일체 포함&

Mastra의 Model 라우터를 통해 8개의 ai& Model에 액세스하세요. 인증은 다음을 사용하여 자동으로 처리됩니다.AIAND_API_KEY environment variable.

자세한 내용은 다음에서 확인하세요.ai& documentation.

.env

AIAND_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: "aiand/deepseek-ai/deepseek-v4-flash"
});

// 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 엔드포인트를 사용합니다. 일부 Provider별 기능은 사용하지 못할 수 있습니다. 자세한 내용은 ai& 문서를 참조하세요.

Model

8 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
aiand/deepseek-ai/deepseek-v4-flash	1.0M						$0.15	$0.25
aiand/deepseek-ai/deepseek-v4-pro	1.0M						$1	$3
aiand/google/gemma-4-31b-it	262K						$0.20	$0.50
aiand/moonshotai/kimi-k2.7-code	262K						$0.75	$4
aiand/moonshotai/kimi-k3	1.0M						$3	$13
aiand/openai/gpt-oss-120b	131K						$0.15	$0.60
aiand/qwen/qwen3.6-27b	262K						—	—
aiand/zai-org/glm-5.2	1.0M						$1	$4

고급 구성

맞춤 헤더

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://api.aiand.com/v1",
    id: "aiand/deepseek-ai/deepseek-v4-flash",
    apiKey: process.env.AIAND_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
      ? "aiand/zai-org/glm-5.2"
      : "aiand/deepseek-ai/deepseek-v4-flash";
  }
});