Estimated 500-token answer. Across 18 models with recent complete speed data.
Average response start
2.21 s
Wait until the first token. Across 18 models with recent response start data.
Average output speed
30.4 tok/s
Generated tokens per second. Across 18 models with recent output speed data.
AI Models available from Phala
Prices and recent speed measurements below are for Phala endpoints. A 500-token response combines the wait for the first token with the time to generate 500 output tokens.
Phala currently has 18 indexed models on this site, including 18 text. This page combines the provider-specific catalog with published pricing and recent performance data so you can identify suitable models and then compare Phala with alternative hosts on each model page.
Review model coverage
Phala 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 1M tokens.
Interpret price and speed together
The lowest published input price shown here is $0.04 / 1M tokens. Recent 500-token response measurements are available for 18 models; missing measurements remain visible and are never estimated.
Confirm deployment requirements
Phala 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.
