Perplexity built Photon, a new in-house retrieval and ranking engine. It replaces an adapted open-source system that hit cost, latency, and recovery limits. Photon uses compact data formats, batched reads, and separate index building from query serving. It now powers Perplexity’s search pipeline. A new fast preset for the Search API offers 160 ms p50 and 230 ms p95 latency. Across six benchmarks, the fast preset cut estimated model-plus-search cost per task by 68%. Task quality remained comparable to the default preset. The fast preset is available to developers today.
What changed
Search ran on an adapted open-source retrieval and ranking engine with high costs, tail latency, and slow node recovery.
What it unlocks
Developers can now use a fast preset in Perplexity’s Search API with lower latency and cost while maintaining task quality.
- 160 ms p50 latency
- 230 ms p95 latency
- 68% lower estimated cost per task
- 64.3% task quality at $59.73
What you need to act on it
- using Perplexity’s Search API
Sources