Estimated 500-token answer. No recent complete speed measurements are published.
Average response start
Insufficient recent data
Wait until the first token. No recent response start measurements are published.
Average output speed
Insufficient recent data
Generated tokens per second. No recent output speed measurements are published.
AI Models available from Recraft
Prices and recent speed measurements below are for Recraft endpoints. A 500-token response combines the wait for the first token with the time to generate 500 output tokens.
How to evaluate Recraft as an AI inference provider
Recraft currently has 11 indexed models on this site, including 11 image. This page combines the provider-specific catalog with published pricing and recent performance data so you can identify suitable models and then compare Recraft with alternative hosts on each model page.
Review model coverage
Recraft 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 65.5K tokens.
Interpret price and speed together
The lowest published input price shown here is Free. Recent 500-token response measurements are available for 0 models; missing measurements remain visible and are never estimated.
Confirm deployment requirements
Recraft does not currently publish a headquarters location in the catalog. 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.
