HQ: United StatesDatacenters: United StatesPrivacyTerms
Average response time
18.84 s
Estimated 500-token answer. Across 19 models with recent complete speed data.
Average response start
0.40 s
Wait until the first token. Across 19 models with recent response start data.
Average output speed
79.8 tok/s
Generated tokens per second. Across 19 models with recent output speed data.
AI Models available from Weights & Biases
Prices and recent speed measurements below are for Weights & Biases endpoints. A 500-token response combines the wait for the first token with the time to generate 500 output tokens.
How to evaluate Weights & Biases as an AI inference provider
Weights & Biases currently has 19 indexed models on this site, including 19 text. This page combines the provider-specific catalog with published pricing and recent performance data so you can identify suitable models and then compare Weights & Biases with alternative hosts on each model page.
Review model coverage
Weights & Biases 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 $0.03 / 1M tokens. Recent 500-token response measurements are available for 19 models; missing measurements remain visible and are never estimated.
Confirm deployment requirements
Weights & Biases lists its headquarters as US. Published datacenter coverage: US. Headquarters and hosting regions describe different things, so verify data residency, service terms, and current availability directly with the provider.
