | $2          |
+| `hyper/minimax-m2.7`                                 | 262K    |       |           |       |       |       | $0.42      | $2          |
 | `hyper/minimax-m3`                                   | 512K    |       |           |       |       |       | $0.33      | $1          |
 | `hyper/qwen3-coder-480b-a35b-instruct-int4-mixed-ar` | 106K    |       |           |       |       |       | $0.57      | $2          |
 | `hyper/qwen3-next-80b-a3b-instruct`                  | 262K    |       |           |       |       |       | $0.12      | $1          |
@@ -59,6 +60,7 @@ for await (const chunk of stream) {
 | `hyper/qwen3.7-flash`                                | 1.0M    |       |           |       |       |       | $0.20      | $0.80       |
 | `hyper/qwen3.7-max`                                  | 1.0M    |       |           |       |       |       | $3         | $8          |
 | `hyper/qwen3.7-plus`                                 | 1.0M    |       |           |       |       |       | $1         | $5          |
+| `hyper/qwen3.8-max`                                  | 1.0M    |       |           |       |       |       | $2         | $6          |
 
 ## Advanced configuration
 
@@ -88,7 +90,7 @@ const agent = new Agent({
   model: ({ requestContext }) => {
     const useAdvanced = requestContext.task === "complex";
     return useAdvanced
-      ? "hyper/qwen3.7-plus"
+      ? "hyper/qwen3.8-max"
       : "hyper/deepseek-v4-flash";
   }
 });

