Perplexity Developers (@perplexitydevs) header
Perplexity Developers (@perplexitydevs) profile picture

Official @perplexity_ai developer account for real-time API updates.

Joined March 2025
Perplexity Context API is live. Context API reads up to 10 URLs per call and returns clean .md, HTML, links, and snippets per page. It returns usable content for 92.3% of URLs, 87.9% fact recall, and 80.3% content precision at $1/1000 URLs fetched. pplx.ai/context-api
15
13
9
179
56,657
We tested Context API against Firecrawl, Exa, Parallel, Keenable, and Contextdev on thousands of URLs from real agent requests. Context API performed the best across usability, fact recall, and content precision.
1
7
625
Access proprietary and open-weight models with a single API key through the Perplexity Orchestrator API. Learn more: docs.perplexity.ai/docs/orch…
Introducing the Perplexity Orchestrator API. Orchestrator lets you choose the right model for the right task, and automatically selects the provider based on availability, capacity, and latency. All open-weight and proprietary models are in one API with unified billing.
3
3
38
1,701
Perplexity Developers retweeted
We are live! Join us for an AMA with Perplexity's CTO, @denisyarats, and lead researcher on decision models, @antoine_chaffin @shashankgoyal95 will be chatting through Decider V1.3, Perplexity's new decision model that's free on OpenRouter right now, where search and AI are headed, and more. www.teapawt.org/i/broadcasts/2jPqVvgrL…
5
11
1
59
7,800
Today we're introducing the Perplexity Monitor API. Monitor API tracks new developments on a topic or changes to specific pages on a schedule, then sends relevant updates to your application through webhooks. Available now at $1/1k runs or URLs fetched. pplx.ai/monitor-api
19
22
15
317
145,625
You can set a plain-language goal for your monitor. Perplexity Decider checks web results for relevance, source legitimacy, new information, and freshness. Monitor can track changes to up to 10 pages, like a pricing page, changelog, or policy page.
1
21
10,515
Monitors run on a fixed interval or a custom cron schedule. Updates arrive through signed webhooks, with automatic retries for transient delivery failures. Create a monitor through the API or API Console using the same API key as Search and Agent API: docs.perplexity.ai/docs/moni…
10
2,451
We're rolling out pplx-decider-v1.3 and pplx-decider-flash-v1.3, the latest version of our open-weight decision models. v1.3 adds locate, a new feature that extracts spans based on type or instructions. Now available in our Decisions API, @huggingface, and @OpenRouter. perplexity.ai/hub/blog/perpl…
33
34
34
384
83,641
Every Agent API effort level now costs less with the same or higher research quality. Effort levels are bundled agent configurations, optimized for specific tasks. A new ultra level is available for the most demanding, long-running requests. pplx.ai/effort-levels
11
2
7
68
24,265
ultra runs three research agents in parallel and a fourth orchestrates, assigns tasks, and merges the findings. Every child agent runs its own research loop with a separate context, using its own model, tools, and step budget.
1
11
892
The Decisions API can now search the web before it answers. A decision model returns a probability, but only knows what it saw in training, and your state. Add "mode": "web_grounding" and Fast Search runs one query per question, so pplx-decider-v1.2 answers from today's web.
14
12
12
205
33,561
When enabled, Fast Search results join state as evidence before the decision model answers. Pass a URL as the state to ask about a page. Requests are $0.001 per search and $0.02 per 1M tokens. pplx.ai/web-grounded-docs
1
16
1,069