IteraCompute

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

Learn more in the IteraCompute documentation.

.env

ITERACOMPUTE_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: "iteracompute/deepseek/deepseek-v4-flash-0731"
});

// 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);
}

备注

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

Models

10 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
iteracompute/deepseek/deepseek-v4-flash-0731	1.0M						$0.29	$1
iteracompute/deepseek/deepseek-v4-pro-0813	1.0M						$0.89	$3
iteracompute/deepseek/deepseek-v4.1-flash	1.0M						$0.29	$1
iteracompute/minimax/minimax-m3	1.0M						$0.30	$1
iteracompute/moonshotai/kimi-k2.7-code	262K						$0.69	$3
iteracompute/moonshotai/kimi-k3	1.0M						$2	$12
iteracompute/qwen/qwen3.8-2.4t-a95b	1.0M						$2	$6
iteracompute/qwen/qwen3.8-27b	131K						—	—
iteracompute/z-ai/glm-5.3	1.0M						$0.99	$3
iteracompute/z-ai/glm-5.3-flash	1.0M						$0.10	$0.35

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.iteracompute.com/v1",
    id: "iteracompute/deepseek/deepseek-v4-flash-0731",
    apiKey: process.env.ITERACOMPUTE_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
      ? "iteracompute/z-ai/glm-5.3-flash"
      : "iteracompute/deepseek/deepseek-v4-flash-0731";
  }
});