Fastest Anthropic Models

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

1. 1A
   claude-opus-4.8-fast

   ReasoningToolsJSON+1$10.00/M · 1.6s ttft · 1M ctx
   121 t/s

   Speed
2. 2A
   claude-haiku-4.5

   ReasoningToolsJSON+131.0 intel · $1.00/M · 521ms ttft
   82 t/s

   Speed
3. 3A
   claude-3-haiku

   ToolsVision12.3 intel · $0.250/M · 542ms ttft
   68 t/s

   Speed
4. 4A
   claude-opus-4.7

   ReasoningToolsJSON+157.3 intel · $5.00/M · 1.6s ttft
   63 t/s

   Speed
5. 5A
   claude-opus-4.5

   ReasoningToolsJSON+143.1 intel · $5.00/M · 777ms ttft
   60 t/s

   Speed
6. 6A
   claude-opus-4.8

   ReasoningToolsJSON+161.4 intel · $5.00/M · 1.8s ttft
   59 t/s

   Speed
7. 7A
   claude-sonnet-4

   ReasoningToolsVision33.0 intel · $3.00/M · 699ms ttft
   49 t/s

   Speed
8. 8A
   claude-sonnet-4.6

   ReasoningToolsJSON+142.6 intel · $3.00/M · 1.0s ttft
   47 t/s

   Speed
9. 9A
   claude-sonnet-4.5

   ReasoningToolsJSON+137.1 intel · $3.00/M · 880ms ttft
   46 t/s

   Speed
10. 10A
    claude-opus-4.6

    ReasoningToolsJSON+152.9 intel · $5.00/M · 1.5s ttft
    41 t/s

    Speed
11. 11A
    claude-3.5-haiku

    ToolsVision18.7 intel · $0.800/M · 832ms ttft
    35 t/s

    Speed
12. 12A
    claude-opus-4.1

    ReasoningToolsJSON+1$15.00/M · 2.1s ttft · 200K ctx
    27 t/s

    Speed
13. 13A
    claude-opus-4.6-fast

    ReasoningToolsJSON+1$30.00/M · 1.3s ttft · 1M ctx
    11 t/s

    Speed
14. 14A
    claude-opus-4

    ReasoningToolsVision$15.00/M · 2.3s ttft · 200K ctx
    10 t/s

    Speed