Skip to main content

routing.run logorouting.run

Access 37 routing.run models through Mastra's model router. Authentication is handled automatically using the ROUTING_RUN_API_KEY environment variable.

Learn more in the routing.run documentation.

.env
ROUTING_RUN_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: "routing-run/route/deepseek-v3.2"
});

// 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 routing.run documentation for details.

Models
Direct link to Models

ModelContextToolsReasoningImageAudioVideoInput $/1MOutput $/1M
routing-run/route/deepseek-v3.2164K$0.49$0.74
routing-run/route/deepseek-v4-flash1.0M$0.49$0.74
routing-run/route/deepseek-v4-flash-full1.0M$0.49$0.74
routing-run/route/deepseek-v4-pro1.0M$0.49$0.74
routing-run/route/deepseek-v4-pro-precision1.0M$0.74$1
routing-run/route/gemma-4-31b-it131K$0.10$0.30
routing-run/route/glm-4.7128K$1$4
routing-run/route/glm-4.7-flash128K$1$4
routing-run/route/glm-5203K$0.79$3
routing-run/route/glm-5-highspeed203K$1$4
routing-run/route/glm-5.1203K$1$3
routing-run/route/glm-5.1-fp16203K$1$4
routing-run/route/glm-5.1-full203K$1$4
routing-run/route/glm-5.1-precision203K$1$4
routing-run/route/kimi-k2.5262K$0.46$2
routing-run/route/kimi-k2.5-highspeed131K$0.65$3
routing-run/route/kimi-k2.6262K$0.46$2
routing-run/route/kimi-k2.6-full262K$0.46$2
routing-run/route/kimi-k2.6-precision262K$0.65$3
routing-run/route/mimo-v2.5256K$0.40$2
routing-run/route/mimo-v2.5-pro1.0M$0.45$1
routing-run/route/mimo-v2.5-pro-precision1.0M$0.45$1
routing-run/route/minimax-m2.5100K$0.19$1
routing-run/route/minimax-m2.5-highspeed100K$0.19$1
routing-run/route/minimax-m2.7100K$0.33$1
routing-run/route/minimax-m2.7-highspeed100K$0.33$1
routing-run/route/mistral-large-3128K$0.50$2
routing-run/route/mistral-medium-2505128K$0.40$2
routing-run/route/mistral-small-2503128K$0.15$0.60
routing-run/route/qwen3.5-397b-a17b262K$1$3
routing-run/route/qwen3.5-9b262K$0.20$0.60
routing-run/route/qwen3.5-9b-chat262K$0.20$0.60
routing-run/route/qwen3.6-27b262K$1$3
routing-run/route/step-3.5-flash262K$0.10$0.29
routing-run/route/step-3.5-flash-2603262K$0.10$0.30
routing-run/route/step-3.5-flash-full262K$0.10$0.29
routing-run/route/stepfun-3.5-flash262K$0.10$0.29
37 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://api.routing.run/v1",
id: "routing-run/route/deepseek-v3.2",
apiKey: process.env.ROUTING_RUN_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
? "routing-run/route/stepfun-3.5-flash"
: "routing-run/route/deepseek-v3.2";
}
});
On this page