RunInfra

Access 4 RunInfra models through Mastra's model router. Authentication is handled automatically using the RUNINFRA_GATEWAY_KEY environment variable.

Learn more in the RunInfra documentation.

.env

RUNINFRA_GATEWAY_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: "runinfra/Inferact/Qwen3.8-2.4T-A95B-NVFP4"
});

// 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);
}

note

Mastra uses the OpenAI-compatible /chat/completions endpoint. Some provider-specific features may not be available. Check the RunInfra documentation for details.

Models

4 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
runinfra/deepseek-ai/DeepSeek-V4-Flash-0731	1.0M						$0.13	$0.27
runinfra/Inferact/Qwen3.8-2.4T-A95B-NVFP4	262K						$2	$6
runinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16	262K						$0.05	$0.15
runinfra/Qwen/Qwen3.8-27B	262K						$0.10	$0.40

Advanced configuration

Custom headers

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://api.runinfra.ai/v1",
    id: "runinfra/Inferact/Qwen3.8-2.4T-A95B-NVFP4",
    apiKey: process.env.RUNINFRA_GATEWAY_KEY,
    headers: {
      "X-Custom-Header": "value"
    }
  }
});

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
      ? "runinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16"
      : "runinfra/Inferact/Qwen3.8-2.4T-A95B-NVFP4";
  }
});