Moark

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

Learn more in the Moark documentation.

.env

MOARK_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: "moark/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);
}

备注

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

Models

10 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
moark/DeepSeek-V4-Flash	1.0M						$0.50	$0.50
moark/deepseek-v4-flash-0731	1.0M						$0.15	$0.30
moark/DeepSeek-V4-Pro	1.0M						$2	$4
moark/GLM-4.7	205K						$0.42	$2
moark/GLM-5.3	1.0M						$1	$4
moark/Kimi-K2.6	262K						$0.98	$4
moark/kimi-k3	1.0M						$3	$15
moark/MiniMax-M2.1	205K						$0.29	$1
moark/MiniMax-M2.7	205K						$0.29	$1
moark/Qwen3.6-Flash	1.0M						$0.18	$1

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://moark.com/v1",
    id: "moark/DeepSeek-V4-Flash",
    apiKey: process.env.MOARK_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
      ? "moark/kimi-k3"
      : "moark/DeepSeek-V4-Flash";
  }
});