Skip to content

Value ranking

Best value on Output Speed

As of October 25, 2026, the best value on Output Speed is GPT-5.6 Terra Pro, at 100.00 normalized points per dollar of input price ($1.00 per million tokens, score 100.0).

Median output speed in tokens per second over the last 14 days on the model maker's own API, measured nightly with a fixed ~800-token prompt and ~250-token answer. Models not yet probed fall back to a dated manual figure. Higher is faster.

“Value” is normalized benchmark score (0–100 for this leaderboard cohort) divided by input price per million tokens. Higher means more capability per dollar on this axis only — always sanity-check latency, context length, and your real workload.

  1. 1
    GPT-5.6 Terra Pro
    OpenAI
    100.00
    100.0 / $1.00/M
  2. 2
    GPT-5.6 Luna Pro
    OpenAI
    57.20
    5.7 / $0.10/M
  3. 3
    GPT-6 Luna Pro
    OpenAI
    57.00
    2.9 / $0.05/M
  4. 4
    GPT-6.1 Sol Pro
    OpenAI
    55.26
    55.3 / $1.00/M
  5. 5
    GLM 5
    Zhipu AI (GLM)
    53.20
    53.2 / $1.00/M
  6. 6
    DeepSeek V4.1 Flash
    DeepSeek
    30.00
    0.6 / $0.02/M
  7. 7
    Nemotron 3 Nano 30B A3B
    NVIDIA
    23.83
    1.4 / $0.06/M
  8. 8
    Gemma 3 4B
    Google
    21.25
    0.8 / $0.04/M
  9. 9
    Gemini 2.5 Flash Lite
    Google
    20.00
    1.0 / $0.05/M
  10. 10
    gpt-oss-20b
    OpenAI
    18.33
    0.3 / $0.02/M
  11. 11
    DeepSeek V4 Flash 0731
    DeepSeek
    13.51
    0.6 / $0.04/M
  12. 12
    Gemini 1.5 Flash
    Google
    13.20
    1.0 / $0.08/M
  13. 13
    Qwen3.5-Flash
    Alibaba (Qwen)
    12.31
    0.8 / $0.07/M
  14. 14
    GPT-4.1 Nano
    OpenAI
    11.80
    1.2 / $0.10/M
  15. 15
    Qwen3.7 Flash
    Alibaba (Qwen)
    11.00
    0.3 / $0.03/M
  16. 16
    Nemotron 3.5 Super VL
    NVIDIA
    10.73
    1.6 / $0.15/M
  17. 17
    GPT-6 Astra Pro
    OpenAI
    10.28
    51.4 / $5.00/M
  18. 18
    Gemini 2.0 Flash
    Google
    9.90
    1.0 / $0.10/M
  19. 19
    Seed 1.6 Flash
    ByteDance Seed
    9.33
    0.7 / $0.08/M
  20. 20
    GPT-5.4 Nano
    OpenAI
    9.00
    0.9 / $0.10/M
  21. 21
    Nemotron 3.5 Lightning
    NVIDIA
    8.43
    0.6 / $0.07/M
  22. 22
    Voxtral Small 24B 2507
    Mistral
    8.00
    0.8 / $0.10/M
  23. 23
    Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)
    Google
    7.80
    1.9 / $0.25/M
  24. 24
    Gemini 3.1 Flash Lite
    Google
    6.96
    0.9 / $0.13/M
  25. 25
    GPT-5 nano
    OpenAI
    6.80
    0.2 / $0.03/M
Open full leaderboard

AI Model Analyzer does not recommend specific vendors; rankings are derived from public data only.