Official @perplexity_ai developer account for real-time API updates.
- Tweets 158
- Following 40
- Followers 7,195
- Likes 255
We're looking forward to working with the new @NVIDIA Vera CPU on SPACE.
It was great to have the @NVIDIA team stop by and drop off their new Vera CPU.
A lot of what we’re building depends on agents being able to run more capable code environments, safely and reliably. We’re excited to test this work on Vera.
ALT NVIDIA and Perplexity team members standing with the Vera hardware.
3
7
111
30,205
Introducing the Perplexity Decisions API.
It's powered by pplx-decider-v1-27b, our multimodal decision model trained to output a probability distribution over a fixed set of answers instead of text.
It costs $0.04/million input tokens and scores 85.71% across benchmarks.
56
94
860
245,435
pplx-decider-v1-27b is fine-tuned from Qwen3.8-27B with a 250k context window.
View the weights on Hugging Face:
huggingface.co/perplexity-ai…
Get started with the Perplexity Decisions API:
docs.perplexity.ai/docs/deci…
4
10
131
14,029
You can use pplx-decider-v1-27b to triage customer support tickets, then route escalations to the Agent API.
Our cookbook shows how to build the workflow, using the Decisions API for the initial decision and the Agent API for escalated requests.
docs.perplexity.ai/docs/cook…
1
36
5,896
You can now build custom reusable agents in the Perplexity Agent API with Profiles, Skills, and managed connectors.
Configure an agent once in the API Portal and reuse it across applications and workflows.
9
9
134
42,191
A Profile saves the agent's model, instructions, tools, Skills, and managed connectors under one versioned ID.
Project members can reuse the same tools and instructions without rebuilding the configuration in every application.
Read more about Profiles:
pplx.ai/agent-profile
1
9
649
We created a cookbook recipe to test Profiles, Skills, and managed connectors together.
Follow it to build an incident responder that reads Datadog telemetry, diffs code in Sandbox, and posts an update to Slack.
pplx.ai/incident-response
6
291
Fast Search is now the default search in Hermes Agent for Nous Portal subscribers.
It’s built for agentic tasks, with single-search-call latency of 160 ms at p50 and 230 ms at p95.
Learn more: pplx.ai/hermes-fast-search
23
32
352
263,634
Fast Search is now available at $1 per 1,000 requests.
It delivers low-latency web search with the lowest cost per task among other search APIs.
Start building with Fast Search: pplx.ai/fast-search-api
Introducing Fast Search in the Perplexity Search API.
Fast Search runs on Photon, our new Rust-based retrieval and ranking service that we built with a small team of engineers and hundreds of agents.
It returns 95% of search results in 230 ms or less.
3
5
91
7,653
A new Perplexity Search SDK cookbook is live.
The recipe fans out focused searches, filters results to official docs, extracts relevant passages, and writes a source-linked brief for your coding agent.
Get started: pplx.ai/pplx-srch-sdk
8
7
59
50,033
Search SDK extracts query-relevant passages from URLs you provide.
Your agent can use those passages instead of full pages, keeping unrelated content out of the model context.
Install the Search SDK Agent Skill in your coding agent: pplx.ai/srch-sdk-agent-skill
1
4
683
Perplexity has joined the Rust Foundation.
We believe in supporting the people who build reliable open-source software. By joining the Rust Foundation, our goal is to improve how people and agents build with Rust.
43
74
1,388
606,622
SPACE is built in Rust and powers the sandboxes behind Perplexity Computer and the Agent API sandbox tool.
Read more about how we built SPACE: pplx.ai/space-blog
4
83
32,200
The Perplexity API MCP server now supports OAuth.
Add api.perplexity.ai/mcp to your client, sign in with your Perplexity account, choose your org, and approve.
Your agent gets real-time web search, deep research, and advanced reasoning.
Get started: pplx.ai/api-get-started
15
11
129
14,821
Under the hood, the MCP tools perplexity_ask, perplexity_research, and perplexity_reason run on Agent API.
Use Agent API for a single, multi-provider endpoint with built-in tools and dynamic presets.
pplx.ai/agent-api-blog
2
2
781
Perplexity Search API is now available in Hermes Agent.
Search API gives Hermes access to an index of more than 400 billion URLs. It returns real-time results and ranks snippets by relevance.
pplx.ai/hermes
30
36
400
309,333
Start building today and get $10 in free API credits when you create an account.
pplx.ai/api-get-started
3
3
29
5,220
Perplexity will be at RustConf 2026 next week.
@zbraniecki will present “Inside SPACE, the Rust Sandbox Platform Behind Perplexity Computer” on September 10. Then join us for happy hour from 5:30–7:30 PM.
Register at:
pplx.ai/rc-happy-hour
2
5
45
43,418
Perplexity API is now available in Stripe Projects.
In the Stripe CLI, type "stripe projects add perplexity/api" to get started.
Provision a Perplexity API project, API key, and prepaid credits straight from your terminal or coding agent using the Stripe Projects CLI.
pplx.ai/pplx-stripe-pro
4
8
45
6,032
New users automatically receive a Perplexity API project and key.
The API key works across the entire Perplexity API platform, including Agent API, Search API, and more.
docs.perplexity.ai/docs/gett…
1
1
5
550
If you already use the Perplexity API, link your existing project.
Linked API projects maintain their existing Perplexity billing.
pplx.ai/api-console
1
229