package/.docs/models/providers/impossibl.md

@@ -0,0 +1,148 @@
+> Discover all available pages from the documentation index: https://mastra.ai/llms.txt
+
+# ![Impossibl logo](https://models.dev/logos/impossibl.svg)Impossibl
+
+Access 76 Impossibl models through Mastra's model router. Authentication is handled automatically using the `IMPOSSIBL_API_KEY` environment variable.
+
+Learn more in the [Impossibl documentation](https://impossibl.com/docs/models).
+
+```bash
+IMPOSSIBL_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: "impossibl/anthropic/claude-fable-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 [Impossibl documentation](https://impossibl.com/docs/models) for details.
+
+## Models
+
+| Model                                        | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
+| -------------------------------------------- | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
+| `impossibl/anthropic/claude-fable-5`         | 1.0M    |       |           |       |       |       | $10        | $50         |
+| `impossibl/anthropic/claude-haiku-4-5`       | 200K    |       |           |       |       |       | $1         | $5          |
+| `impossibl/anthropic/claude-opus-4-5`        | 200K    |       |           |       |       |       | $5         | $25         |
+| `impossibl/anthropic/claude-opus-4-6`        | 1.0M    |       |           |       |       |       | $5         | $25         |
+| `impossibl/anthropic/claude-opus-4-7`        | 1.0M    |       |           |       |       |       | $5         | $25         |
+| `impossibl/anthropic/claude-opus-4-8`        | 1.0M    |       |           |       |       |       | $5         | $25         |
+| `impossibl/anthropic/claude-sonnet-4-5`      | 200K    |       |           |       |       |       | $3         | $15         |
+| `impossibl/anthropic/claude-sonnet-4-6`      | 1.0M    |       |           |       |       |       | $3         | $15         |
+| `impossibl/anthropic/claude-sonnet-5`        | 1.0M    |       |           |       |       |       | $2         | $10         |
+| `impossibl/cerebras/gpt-oss-120b`            | 131K    |       |           |       |       |       | $0.35      | $0.75       |
+| `impossibl/deepseek/deepseek-v4-flash`       | 1.0M    |       |           |       |       |       | $0.19      | $0.51       |
+| `impossibl/deepseek/deepseek-v4-pro`         | 1.0M    |       |           |       |       |       | $2         | $3          |
+| `impossibl/fireworks/glm-5.2`                | 1.0M    |       |           |       |       |       | $1         | $4          |
+| `impossibl/fireworks/gpt-oss-120b`           | 131K    |       |           |       |       |       | $0.15      | $0.60       |
+| `impossibl/fireworks/gpt-oss-20b`            | 131K    |       |           |       |       |       | $0.07      | $0.30       |
+| `impossibl/google/gemini-2.5-flash`          | 1.0M    |       |           |       |       |       | $0.30      | $3          |
+| `impossibl/google/gemini-2.5-flash-lite`     | 1.0M    |       |           |       |       |       | $0.10      | $0.40       |
+| `impossibl/google/gemini-2.5-pro`            | 1.0M    |       |           |       |       |       | $1         | $10         |
+| `impossibl/google/gemini-3.1-flash-lite`     | 1.0M    |       |           |       |       |       | $0.25      | $2          |
+| `impossibl/google/gemini-3.1-pro-preview`    | 1.0M    |       |           |       |       |       | $2         | $12         |
+| `impossibl/google/gemini-3.5-flash`          | 1.0M    |       |           |       |       |       | $2         | $9          |
+| `impossibl/google/gemini-3.5-flash-lite`     | 1.0M    |       |           |       |       |       | $0.30      | $3          |
+| `impossibl/google/gemini-3.6-flash`          | 1.0M    |       |           |       |       |       | $2         | $8          |
+| `impossibl/groq/gpt-oss-120b`                | 131K    |       |           |       |       |       | $0.15      | $0.60       |
+| `impossibl/groq/gpt-oss-20b`                 | 131K    |       |           |       |       |       | $0.07      | $0.30       |
+| `impossibl/moonshotai/kimi-k3`               | 1.0M    |       |           |       |       |       | $3         | $15         |
+| `impossibl/openai/gpt-3.5-turbo`             | 16K     |       |           |       |       |       | $0.50      | $2          |
+| `impossibl/openai/gpt-4-turbo`               | 128K    |       |           |       |       |       | $10        | $30         |
+| `impossibl/openai/gpt-4.1`                   | 1.0M    |       |           |       |       |       | $2         | $8          |
+| `impossibl/openai/gpt-4.1-mini`              | 1.0M    |       |           |       |       |       | $0.40      | $2          |
+| `impossibl/openai/gpt-4.1-nano`              | 1.0M    |       |           |       |       |       | $0.10      | $0.40       |
+| `impossibl/openai/gpt-4o`                    | 128K    |       |           |       |       |       | $3         | $10         |
+| `impossibl/openai/gpt-4o-mini`               | 128K    |       |           |       |       |       | $0.15      | $0.60       |
+| `impossibl/openai/gpt-5`                     | 400K    |       |           |       |       |       | $1         | $10         |
+| `impossibl/openai/gpt-5-codex`               | 400K    |       |           |       |       |       | $1         | $10         |
+| `impossibl/openai/gpt-5-mini`                | 400K    |       |           |       |       |       | $0.25      | $2          |
+| `impossibl/openai/gpt-5-nano`                | 400K    |       |           |       |       |       | $0.05      | $0.40       |
+| `impossibl/openai/gpt-5-pro`                 | 400K    |       |           |       |       |       | $15        | $120        |
+| `impossibl/openai/gpt-5.1`                   | 400K    |       |           |       |       |       | $1         | $10         |
+| `impossibl/openai/gpt-5.1-codex`             | 400K    |       |           |       |       |       | $1         | $10         |
+| `impossibl/openai/gpt-5.1-codex-mini`        | 400K    |       |           |       |       |       | $0.25      | $2          |
+| `impossibl/openai/gpt-5.2`                   | 400K    |       |           |       |       |       | $2         | $14         |
+| `impossibl/openai/gpt-5.2-codex`             | 400K    |       |           |       |       |       | $2         | $14         |
+| `impossibl/openai/gpt-5.3-codex`             | 400K    |       |           |       |       |       | $2         | $14         |
+| `impossibl/openai/gpt-5.4`                   | 1.1M    |       |           |       |       |       | $3         | $15         |
+| `impossibl/openai/gpt-5.4-mini`              | 400K    |       |           |       |       |       | $0.75      | $5          |
+| `impossibl/openai/gpt-5.4-nano`              | 400K    |       |           |       |       |       | $0.20      | $1          |
+| `impossibl/openai/gpt-5.4-pro`               | 1.1M    |       |           |       |       |       | $30        | $180        |
+| `impossibl/openai/gpt-5.5`                   | 1.1M    |       |           |       |       |       | $5         | $30         |
+| `impossibl/openai/gpt-5.5-pro`               | 1.1M    |       |           |       |       |       | $30        | $180        |
+| `impossibl/openai/gpt-5.6-luna`              | 1.1M    |       |           |       |       |       | $0.20      | $1          |
+| `impossibl/openai/gpt-5.6-sol`               | 1.1M    |       |           |       |       |       | $5         | $30         |
+| `impossibl/openai/gpt-5.6-terra`             | 1.1M    |       |           |       |       |       | $2         | $12         |
+| `impossibl/openai/o1`                        | 200K    |       |           |       |       |       | $15        | $60         |
+| `impossibl/openai/o3`                        | 200K    |       |           |       |       |       | $2         | $8          |
+| `impossibl/openai/o3-mini`                   | 200K    |       |           |       |       |       | $1         | $4          |
+| `impossibl/openai/o4-mini`                   | 200K    |       |           |       |       |       | $1         | $4          |
+| `impossibl/qwen/qwen3.6-flash`               | 1.0M    |       |           |       |       |       | $0.25      | $2          |
+| `impossibl/qwen/qwen3.7-max`                 | 1.0M    |       |           |       |       |       | $3         | $8          |
+| `impossibl/qwen/qwen3.7-plus`                | 1.0M    |       |           |       |       |       | $0.40      | $2          |
+| `impossibl/qwen/qwen3.8-max-preview`         | 1.0M    |       |           |       |       |       | $3         | $8          |
+| `impossibl/thinkingmachines/inkling`         | 66K     |       |           |       |       |       | $2         | $5          |
+| `impossibl/xai/grok-4.20-0309-non-reasoning` | 1.0M    |       |           |       |       |       | $1         | $3          |
+| `impossibl/xai/grok-4.20-0309-reasoning`     | 1.0M    |       |           |       |       |       | $1         | $3          |
+| `impossibl/xai/grok-4.3`                     | 1.0M    |       |           |       |       |       | $1         | $3          |
+| `impossibl/xai/grok-4.5`                     | 500K    |       |           |       |       |       | $2         | $6          |
+| `impossibl/xai/grok-build-0.1`               | 256K    |       |           |       |       |       | $1         | $2          |
+| `impossibl/xiaomi/mimo-v2.5`                 | 1.0M    |       |           |       |       |       | $0.14      | $0.28       |
+| `impossibl/zai/glm-4.5`                      | 131K    |       |           |       |       |       | $0.60      | $2          |
+| `impossibl/zai/glm-4.5-air`                  | 131K    |       |           |       |       |       | $0.20      | $1          |
+| `impossibl/zai/glm-4.6`                      | 205K    |       |           |       |       |       | $0.60      | $2          |
+| `impossibl/zai/glm-4.7`                      | 205K    |       |           |       |       |       | $0.60      | $2          |
+| `impossibl/zai/glm-5`                        | 205K    |       |           |       |       |       | $1         | $3          |
+| `impossibl/zai/glm-5-turbo`                  | 200K    |       |           |       |       |       | $1         | $4          |
+| `impossibl/zai/glm-5.1`                      | 200K    |       |           |       |       |       | $1         | $4          |
+| `impossibl/zai/glm-5.2`                      | 1.0M    |       |           |       |       |       | $1         | $4          |
+
+## Advanced configuration
+
+### Custom headers
+
+```typescript
+const agent = new Agent({
+  id: "custom-agent",
+  name: "custom-agent",
+  model: {
+    url: "https://api.impossibl.com/v1",
+    id: "impossibl/anthropic/claude-fable-5",
+    apiKey: process.env.IMPOSSIBL_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
+      ? "impossibl/zai/glm-5.2"
+      : "impossibl/anthropic/claude-fable-5";
+  }
+});
+```

