Official @perplexity_ai developer account for real-time API updates.
Joined March 2025
- Tweets170
- Following39
- Followers7.9K
- Likes255
Perplexity Developers retweeted
Introducing SPACE, the sandbox platform behind Perplexity Computer.
It creates isolated environments for code, files, and long-running agent sessions.
SPACE has handled 100% of Computer production traffic since June.
research.perplexity.ai/artic…
Perplexity Developers retweeted
I used the new wide-research preset in the Perplexity API to check the most recent earnings call for every company in the S&P 500 for mentions of "AI agents", and pull the corresponding YoY revenue growth for each.
The agent pulled historical financials and earnings call transcripts for 500 companies, with every output row cited. Computer outputted the results to a dashboard, and deployed it publicly.
Results: 66 companies mentioned AI agents, with median YoY growth +12.7% for that cohort, compared to +8.1% for the rest.
Good example of how the Perplexity API's wide-research preset can tackle an in-depth task for an n=500 use case.
Narrow search is essentially solved. That's why simple browse/search benchmarks are so saturated.
The frontier is wide research: find every qualifying result and back each one with evidence.
Today we launched WANDR, a 500-task benchmark built on real knowledge work. It's difficult even for today's most powerful models.
Perplexity Agent API's Search as Code architecture excels on WANDR because it allows the model to design the research once and then deterministically execute it at scale without overwhelming the model’s context.
Using wide research in your existing agent research workflows? Try out our wide-research preset in Agent API: docs.perplexity.ai/docs/agen…
WANDR Research Article: research.perplexity.ai/artic…
Github Repo: github.com/perplexityai/wand…
Perplexity Developers retweeted
This agent drafts a cited VC investment memo in ~90 seconds for $0.40.
1️⃣ 4 LangGraph nodes powered by the @Perplexity_AI Agent API research financials, product, and market in parallel
2️⃣ A tool-less synthesizer writes the memo from only what they found
Deep dive:
langchain.com/blog/build-an-…
Perplexity Developers retweeted
GLM-5.2 is available in Perplexity's Agent API. Just tested it, and it's powerful when paired with the Search SDK inside a sandbox.
- Spin up a sandbox environment
- Call the web search tool (people search, finance search, etc. also work)
- Pretty good for wide & deep research
@Zai_org's flagship model, GLM-5.2, is now available in Perplexity's Agent API.
GLM-5.2 is one of the strongest open-source models for long-horizon coding and agentic workflows. It shines in Agent API, making particularly effective use of our Search as Code architecture.
Combine frontier reasoning with real-time programmatic search with just one API call.
OpenAI-compatible interface and first-party pricing with no markup.
Get started: docs.perplexity.ai/docs/agen…
Perplexity Developers retweeted
Today we're announcing that hybrid agentic inference is coming to Perplexity Computer.
Computer can split tasks between a local model running on your machine and frontier models in the cloud. This keeps private data on your device and maximizes token efficiency.
Coming soon.
Perplexity Developers retweeted
🌐 @perplexity_ai is now integrated with @Haystack_AI!
- `PerplexityWebSearch` to fetch fresh web results directly into your pipelines
- `PerplexityChatGenerator` to power agent conversations with Perplexity's OpenAI-compatible LLM API
- `PerplexityTextEmbedder` and `PerplexityDocumentEmbedder` for semantic embeddings
The web search component is especially useful when your agents need real-time information beyond their training data. Just instantiate it with your API key, set `top_k` results, and pass your query. You get back both documents and source links in a single call. Perplexity's API combines language models with live web access, making it a strong choice for building knowledge-intensive applications that need current information.
🐍 pip install perplexity-haystack
🧩 haystack.deepset.ai/integrat……
📖 docs.perplexity.ai
Perplexity Developers retweeted
MiniMax Agent now uses @perplexity_ai Search.
We benchmarked 3 AI-native search providers across 700+ agent tasks. Perplexity delivered the best combination of answer quality and snippet density: more useful evidence per token, less irrelevant context, and lower end-to-end cost.
