Estimated 500-token answer. Across 5 models with recent complete speed data.
Average response start
17.17 s
Wait until the first token. Across 5 models with recent response start data.
Average output speed
52.2 tok/s
Generated tokens per second. Across 5 models with recent output speed data.
AI Models available from Perplexity
Prices and recent speed measurements below are for Perplexity endpoints. A 500-token response combines the wait for the first token with the time to generate 500 output tokens.
How to evaluate Perplexity as an AI inference provider
Perplexity currently has 7 indexed models on this site, including 2 embeddings, 5 text. This page combines the provider-specific catalog with published pricing and recent performance data so you can identify suitable models and then compare Perplexity with alternative hosts on each model page.
Review model coverage
Perplexity offers model-specific routes rather than one interchangeable service. Check modality, context window, supported inputs, and parameter support before comparing price. The largest published context window in this catalog is 200K tokens.
Interpret price and speed together
The lowest published input price shown here is $0.004 / 1M tokens. Recent 500-token response measurements are available for 5 models; missing measurements remain visible and are never estimated.
Confirm deployment requirements
Perplexity lists its headquarters as US. Published datacenter coverage: no datacenter regions are currently published. Headquarters and hosting regions describe different things, so verify data residency, service terms, and current availability directly with the provider.
