Perplexity

perplexity

YAML config

providers:
  - id: perplexity:sonar-large-32k-online
    config:
      apiKey: ${PERPLEXITY_API_KEY}

TypeScript usage

import { createProvider } from "@evalguard/core";

const provider = createProvider("perplexity", process.env.PERPLEXITY_API_KEY);
const response = await provider.complete({
  model: "sonar-large-32k-online",
  messages: [{ role: "user", content: "Hello" }],
});

Authentication

Set PERPLEXITY_API_KEY in your environment. EvalGuard validates the key on first call and surfaces typed errors for 401 / 403 / rate-limit responses (with Retry-After parsing).

Setup walkthrough

  1. 1. Sign up for an account on the Perplexity website.
  2. 2. Obtain your API key from the account dashboard.
  3. 3. Review the API documentation to understand the endpoints and parameters.
  4. 4. Set up your development environment with the necessary libraries for making HTTP requests.
  5. 5. Test the API with a simple request to ensure your setup is correct.

Gotchas

  • API rate limits are enforced; exceeding them may result in temporary access restrictions.
  • Certain features may not be available in all regions; check the documentation for regional limitations.
  • Authentication tokens may expire; ensure to handle token refresh in your application.

Cost note

Pricing is $0.002 per 1,000 tokens for the cheapest model and $0.006 per 1,000 tokens for the flagship model.

Recommended models

Eval / judge
perplexity-3.5-turbo
Agent / tool-use
perplexity-3.5-turbo
Code
perplexity-codex-1
Vision
perplexity-vision-1

LLM-generated (llm-gpt-4o) · 2026-05-23