InfraPerplexityConfirmed
Story 4 of 18 in the Wednesday 18 November editionPerplexity launches Context API for agent URL extraction at $1 per 1k
Live on 18 November 2026 at POST /v1/context, returning clean Markdown, HTML, links, query highlights and Open Graph metadata with zero charge on failed URLs.

Perplexity launched the Perplexity Context API (POST /v1/context) on 18 November 2026, adding a parallel web-page extraction primitive alongside its Orchestrator API and Monitor API. Each request accepts 1 to 10, 15 or 25 HTTP/HTTPS URLs by usage tier (up to 50 on raised limits) and returns ordered per-page Markdown, raw HTML, deduplicated absolute links, query-matched passage highlights (1 to 4,096 tokens per URL, default 1,024) and Open Graph metadata.
Freshness controls, per-URL fault isolation and 715-site benchmark scores
To build Markdown, Context API splits each document into blocks and runs a classifier model to strip cookie banners, navigation and ads while keeping verbatim source passages. By default it serves copies from Perplexity’s index fetched within the prior two days before live fetching, with overrides for max_age_seconds (0 for forced live reads up to two years), cache_only, if_modified_since and 1-to-5 decision criteria questions.
URLs execute in parallel with independent timeouts (1,000 to 110,000 ms overall, or 95,000 ms with criteria), billing $1 per 1,000 URLs returning ok ($0.001 per URL) and $0 for failed fetches. Across thousands of agent URLs spanning 715 sites judged blindly against Firecrawl, Exa, Parallel, Keenable and Context.dev, Context API scored 92.3% usable content, 87.9% fact recall and 80.3% content precision.
Technical details
- Endpoint and billing
- POST https://api.perplexity.ai/v1/context at $1 per 1,000 URLs returning ok (failed URLs unbilled)
- Batch limits and request cap
- 10, 15 or 25 URLs per call by usage tier (up to 50 raised); 512 KiB max request body
- Response formats and freshness
- markdown (default), html, links, highlights (1-4,096 tokens) and metadata; 2-day default index cache
- 715-site blind evaluation
- 92.3% usable URLs, 87.9% key-fact recall and 80.3% content precision vs five rival extractors
Release details & context
Per-URL status codes, conditional fetches and server error semantics
Perplexity’s quickstart documentation distinguishes whole-request HTTP failures from granular per-URL outcomes. While HTTP 400 rejects malformed payloads over 512 KiB or unsupported format combinations and HTTP 5xx discards partial batches so callers can retry cleanly, HTTP 200 responses report individual URL states including unchanged since if_modified_since, blocked URLs, bot_challenge blocks and upstream status codes so agents only retry timed-out targets.
Passing an empty formats array returns page metadata and Open Graph tags alone without transferring full Markdown or HTML bodies, and HTML output is omitted automatically on non-HTML documents such as PDFs.
Common questions
How do developers force Perplexity’s Context API to bypass its two-day web index cache?
Set max_age_seconds to 0 on the POST /v1/context request to force a live fetch of every URL, or set cache_only to true when a workflow must never trigger outbound live requests.
Does Perplexity charge for URLs that time out or hit a bot challenge in a Context API batch?
No, Perplexity bills $0.001 only for each URL that returns ok, leaving failed, blocked or timed-out URLs unbilled.
Sources
- PrimaryPerplexity Hub: Context API extracts full context from any web pageperplexity.ai
- OfficialPerplexity Docs: Context API quickstartdocs.perplexity.ai
- On XPerplexity Developers (@perplexitydevs) Context API launch post on Xx.com
- On XAravind Srinivas (@AravSrinivas) Context API announcement on Xx.com
Perplexity release timeline (13 launches tracked)
- Perplexity launches Monitor API for scheduled web and page webhooks
Perplexity launches the Monitor API to watch web topics or up to 10 URLs on cron schedules and send Decider-filtered webhooks at $1 per 1k runs.
- Perplexity launches Frontier Research lab backed by 10,000+ GPUs
Perplexity forms Perplexity Frontier Research with 10,000+ GPUs to build autonomous research systems and publish open-source models and data.
- Perplexity launches Orchestrator API to route across 45+ AI models
Perplexity launches its Orchestrator API to route requests across more than 45 open-weight and proprietary models under one API key and bill.
- Perplexity rolls out Multiagent mode in Computer and Teammates for Max
Perplexity rolls out a Multiagent effort level on web for Max subscribers in Computer and Teammates to run parallel multi-model research streams.

