gpt-oss-120b (free) has the lowest latency of any OpenAI model, responding in about 170ms to first token. gpt-oss-120b (170ms) and gpt-oss-safeguard-20b (253ms) 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.
gpt-oss-120b (free) has the lowest latency of any OpenAI model, responding in about 170ms to first token. gpt-oss-120b (170ms) and gpt-oss-safeguard-20b (253ms) round out the top three.
gpt-oss-120b (170ms) is the closest alternative on this metric, followed by gpt-oss-safeguard-20b (253ms). See the full ranking above for the tradeoffs.
modelgrep tracks 62 OpenAI models with live benchmarks, speed, latency and per-provider pricing, led on intelligence by GPT-5.4. 25 of them qualify for this ranking.