Skip to content

Anthropic API

Hosted API
Models on live video
3
Regions measured
3
Real-time models
1 of 3
Median output speed
95 tok/s
Median E2E · US East
9.2 s
Median blended $/1M
$6.32

Models on Anthropic API

#Details
1View claude-haiku-4-5Claude Haiku 4.5Anthropic
221 tok/s
60 ms169 ms$4.34<200 ms
2View claude-sonnet-4-6Claude Sonnet 4.6ReasoningAnthropic
95 tok/s
144 ms9.2 s$6.32
3View claude-opus-4-6Claude Opus 4.6ReasoningAnthropic
55 tok/s
207 ms12 s$6.93
Output speed by model
Output speed by model. 3 bars. Highest: Claude Haiku 4.5 at 221 tok/s. Toggle the data table for exact values.Claude Haiku 4.5Claude Haiku 4.5221 tok/sClaude Sonnet 4.6Claude Sonnet 4.695 tok/sClaude Opus 4.6Claude Opus 4.655 tok/s

Reasoning models are indicated by a lightbulb icon

Real-time coverage

US East (Virginia)1 of 3 under 200 ms
US West (Oregon)1 of 3 under 200 ms
EU West (Ireland)1 of 3 under 200 ms

Latency columns use the US East (Virginia) reference region. Real-time marks a model that closes the loop under 200 ms end to end on Anthropic API from at least one region.