Ollama Cloud

Access 12 Ollama Cloud models through Mastra's model router. Authentication is handled automatically using the OLLAMA_API_KEY environment variable.

Learn more in the Ollama Cloud documentation.

OLLAMA_API_KEY=your-api-key

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/cogito-2.1:671b-cloud"
});

// 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 Ollama Cloud documentation for details.

Models

12 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
ollama-cloud/cogito-2.1:671b-cloud	160K						—	—
ollama-cloud/deepseek-v3.1:671b-cloud	160K						—	—
ollama-cloud/gemini-3-pro-preview:latest	1.0M						—	—
ollama-cloud/glm-4.6:cloud	200K						—	—
ollama-cloud/gpt-oss:120b-cloud	200K						—	—
ollama-cloud/gpt-oss:20b-cloud	200K						—	—
ollama-cloud/kimi-k2-thinking:cloud	256K						—	—
ollama-cloud/kimi-k2:1t-cloud	256K						—	—
ollama-cloud/minimax-m2:cloud	200K						—	—
ollama-cloud/qwen3-coder:480b-cloud	200K						—	—
ollama-cloud/qwen3-vl-235b-cloud	200K						—	—
ollama-cloud/qwen3-vl-235b-instruct-cloud	200K						—	—

Advanced Configuration

Custom Headers

const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://ollama.com/v1",
    id: "ollama-cloud/cogito-2.1:671b-cloud",
    apiKey: process.env.OLLAMA_API_KEY,
    headers: {
      "X-Custom-Header": "value"
    }
  }
});

Dynamic Model Selection

const agent = new Agent({
  id: "dynamic-agent",
  name: "Dynamic Agent",
  model: ({ requestContext }) => {
    const useAdvanced = requestContext.task === "complex";
    return useAdvanced
      ? "ollama-cloud/qwen3-vl-235b-instruct-cloud"
      : "ollama-cloud/cogito-2.1:671b-cloud";
  }
});