Perplexity stands as both the fastest and highest-quality API on the marketplace. We deliver a median latency of 358ms—over 150ms faster than the next-best provider—while keeping 95th-percentile latency under 800ms.
SOFTWARE
-
Perplexity Search API: Completeness, Freshness, Speed
By
–
We built Perplexity Search API around three criteria: 1. Completeness + freshness + speed
2. Fine-grained content understanding
3. Hybrid retrieval and ranking. The system processes ~200M daily queries using distributed crawling/indexing, multi-stage ranking, and dynamic -
New Search API Launched for AI Systems Integration
By
–
With Microsoft retiring the Bing Search APIs in August, legacy search engines have abandoned the developer community who need real-time access to information. We're stepping in to provide a search API designed for the new retrieval paradigms introduced by frontier AI systems.
-
Perplexity Launches Search API for Real-Time Web Information
By
–
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. https://
perplexity.ai/hub/blog/intro
ducing-the-perplexity-search-api
… -
ElevenLabs Dominates Audio TTS Market with v3 Model and Music AI
By
–
In audio, ElevenLabs defends its TTS lead (~74% share), with its new v3 model seeing swift adoption. Music models also emerged on Poe this summer, with ElevenLabs Music taking an early 10.1% share of the audio category, ahead of Google's Lyria at 3.3%. (5/6)
-
Model Release Enables Developers to Build AI Apps Locally
By
–
I'm happy it's released, it was such a cool post-training project Now I hope that app developers can take these models and build cool stuff with them, with less reliance on costly and slow cloud models. There's so much to do, life is too short to optimize ChatGPT prompts!
-
LFM2-1.2B Achieves Parity with Larger Models for Edge
By
–
For latency purposes on edge devices, we wanted it to be a non-thinking model. That was a big challenge, but we managed to squeeze a ton of performance from LFM2-1.2B and perform on par with much bigger models on our internal bench (see figure) but also BFCL v3 and v4.
-
350M Model Shows Power of Fine-Tuning for Big Data
By
–
It comes in two sizes: 1.2B and 350M I'm a big fan of the 350M model that can be used on GPUs to do big data operations. It's an absolute banger that shows how powerful fine-tuning can be
-
Tiny Task-Specific AI Models for Edge Devices
By
–
We're releasing a collection of tiny task-specific models Want to do data extraction, translation, RAG, tool use, or math on a Raspberry Pi? We got you covered! Here are a few examples ↓