Fastest LLM APIs (real-world speed ranking)

As of 2026-11-05, the top model is MiniMax-M3.1-Flash (308 tok/s). See the full ranking below — click a model for details or run your own test.

⚡ Fastest💰 Cheapest⭐ Best value
  1. 🥇
    MiniMax-M3.1-Flashapi.minimax.io
    TTFT 0.61s · peak 144 · 2 runs
    308 tok/s
  2. 🥈
    deepseek-flashapi.deepseek.com
    TTFT 0.74s · peak 179 · 2 runs
    292 tok/s
  3. 🥉
    mimo-v2.6-proapi.xiaomimimo.com
    TTFT 1.46s · peak 256 · 1 runs
    143 tok/s
  4. 4
    tencent/hy3-freeapi.orcarouter.ai
    TTFT 1.22s · peak 137 · 2 runs
    136 tok/s
  5. 5
    deepseek-v4-proapi.deepseek.com
    TTFT 3.47s · peak 0 · 8 runs
    132 tok/s
  6. 6
    deepseek-v4-flashapi.deepseek.com
    TTFT 3.21s · peak 0 · 8 runs
    132 tok/s
  7. 7
    glm-5.3open.bigmodel.cn
    TTFT 3.38s · peak 270 · 2 runs
    100 tok/s
  8. 8
    L2LongCat-2.5-Previewapi.longcat.chat
    TTFT 1.46s · peak 119 · 1 runs
    88 tok/s
  9. 9
    kimi-k3api.moonshot.cn
    TTFT 2.90s · peak 103 · 2 runs
    81 tok/s
  10. 10
    qwen-plusdashscope.aliyuncs.com
    TTFT 0.87s · peak 47 · 2 runs
    40 tok/s
Full pricing →Speed leaderboard →Run your own test ▶
📋 Embed this ranking on your site

Copy the code below (live data, auto-updating):

<iframe src="https://www.tokrace.com/embed/best/fastest?lang=en" width="400" height="360" style="border:0;border-radius:12px" loading="lazy" title="Fastest LLM APIs (real-world speed ranking)"></iframe>

· Speed is the median of anonymous benchmarks; prices follow official pages and cross-currency uses a fixed USD rate. Reference only.