The fastest OpenAI model is gpt-oss-safeguard-20b at 570 output tokens per second. gpt-oss-120b (free) (547 t/s) and gpt-oss-120b (547 t/s) round out the top three.
AI models ranked by output speed (tokens per second, p50). The fastest large language models for low-latency and high-throughput applications.
The fastest OpenAI model is gpt-oss-safeguard-20b at 570 output tokens per second. gpt-oss-120b (free) (547 t/s) and gpt-oss-120b (547 t/s) round out the top three.
gpt-oss-120b (free) (547 t/s) is the closest alternative on this metric, followed by gpt-oss-120b (547 t/s). 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.