Fastest LLMs

AI models ranked by output speed (tokens per second, p50). The fastest large language models for low-latency and high-throughput applications.

1. 1M
   morph-v3-fast

   $0.800/M · 495ms ttft · 82K ctx
   3.1k t/s

   Speed
2. 2M
   morph-v3-large

   $0.900/M · 435ms ttft · 262K ctx
   3.0k t/s

   Speed
3. 3O
   gpt-oss-safeguard-20b

   ReasoningToolsJSON$0.075/M · 235ms ttft · 131K ctx
   530 t/s

   Speed
4. 4Z
   glm-4.7

   ReasoningToolsJSON42.1 intel · $0.400/M · 564ms ttft
   474 t/s

   Speed
5. 5O
   gpt-oss-120b:free

   ReasoningTools24.5 intel · Free/M · 181ms ttft
   450 t/s

   Speed
6. 6O
   gpt-oss-120b

   ReasoningToolsJSON24.5 intel · $0.039/M · 181ms ttft
   450 t/s

   Speed
7. 7X
   grok-4.20-multi-agent

   ReasoningJSONVision$2.00/M · 21.7s ttft · 2M ctx
   355 t/s

   Speed
8. 8O
   gpt-oss-20b:free

   ReasoningToolsJSON24.5 intel · Free/M · 235ms ttft
   348 t/s

   Speed
9. 9O
   gpt-oss-20b

   ReasoningToolsJSON24.5 intel · $0.029/M · 235ms ttft
   348 t/s

   Speed
10. 10M
    minimax-m2.7

    ReasoningToolsJSON49.6 intel · $0.250/M · 673ms ttft
    334 t/s

    Speed
11. 11I
    mercury-2

    ReasoningToolsJSON32.8 intel · $0.250/M · 303ms ttft
    328 t/s

    Speed
12. 12Q
    qwen3-32b

    ReasoningToolsJSON16.5 intel · $0.080/M · 292ms ttft
    303 t/s

    Speed
13. 13M
    phi-4-mini-instruct

    JSON8.4 intel · $0.080/M · 140ms ttft
    277 t/s

    Speed
14. 14N
    nemotron-3-super-120b-a12b:free

    ReasoningToolsJSON36.0 intel · Free/M · 1.2s ttft
    240 t/s

    Speed
15. 15N
    nemotron-3-super-120b-a12b

    ReasoningToolsJSON36.0 intel · $0.090/M · 1.2s ttft
    240 t/s

    Speed
16. 16G
    gemini-2.5-flash-lite-preview-09-2025

    ReasoningToolsJSON+219.4 intel · $0.100/M · 397ms ttft
    202 t/s

    Speed
17. 17M
    minimax-m2.5

    ReasoningToolsJSON41.9 intel · $0.150/M · 521ms ttft
    199 t/s

    Speed
18. 18N
    nemotron-3-nano-omni-30b-a3b-reasoning:free

    ReasoningToolsVision+121.4 intel · Free/M · 436ms ttft
    194 t/s

    Speed
19. 19G
    gemini-2.5-flash-image

    JSONVisionImage out$0.300/M · 1.7s ttft · 33K ctx
    189 t/s

    Speed
20. 20Q
    qwen3.5-35b-a3b

    ReasoningToolsJSON+130.7 intel · $0.140/M · 400ms ttft
    174 t/s

    Speed
21. 21Q
    qwen3.6-35b-a3b

    ReasoningToolsJSON+131.5 intel · $0.150/M · 310ms ttft
    173 t/s

    Speed
22. 22A
    trinity-large-thinking

    ReasoningToolsJSON31.9 intel · $0.220/M · 542ms ttft
    168 t/s

    Speed
23. 23Q
    qwen3-next-80b-a3b-thinking

    ReasoningToolsJSON26.7 intel · $0.098/M · 352ms ttft
    168 t/s

    Speed
24. 24G
    gemini-3.5-flash

    ReasoningToolsJSON+243.3 intel · $1.50/M · 1.7s ttft
    164 t/s

    Speed
25. 25M
    kimi-k2-0905

    ToolsJSON30.9 intel · $0.600/M · 258ms ttft
    162 t/s

    Speed