Chutes
Access 33 Chutes models through Mastra's model router. Authentication is handled automatically using the CHUTES_API_KEY environment variable.
Learn more in the Chutes documentation.
CHUTES_API_KEY=your-api-key
import { Agent } from "@mastra/core";
const agent = new Agent({
name: "my-agent",
instructions: "You are a helpful assistant",
model: "chutes/Qwen/Qwen3-235B-A22B-Instruct-2507"
});
// 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 Chutes documentation for details.
Models
| Model | Image | Audio | Video | Tools | Streaming | Context Window |
|---|---|---|---|---|---|---|
chutes/chutesai/Devstral-Small-2505 | ✗ | ✗ | ✗ | ✓ | ✗ | 32,768 |
chutes/chutesai/Mistral-Small-3.2-24B-Instruct-2506 | ✗ | ✗ | ✗ | ✓ | ✗ | 131,072 |
chutes/deepseek-ai/DeepSeek-R1-0528 | ✗ | ✗ | ✗ | ✓ | ✗ | 75,000 |
chutes/deepseek-ai/DeepSeek-R1-0528-Qwen3-8B | ✗ | ✗ | ✗ | ✓ | ✗ | 131,072 |
chutes/deepseek-ai/DeepSeek-R1-Distill-Llama-70B | ✗ | ✗ | ✗ | ✗ | ✗ | 131,072 |
chutes/deepseek-ai/DeepSeek-V3-0324 | ✗ | ✗ | ✗ | ✓ | ✗ | 75,000 |
chutes/deepseek-ai/DeepSeek-V3.1 | ✗ | ✗ | ✗ | ✓ | ✗ | 163,840 |
chutes/deepseek-ai/DeepSeek-V3.1-Terminus | ✗ | ✗ | ✗ | ✓ | ✗ | 131,072 |
chutes/deepseek-ai/DeepSeek-V3.1-turbo | ✗ | ✗ | ✗ | ✓ | ✗ | 128,000 |
chutes/deepseek-ai/DeepSeek-V3.1:THINKING | ✗ | ✗ | ✗ | ✓ | ✗ | 163,840 |
chutes/deepseek-ai/DeepSeek-V3.2-Exp | ✗ | ✗ | ✗ | ✓ | ✗ | 128,000 |
chutes/meituan-longcat/LongCat-Flash-Chat-FP8 | ✗ | ✗ | ✗ | ✓ | ✗ | 131,072 |
chutes/moonshotai/Kimi-Dev-72B | ✗ | ✗ | ✗ | ✓ | ✗ | 131,072 |
chutes/moonshotai/Kimi-K2-Instruct-0905 | ✗ | ✗ | ✗ | ✓ | ✗ | 262,144 |
chutes/moonshotai/Kimi-K2-Instruct-75k | ✗ | ✗ | ✗ | ✓ | ✗ | 75,000 |
chutes/moonshotai/Kimi-VL-A3B-Thinking | ✓ | ✗ | ✗ | ✓ | ✗ | 131,072 |
chutes/openai/gpt-oss-120b | ✗ | ✗ | ✗ | ✓ | ✗ | 131,072 |
chutes/Qwen/Qwen3-235B-A22B-Instruct-2507 | ✗ | ✗ | ✗ | ✓ | ✗ | 262,144 |
chutes/Qwen/Qwen3-235B-A22B-Thinking-2507 | ✗ | ✗ | ✗ | ✓ | ✗ | 262,144 |
chutes/Qwen/Qwen3-30B-A3B | ✗ | ✗ | ✗ | ✓ | ✗ | 40,960 |
chutes/Qwen/Qwen3-30B-A3B-Instruct-2507 | ✗ | ✗ | ✗ | ✓ | ✗ | 262,144 |
chutes/Qwen/Qwen3-30B-A3B-Thinking-2507 | ✗ | ✗ | ✗ | ✓ | ✗ | 262,144 |
chutes/Qwen/Qwen3-Coder-30B-A3B-Instruct | ✗ | ✗ | ✗ | ✓ | ✗ | 262,144 |
chutes/Qwen/Qwen3-Coder-480B-A35B-Instruct-FP8 | ✗ | ✗ | ✗ | ✓ | ✗ | 262,144 |
chutes/Qwen/Qwen3-Next-80B-A3B-Instruct | ✗ | ✗ | ✗ | ✓ | ✗ | 262,144 |
chutes/Qwen/Qwen3-Next-80B-A3B-Thinking | ✗ | ✗ | ✗ | ✓ | ✗ | 262,144 |
chutes/tngtech/DeepSeek-R1T-Chimera | ✗ | ✗ | ✗ | ✗ | ✗ | 163,840 |
chutes/tngtech/DeepSeek-TNG-R1T2-Chimera | ✗ | ✗ | ✗ | ✗ | ✗ | 163,840 |
chutes/zai-org/GLM-4.5-Air | ✗ | ✗ | ✗ | ✓ | ✗ | 131,072 |
chutes/zai-org/GLM-4.5-FP8 | ✗ | ✗ | ✗ | ✓ | ✗ | 131,072 |
chutes/zai-org/GLM-4.5-turbo | ✗ | ✗ | ✗ | ✓ | ✗ | 131,072 |
chutes/zai-org/GLM-4.6-FP8 | ✗ | ✗ | ✗ | ✓ | ✗ | 204,800 |
chutes/zai-org/GLM-4.6-turbo | ✗ | ✗ | ✗ | ✓ | ✗ | 204,800 |
Advanced Configuration
Custom Headers
const agent = new Agent({
name: "custom-agent",
model: {
url: "https://llm.chutes.ai/v1",
id: "chutes/Qwen/Qwen3-235B-A22B-Instruct-2507",
apiKey: process.env.CHUTES_API_KEY,
headers: {
"X-Custom-Header": "value"
}
}
});
Dynamic Model Selection
const agent = new Agent({
name: "dynamic-agent",
model: ({ runtimeContext }) => {
const useAdvanced = runtimeContext.task === "complex";
return useAdvanced
? "chutes/zai-org/GLM-4.6-turbo"
: "chutes/Qwen/Qwen3-235B-A22B-Instruct-2507";
}
});