올라마 클라우드

Mastra의 Model 라우터를 통해 20개의 Ollama Cloud Model에 액세스하세요. 인증은 다음을 사용하여 자동으로 처리됩니다.OLLAMA_API_KEY environment variable.

자세한 내용은 다음에서 확인하세요.Ollama Cloud documentation.

.env

OLLAMA_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: "ollama-cloud/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 endpoint를 사용합니다. 일부 Provider별 기능은 제공되지 않을 수 있습니다. 자세한 내용은 Ollama Cloud 문서를 확인하세요.

Model

20 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
ollama-cloud/deepseek-v4-flash	1.0M						—	—
ollama-cloud/deepseek-v4-flash:0731	1.0M						—	—
ollama-cloud/deepseek-v4-pro	1.0M						—	—
ollama-cloud/gemma4:31b	262K						—	—
ollama-cloud/glm-5.1	203K						—	—
ollama-cloud/glm-5.2	976K						—	—
ollama-cloud/gpt-oss:120b	131K						—	—
ollama-cloud/gpt-oss:20b	131K						—	—
ollama-cloud/kimi-k2.5	262K						—	—
ollama-cloud/kimi-k2.6	262K						—	—
ollama-cloud/kimi-k2.7-code	262K						—	—
ollama-cloud/kimi-k3	1.0M						—	—
ollama-cloud/minimax-m2.5	205K						—	—
ollama-cloud/minimax-m2.7	197K						—	—
ollama-cloud/minimax-m3	512K						—	—
ollama-cloud/mistral-large-3:675b	262K						—	—
ollama-cloud/nemotron-3-nano:30b	1.0M						—	—
ollama-cloud/nemotron-3-super	262K						—	—
ollama-cloud/nemotron-3-ultra	262K						—	—
ollama-cloud/qwen3.5:397b	262K						—	—

고급 구성

맞춤 헤더

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://ollama.com/v1",
    id: "ollama-cloud/deepseek-v4-flash",
    apiKey: process.env.OLLAMA_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
      ? "ollama-cloud/qwen3.5:397b"
      : "ollama-cloud/deepseek-v4-flash";
  }
});