Inco

Access 7 Inco models through Mastra's model router. Authentication is handled automatically using the INCO_API_KEY environment variable.

Learn more in the Inco documentation.

.env

INCO_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: "inco/deepseek-v4.1-flash:fast"
});

// 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);
}

note

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

Models

7 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
inco/deepseek-v4.1-flash:fast	1.0M						$0.60	$2
inco/glm-5.3	1.0M						$1	$4
inco/glm-5.3-flash:fast	1.0M						$0.15	$0.50
inco/glm-5.3:fast	1.0M						$3	$9
inco/kimi-k3:fast	1.0M						$6	$30
inco/minimax-m3	1.0M						$0.30	$1
inco/minimax-m3:fast	1.0M						$0.60	$2

Model availability, capabilities, context windows, and pricing are sourced from models.dev and may change.

Advanced configuration

Custom headers

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://api.inco.ai/v1",
    id: "inco/deepseek-v4.1-flash:fast",
    apiKey: process.env.INCO_API_KEY,
    headers: {
      "X-Custom-Header": "value"
    }
  }
});

Dynamic model selection

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
      ? "inco/minimax-m3:fast"
      : "inco/deepseek-v4.1-flash:fast";
  }
});