Cortecs

Access 10 Cortecs models through Mastra's model router. Authentication is handled automatically using the CORTECS_API_KEY environment variable.

Learn more in the Cortecs documentation.

CORTECS_API_KEY=your-api-key

import { Agent } from "@mastra/core";

const agent = new Agent({
  name: "my-agent",
  instructions: "You are a helpful assistant",
  model: "cortecs/claude-sonnet-4",
});

// 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);
}

OpenAI Compatibility

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

Models

Model	Image	Audio	Video	Tools	Streaming	Context Window
cortecs/nova-pro-v1	✓	✗	✗	✓	✗	300,000
cortecs/deepseek-v3-0324	✗	✗	✗	✓	✗	128,000
cortecs/kimi-k2-instruct	✗	✗	✗	✓	✗	131,000
cortecs/gpt-4.1	✓	✗	✗	✓	✗	1,047,576
cortecs/gemini-2.5-pro	✓	✗	✗	✓	✗	1,048,576
cortecs/gpt-oss-120b	✗	✗	✗	✓	✗	128,000
cortecs/qwen3-coder-480b-a35b-instruct	✗	✗	✗	✓	✗	262,000
cortecs/claude-sonnet-4	✓	✗	✗	✓	✗	200,000
cortecs/llama-3.1-405b-instruct	✗	✗	✗	✓	✗	128,000
cortecs/qwen3-32b	✗	✗	✗	✓	✗	16,384

Advanced Configuration

Custom Headers

const agent = new Agent({
  name: "custom-agent",
  model: {
    url: "https://api.cortecs.ai/v1",
    modelId: "claude-sonnet-4",
    apiKey: process.env.CORTECS_API_KEY,
    headers: {
      "X-Custom-Header": "value",
    },
  },
});

Dynamic Model Selection

const agent = new Agent({
  name: "dynamic-agent",
  model: ({ runtimeContext }) => {
    const useAdvanced = runtimeContext.task === "complex";
    return useAdvanced
      ? "cortecs/qwen3-coder-480b-a35b-instruct"
      : "cortecs/claude-sonnet-4";
  },
});