Perplexity Agent

Access 16 Perplexity Agent models through Mastra's model router. Authentication is handled automatically using the PERPLEXITY_API_KEY environment variable.

Learn more in the Perplexity Agent documentation.

PERPLEXITY_API_KEY=your-api-key

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

const agent = new Agent({
  id: "my-agent",
  name: "My Agent",
  instructions: "You are a helpful assistant",
  model: "perplexity-agent/anthropic/claude-haiku-4-5"
});

// 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);
}

:::info

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

:::

Models

<ProviderModelsTable models={[ { "model": "perplexity-agent/anthropic/claude-haiku-4-5", "imageInput": true, "audioInput": false, "videoInput": false, "toolUsage": true, "reasoning": true, "contextWindow": 200000, "maxOutput": 64000, "inputCost": 1, "outputCost": 5 }, { "model": "perplexity-agent/anthropic/claude-opus-4-5", "imageInput": true, "audioInput": false, "videoInput": false, "toolUsage": true, "reasoning": true, "contextWindow": 200000, "maxOutput": 64000, "inputCost": 5, "outputCost": 25 }, { "model": "perplexity-agent/anthropic/claude-opus-4-6", "imageInput": true, "audioInput": false, "videoInput": false, "toolUsage": true, "reasoning": true, "contextWindow": 200000, "maxOutput": 128000, "inputCost": 5, "outputCost": 25 }, { "model": "perplexity-agent/anthropic/claude-sonnet-4-5", "imageInput": true, "audioInput": false, "videoInput": false, "toolUsage": true, "reasoning": true, "contextWindow": 200000, "maxOutput": 64000, "inputCost": 3, "outputCost": 15 }, { "model": "perplexity-agent/anthropic/claude-sonnet-4-6", "imageInput": true, "audioInput": false, "videoInput": false, "toolUsage": true, "reasoning": true, "contextWindow": 200000, "maxOutput": 64000, "inputCost": 3, "outputCost": 15 }, { "model": "perplexity-agent/google/gemini-2.5-flash", "imageInput": true, "audioInput": true, "videoInput": true, "toolUsage": true, "reasoning": true, "contextWindow": 1048576, "maxOutput": 65536, "inputCost": 0.3, "outputCost": 2.5 }, { "model": "perplexity-agent/google/gemini-2.5-pro", "imageInput": true, "audioInput": true, "videoInput": true, "toolUsage": true, "reasoning": true, "contextWindow": 1048576, "maxOutput": 65536, "inputCost": 1.25, "outputCost": 10 }, { "model": "perplexity-agent/google/gemini-3-flash-preview", "imageInput": true, "audioInput": true, "videoInput": true, "toolUsage": true, "reasoning": true, "contextWindow": 1048576, "maxOutput": 65536, "inputCost": 0.5, "outputCost": 3 }, { "model": "perplexity-agent/google/gemini-3.1-pro-preview", "imageInput": true, "audioInput": true, "videoInput": true, "toolUsage": true, "reasoning": true, "contextWindow": 1048576, "maxOutput": 65536, "inputCost": 2, "outputCost": 12 }, { "model": "perplexity-agent/nvidia/nemotron-3-super-120b-a12b", "imageInput": false, "audioInput": false, "videoInput": false, "toolUsage": true, "reasoning": true, "contextWindow": 1000000, "maxOutput": 32000, "inputCost": 0.25, "outputCost": 2.5 }, { "model": "perplexity-agent/openai/gpt-5-mini", "imageInput": true, "audioInput": false, "videoInput": false, "toolUsage": true, "reasoning": true, "contextWindow": 400000, "maxOutput": 128000, "inputCost": 0.25, "outputCost": 2 }, { "model": "perplexity-agent/openai/gpt-5.1", "imageInput": true, "audioInput": false, "videoInput": false, "toolUsage": true, "reasoning": true, "contextWindow": 400000, "maxOutput": 128000, "inputCost": 1.25, "outputCost": 10 }, { "model": "perplexity-agent/openai/gpt-5.2", "imageInput": true, "audioInput": false, "videoInput": false, "toolUsage": true, "reasoning": true, "contextWindow": 400000, "maxOutput": 128000, "inputCost": 1.75, "outputCost": 14 }, { "model": "perplexity-agent/openai/gpt-5.4", "imageInput": true, "audioInput": false, "videoInput": false, "toolUsage": true, "reasoning": true, "contextWindow": 1050000, "maxOutput": 128000, "inputCost": 2.5, "outputCost": 15 }, { "model": "perplexity-agent/perplexity/sonar", "imageInput": false, "audioInput": false, "videoInput": false, "toolUsage": true, "reasoning": false, "contextWindow": 128000, "maxOutput": 8192, "inputCost": 0.25, "outputCost": 2.5 }, { "model": "perplexity-agent/xai/grok-4-1-fast-non-reasoning", "imageInput": true, "audioInput": false, "videoInput": false, "toolUsage": true, "reasoning": false, "contextWindow": 2000000, "maxOutput": 30000, "inputCost": 0.2, "outputCost": 0.5 } ]} />

Advanced configuration

Custom headers

const agent = new Agent({
  id: "custom-agent",
  name: "custom-agent",
  model: {
    url: "https://api.perplexity.ai/v1",
    id: "perplexity-agent/anthropic/claude-haiku-4-5",
    apiKey: process.env.PERPLEXITY_API_KEY,
    headers: {
      "X-Custom-Header": "value"
    }
  }
});

Dynamic model selection

const agent = new Agent({
  id: "dynamic-agent",
  name: "Dynamic Agent",
  model: ({ requestContext }) => {
    const useAdvanced = requestContext.task === "complex";
    return useAdvanced
      ? "perplexity-agent/xai/grok-4-1-fast-non-reasoning"
      : "perplexity-agent/anthropic/claude-haiku-4-5";
  }
});

Direct provider installation

This provider can also be installed directly as a standalone package, which can be used instead of the Mastra model router string. View the package documentation for more details.

npm install @ai-sdk/openai