Start typing to search.
Average response time
49.22 s
Estimated 500-token answer. Across 38 models with recent complete speed data.
Average response start
4.67 s
Wait until the first token. Across 38 models with recent response start data.
Average output speed
55.1 tok/s
Generated tokens per second. Across 38 models with recent output speed data.
Prices and recent speed measurements below are for Azure endpoints. A 500-token response combines the wait for the first token with the time to generate 500 output tokens.
Model data fetched .
Practical comparison guide
Azure currently has 50 indexed models on this site, including 45 text, 1 image, 1 transcription, 1 speech, 2 embeddings. This page combines the provider-specific catalog with published pricing and recent performance data so you can identify suitable models and then compare Azure with alternative hosts on each model page.
Azure 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 1.1M tokens.
The lowest published input price shown here is $0.02 / 1M tokens. Recent 500-token response measurements are available for 38 models; missing measurements remain visible and are never estimated.
Azure lists its headquarters as US. Published datacenter coverage: swedencentral, us-east-2. Headquarters and hosting regions describe different things, so verify data residency, service terms, and current availability directly with the provider.