package/.docs/models/providers/infomaniak.md

@@ -0,0 +1,83 @@
+> Discover all available pages from the documentation index: https://mastra.ai/llms.txt
+
+# ![Infomaniak logo](https://models.dev/logos/infomaniak.svg)Infomaniak
+
+Access 10 Infomaniak models through Mastra's model router. Authentication is handled automatically using the `INFOMANIAK_API_KEY` environment variable. Configure `INFOMANIAK_PRODUCT_ID` as well.
+
+Learn more in the [Infomaniak documentation](https://www.infomaniak.com/en/hosting/ai-services/open-source-models).
+
+```bash
+INFOMANIAK_PRODUCT_ID=your-value
+INFOMANIAK_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: "infomaniak/Qwen/Qwen3.5-122B-A10B-FP8"
+});
+
+// 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 [Infomaniak documentation](https://www.infomaniak.com/en/hosting/ai-services/open-source-models) for details.
+
+## Models
+
+| Model                                                  | Context | Tools | Reasoning | Image | Audio | Video | Input $/1M | Output $/1M |
+| ------------------------------------------------------ | ------- | ----- | --------- | ----- | ----- | ----- | ---------- | ----------- |
+| `infomaniak/bge_multilingual_gemma2`                   | 8K      |       |           |       |       |       | $0.08      | —           |
+| `infomaniak/google/gemma-4-31B-it`                     | 100K    |       |           |       |       |       | $0.25      | $0.50       |
+| `infomaniak/mini_lm_l12_v2`                            | 128     |       |           |       |       |       | —          | —           |
+| `infomaniak/mistralai/Ministral-3-14B-Instruct-2512`   | 100K    |       |           |       |       |       | $0.37      | $0.50       |
+| `infomaniak/mistralai/Mistral-Small-4-119B-2603`       | 256K    |       |           |       |       |       | $0.25      | $0.93       |
+| `infomaniak/moonshotai/Kimi-K2.6`                      | 256K    |       |           |       |       |       | $0.74      | $4          |
+| `infomaniak/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8` | 1.0M    |       |           |       |       |       | $0.06      | $0.25       |
+| `infomaniak/Qwen/Qwen3.5-122B-A10B-FP8`                | 200K    |       |           |       |       |       | $0.50      | $4          |
+| `infomaniak/Qwen/Qwen3.5-397B-A17B-FP8`                | 200K    |       |           |       |       |       | $0.99      | $4          |
+| `infomaniak/swiss-ai/Apertus-v1.5-70B`                 | 100K    |       |           |       |       |       | $0.87      | $3          |
+
+## Advanced configuration
+
+### Custom headers
+
+```typescript
+const agent = new Agent({
+  id: "custom-agent",
+  name: "custom-agent",
+  model: {
+    url: "https://api.infomaniak.com/2/ai/${INFOMANIAK_PRODUCT_ID}/openai/v1",
+    id: "infomaniak/Qwen/Qwen3.5-122B-A10B-FP8",
+    apiKey: process.env.INFOMANIAK_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
+      ? "infomaniak/swiss-ai/Apertus-v1.5-70B"
+      : "infomaniak/Qwen/Qwen3.5-122B-A10B-FP8";
+  }
+});
+```