docs.perplexity.ai

Design an agent's retry/backoff logic and account-tier expectations around Perplexity's usage-tier-based rate limits.

Have a Perplexity Sonar chat completion also return relevant images and suggested follow-up questions alongside the text answer.

Retrieve ranked raw web search results (no LLM-generated answer) via Perplexity's standalone Search API for retrieval-only agent pipelines.

Extract and correctly attribute the source URLs and metadata Perplexity used to ground a Sonar chat completion answer.

Call Perplexity's Sonar models from an existing OpenAI Python/TypeScript SDK integration by only swapping the base URL and API key.

Submit a long-running Perplexity Sonar request (e.g. sonar-deep-research) as a background async job and poll it to completion.

Stream a Perplexity Sonar chat completion token-by-token while still reliably capturing citations and search_results.

Force a Perplexity Sonar chat completion to return machine-readable JSON matching a caller-supplied schema instead of free text.

Constrain Perplexity Sonar/Search API results to a specific recency window or explicit publish/update date range.

Restrict Perplexity Sonar/Search API grounding to an explicit allowlist or denylist of domains using search_domain_filter.

Pick the cheapest Perplexity Sonar model that still meets an agent task's depth-of-research and reasoning needs.

Get a single grounded, cited answer to a natural-language question using Perplexity's Sonar chat completions endpoint.