Skip to main content

Chutes logoChutes

Access 39 Chutes models through Mastra's model router. Authentication is handled automatically using the CHUTES_API_KEY environment variable.

Learn more in the Chutes documentation.

.env
CHUTES_API_KEY=your-api-key
src/mastra/agents/my-agent.ts
import { Agent } from "@mastra/core/agent";

const agent = new Agent({
id: "my-agent",
name: "My Agent",
instructions: "You are a helpful assistant",
model: "chutes/MiniMaxAI/MiniMax-M2.5-TEE"
});

// 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
Direct link to Models

ModelContextToolsReasoningImageAudioVideoInput $/1MOutput $/1M
chutes/deepseek-ai/DeepSeek-R1-0528-TEE164K$0.45$2
chutes/deepseek-ai/DeepSeek-R1-Distill-Llama-70B131K$0.03$0.11
chutes/deepseek-ai/DeepSeek-V3-0324-TEE164K$0.25$1
chutes/deepseek-ai/DeepSeek-V3.1-TEE164K$0.27$1
chutes/deepseek-ai/DeepSeek-V3.2-TEE131K$0.28$0.42
chutes/google/gemma-4-31B-turbo-TEE131K$0.13$0.38
chutes/MiniMaxAI/MiniMax-M2.5-TEE197K$0.15$1
chutes/moonshotai/Kimi-K2.5-TEE262K$0.44$2
chutes/moonshotai/Kimi-K2.6-TEE262K$0.95$4
chutes/NousResearch/DeepHermes-3-Mistral-24B-Preview33K$0.02$0.10
chutes/NousResearch/Hermes-4-14B41K$0.01$0.05
chutes/openai/gpt-oss-120b-TEE131K$0.09$0.36
chutes/Qwen/Qwen2.5-72B-Instruct33K$0.30$1
chutes/Qwen/Qwen2.5-Coder-32B-Instruct33K$0.03$0.11
chutes/Qwen/Qwen2.5-VL-32B-Instruct16K$0.05$0.22
chutes/Qwen/Qwen3-235B-A22B-Instruct-2507-TEE262K$0.10$0.60
chutes/Qwen/Qwen3-235B-A22B-Thinking-2507262K$0.11$0.60
chutes/Qwen/Qwen3-30B-A3B41K$0.06$0.22
chutes/Qwen/Qwen3-32B-TEE41K$0.08$0.24
chutes/Qwen/Qwen3-Coder-Next-TEE262K$0.12$0.75
chutes/Qwen/Qwen3-Next-80B-A3B-Instruct262K$0.10$0.80
chutes/Qwen/Qwen3.5-397B-A17B-TEE262K$0.39$2
chutes/Qwen/Qwen3.6-27B-TEE262K$0.20$2
chutes/Qwen/Qwen3Guard-Gen-0.6B33K$0.01$0.01
chutes/rednote-hilab/dots.ocr131K$0.01$0.01
chutes/tngtech/DeepSeek-TNG-R1T2-Chimera-TEE164K$0.30$1
chutes/unsloth/gemma-3-12b-it131K$0.03$0.10
chutes/unsloth/gemma-3-27b-it128K$0.03$0.11
chutes/unsloth/gemma-3-4b-it96K$0.01$0.03
chutes/unsloth/Llama-3.2-1B-Instruct16K$0.01$0.01
chutes/unsloth/Llama-3.2-3B-Instruct16K$0.01$0.01
chutes/unsloth/Mistral-Nemo-Instruct-2407131K$0.02$0.04
chutes/XiaomiMiMo/MiMo-V2-Flash-TEE262K$0.09$0.29
chutes/zai-org/GLM-4.6V131K$0.30$0.90
chutes/zai-org/GLM-4.7-FP8203K$0.30$1
chutes/zai-org/GLM-4.7-TEE203K$0.39$2
chutes/zai-org/GLM-5-TEE203K$0.95$3
chutes/zai-org/GLM-5-Turbo203K$0.49$2
chutes/zai-org/GLM-5.1-TEE203K$1$4
39 available models

Advanced configuration
Direct link to Advanced configuration

Custom headers
Direct link to Custom headers

src/mastra/agents/my-agent.ts
const agent = new Agent({
id: "custom-agent",
name: "custom-agent",
model: {
url: "https://llm.chutes.ai/v1",
id: "chutes/MiniMaxAI/MiniMax-M2.5-TEE",
apiKey: process.env.CHUTES_API_KEY,
headers: {
"X-Custom-Header": "value"
}
}
});

Dynamic model selection
Direct link to Dynamic model selection

src/mastra/agents/my-agent.ts
const agent = new Agent({
id: "dynamic-agent",
name: "Dynamic Agent",
model: ({ requestContext }) => {
const useAdvanced = requestContext.task === "complex";
return useAdvanced
? "chutes/zai-org/GLM-5.1-TEE"
: "chutes/MiniMaxAI/MiniMax-M2.5-TEE";
}
});
On this page