Claude Haiku 4.5 has the lowest latency of any Anthropic model, responding in about 521ms to first token. Claude 3 Haiku (542ms) and Claude Sonnet 4 (699ms) round out the top three.
AI models ranked by time-to-first-token (p50). The most responsive large language models for real-time and interactive use cases.
Claude Haiku 4.5 has the lowest latency of any Anthropic model, responding in about 521ms to first token. Claude 3 Haiku (542ms) and Claude Sonnet 4 (699ms) round out the top three.
Claude 3 Haiku (542ms) is the closest alternative on this metric, followed by Claude Sonnet 4 (699ms). See the full ranking above for the tradeoffs.
modelgrep tracks 16 Anthropic models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by Claude Fable 5. 14 of them qualify for this ranking.