Pendra

Access 6 Pendra models through Mastra's model router. Authentication is handled automatically using the PENDRA_API_KEY environment variable.

Learn more in the Pendra documentation.

.env

PENDRA_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: "pendra/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);
}

note

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

Models

6 available models

Model	Context	Tools	Reasoning	Image	Audio	Video	Input $/1M	Output $/1M
pendra/deepseek-v4-flash	1.0M						—	—
pendra/glm-4.7-flash	200K						—	—
pendra/gpt-oss:120b	131K						—	—
pendra/llama3.3:70b	128K						—	—
pendra/qwen3-coder:30b	262K						—	—
pendra/qwen3.6:27b	262K						—	—

Advanced configuration

Custom headers

src/mastra/agents/my-agent.ts

const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://api.pendra.ai/api/v1",
    id: "pendra/deepseek-v4-flash",
    apiKey: process.env.PENDRA_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
      ? "pendra/qwen3.6:27b"
      : "pendra/deepseek-v4-flash";
  }
});