Introducing Bird SQL, a Twitter search interface that is powered by Perplexity’s structured search engine. It uses OpenAI Codex to translate natural language into SQL, giving everyone the ability to navigate large datasets like Twitter. perplexity.ai/sql
With Bird SQL, you can quickly find information on Twitter that would have been impossible to find with conventional search engines or web browsing:
"most liked tweets about #worldcup" perplexity.ai/sql?uuid=9b03e…
If you are interested in using our search engine on your structured or unstructured data, contact us at support@perplexity.ai, our Discord server, or via Twitter. Join our Discord to learn more about search and large language models: discord.com/invite/kWJZsxP…
This is a demo, not a commercial product. There are limitations to our Twitter data, database performance, and the expressiveness of SQL. Bird SQL does not interpret the content of tweets. For unstructured search, try Perplexity Ask.
The work targets XLM-RoBERTa’s 250K-token Unigram vocabulary, commonly used for ranking and retrieval.
The encoder produces the same tokens as the reference implementation, but avoids rebuilding strings and chasing hash maps while deciding how text should be split.
At production input lengths, the encoder cuts p50 latency by roughly 5× vs. HuggingFace tokenizers, 2× vs. SentencePiece C++, and 1.5× vs. IREE C.
At 514 tokens, it runs in 63 µs with zero heap allocations.
Today we're launching Perplexity Computer for Professional Finance.
Finance teams can bring licensed data from providers like Morningstar, PitchBook, Daloopa, and Carbon Arc into Computer.
We’ve also added 35 dedicated finance workflows for the work analysts repeat every week.
Company tearsheet: enter a company and get a brief with the business summary, key metrics, recent news, and sources.
Annotated stock chart: enter a ticker and get a chart marked up with relevant events: earnings, news, product launches, market moves, or other catalysts.
Perplexity Computer now connects to your health apps, wearable devices, lab results, and medical records.
Build personalized tools and applications with your health data, or track everything in your health dashboard.
Combine personal health data with premium sources and medical journals for endless new ways to interact with your health information.
Build a custom marathon training protocol based on fitness data, generate a visit prep summary ahead of a doctor's appointment, or create personalized nutrition plans.
The Perplexity API platform is now a full-stack, model-agnostic API platform for building agents.
It replaces your model provider, search layer, and embeddings, built on the same infrastructure that powers Perplexity.
The Perplexity API platform consists of four APIs with one API key.
Agent API — orchestrate models for multi-step workflows
Search API — real-time web context
Embeddings API — retrieval at scale
Sandbox API — code execution for agents (coming soon)
Perplexity Agent API is a managed runtime for building agentic workflows with integrated search, tool execution, and multi-model orchestration.
Swap between the latest frontier models, configure curated presets, tool access, step limits, and token budgets, all from one endpoint.