추론

Mastra의 Model 라우터를 통해 9개의 추론 Model에 액세스하세요. 인증은 다음을 사용하여 자동으로 처리됩니다.INFERENCE_API_KEY environment variable.

자세한 내용은 다음에서 확인하세요.Inference documentation.

.env

INFERENCE_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: "inference/google/gemma-3"
});

// 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);
}

정보

Mastra는 OpenAI 호환 /chat/completions endpoint를 사용합니다. 일부 Provider별 기능은 사용하지 못할 수 있습니다. 자세한 내용은 Inference 문서를 확인하세요.

Model

9 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
inference/google/gemma-3	125K						$0.15	$0.30
inference/meta/llama-3.1-8b-instruct	16K						$0.03	$0.03
inference/meta/llama-3.2-11b-vision-instruct	16K						$0.06	$0.06
inference/meta/llama-3.2-1b-instruct	16K						$0.01	$0.01
inference/meta/llama-3.2-3b-instruct	16K						$0.02	$0.02
inference/mistral/mistral-nemo-12b-instruct	16K						$0.04	$0.10
inference/osmosis/osmosis-structure-0.6b	4K						$0.10	$0.50
inference/qwen/qwen-2.5-7b-vision-instruct	125K						$0.20	$0.20
inference/qwen/qwen3-embedding-4b	32K						$0.01	—

고급 구성

맞춤 헤더

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://inference.net/v1",
    id: "inference/google/gemma-3",
    apiKey: process.env.INFERENCE_API_KEY,
    headers: {
      "X-Custom-Header": "value"
    }
  }
});

동적 Model 선택

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
      ? "inference/qwen/qwen3-embedding-4b"
      : "inference/google/gemma-3";
  }
});