Compared with Serper, our previous default:
⚡Tool calls per task: 17.8 vs 32.6 (45% reduction)
💰Token usage: 94.6M vs. 162.3M (42% reduction)
🔍Pass rate: +2% increase
Total cost: 27% decrease in total cost savings
In agent workflows, search is not a one-shot lookup. It is a loop.
Better snippets mean better grounding. Better grounding means fewer searches, less context, better answers, and lower cost.
One good search can save 14 bad ones.
Now shipping in MiniMax Agent.
agent.minimax.io/
Perplexity Developers retweeted
We've productionized query-aware compression for faster, cleaner, more-accurate search.
Better context is better than more context.
Our system cuts context tokens up to 70% while improving answer quality.
Perplexity Developers retweeted
We’ve developed our own inference engine Runtime-Optimized Serving Engine (ROSE) to serve models ranging from embeddings to trillion-parameter LLMs.
With CuTeDSL integrated into our inference engine, Perplexity can build the specialized GPU kernels faster to bring models up to peak performance on NVIDIA Hopper and Blackwell GPUs.
Perplexity Developers retweeted
Perplexity now powers Samsung’s Browsing Assist in the Samsung Browser on Galaxy Android and Windows.
Read more: perplexity.ai/hub/blog/perpl…
Perplexity Developers retweeted
System-level AI on the Galaxy S26. Real-time search and reasoning for Bixby. Agentic web automation in Samsung Internet. All via Perplexity's APIs. Proud to see this ship.
Perplexity Developers retweeted
We’ve partnered with Samsung to bring Perplexity directly into the upcoming Galaxy S26.
Every new S26 will ship with Perplexity built in as a system‑level AI, with its own wake word: “Hey Plex.”
Perplexity Developers retweeted
DM me for early API access!
Perplexity Developers retweeted
We're bringing Perplexity to London! 🇬🇧
Join us Oct 17–18 for our first UK Hackathon — 24hrs of building with the Sonar API!
💡 Exclusive beta features
🏆 $10K+ in prizes
🥡 Food, swag & community
Perplexity Developers retweeted
Today we're launching Perplexity Search API - giving devs access to the same infrastructure powering our answer engine. Real-time, citation-rich, built for AI.
Excited to see what you build!
Introducing Perplexity Search API
We've built a search index of billions of webpages to provide real-time, quality information from the web.
Now developers have access to the full power of our index, providing the most accurate results in milliseconds.
perplexity.ai/hub/blog/intro…
Perplexity Developers retweeted
Introducing Perplexity Search API
We've built a search index of billions of webpages to provide real-time, quality information from the web.
Now developers have access to the full power of our index, providing the most accurate results in milliseconds.
perplexity.ai/hub/blog/intro…
Perplexity Developers retweeted
Sonar APl updates — full transparency & dev control:
- Now receive exact query snippets: source, title, date, url, text.
- Doubled domain filter limit to 20.
- New image quality params & query type classification.
It's your search engine — we just hand you the tools.
Perplexity Developers retweeted
Sonar just got a massive upgrade.
- Async mode + reasoning effort are now live for Sonar deep research: more control, improved workflows.
- Academic mode now on all models
- Every citation is now richer: title, url, date.
Let's see what you build next. Stay curious.
Perplexity Developers retweeted
Le Monde — one of the most respected newspapers in the world — is now using our Sonar API to power search + discovery on their site.
Real-time, grounded answers. Directly on one of the most trusted destinations on the internet.
Huge moment for open knowledge.
Perplexity Developers retweeted
Our Sonar-Reasoning-Pro-High model tied for first place with Gemini-2.5-Pro-Grounding on @lmarena_ai's new Search Arena.
Sonar-Reasoning-Pro-High beat Gemini-2.5-Pro-Grounding 53% of the time while the rest of the Sonar models outperformed all other models.
