Enterprise DNA Enterprise DNA
Directories / Models / Cheapest Context

Cheapest models for context

Ranked by input $/Mtoken, then output. Large context windows for long docs and repos.

  1. 1
    Hy3 (free)

    Tencent · 262,144 context

    Input

    $0/M

    Output

    $0/M

  2. 2
    Qwen3 Coder 480B A35B (free)

    Qwen · 1,048,576 context

    Input

    $0/M

    Output

    $0/M

  3. 3
    Claude Sonnet 5 (Free)

    Anthropic · 1,000,000 context

    Input

    $0/M

    Output

    $0/M

  4. 4
    GLM 5.2 (Free)

    Z Ai · 1,000,000 context

    Input

    $0/M

    Output

    $0/M

  5. 5
    Kimi K2.7 Code (Free)

    Moonshotai · 262,144 context

    Input

    $0/M

    Output

    $0/M

  6. 6
    Nemotron 3 Ultra (free)

    NVIDIA · 1,000,000 context

    Input

    $0/M

    Output

    $0/M

  7. 7
    glm-4.7

    Novita · 205,000 context

    Input

    $0/M

    Output

    $0/M

  8. 8
    kimi-k2-thinking

    Novita · 256,000 context

    Input

    $0/M

    Output

    $0/M

  9. 9
    minimax-m2.1

    Novita · 205,000 context

    Input

    $0/M

    Output

    $0/M

  10. 10
    Step 3.7 Flash (Free)

    Stepfun · 256,000 context

    Input

    $0/M

    Output

    $0/M

  11. 11
    Gemma 4 31B (free)

    Google · 262,144 context

    Input

    $0/M

    Output

    $0/M

  12. 12
    GLM-4.6

    Zhipuai · 202,752 context

    Input

    $0/M

    Output

    $0/M

  13. 13
    Gemma 4 26B A4B (free)

    Google · 262,144 context

    Input

    $0/M

    Output

    $0/M

  14. 14
    Nemotron 3 Super (free)

    NVIDIA · 1,000,000 context

    Input

    $0/M

    Output

    $0/M

  15. 15
    gpt-oss-120b (free)

    OpenAI · 131,072 context

    Input

    $0/M

    Output

    $0/M

  16. 16
    glm-4.7-flash

    Novita · 200,000 context

    Input

    $0/M

    Output

    $0/M

  17. 17
    GLM 4.7 Flash (Free)

    Z Ai · 200,000 context

    Input

    $0/M

    Output

    $0/M

  18. 18
    Cohere Command A

    Cohere · 128,000 context

    Input

    $0/M

    Output

    $0/M

  19. 19
    North Mini Code (free)

    Cohere · 256,000 context

    Input

    $0/M

    Output

    $0/M

  20. 20
    GLM-4.5

    Zhipuai · 131,072 context

    Input

    $0/M

    Output

    $0/M

  21. 21
    Grok 3

    xAI · 128,000 context

    Input

    $0/M

    Output

    $0/M

  22. 22
    Meituan/Longcat-Flash-Lite

    Meituan · 256,000 context

    Input

    $0/M

    Output

    $0/M

  23. 23
    glm-4.6v

    Novita · 131,000 context

    Input

    $0/M

    Output

    $0/M

  24. 24
    gpt-oss-20b (free)

    OpenAI · 131,072 context

    Input

    $0/M

    Output

    $0/M

  25. 25
    Mistral Small 3.1

    Mistral Ai · 128,000 context

    Input

    $0/M

    Output

    $0/M

  26. 26
    Qwen3 30B A3B 2507

    Qwen · 262,144 context

    Input

    $0/M

    Output

    $0/M

  27. 27
    Nemotron 3 Nano 30B A3B (free)

    NVIDIA · 256,000 context

    Input

    $0/M

    Output

    $0/M

  28. 28
    Qwen3 Next 80B A3B Instruct (free)

    Qwen · 262,144 context

    Input

    $0/M

    Output

    $0/M

  29. 29
    Mistral Medium 3 (25.05)

    Mistral Ai · 128,000 context

    Input

    $0/M

    Output

    $0/M

  30. 30
    Llama 3.3 70B Instruct (free)

    Meta · 131,072 context

    Input

    $0/M

    Output

    $0/M

  31. 31
    nvidia-nemotron-nano-9b-v2

    NVIDIA · 131,072 context

    Input

    $0/M

    Output

    $0/M

  32. 32
    Phi-4-mini-instruct

    Microsoft · 128,000 context

    Input

    $0/M

    Output

    $0/M

  33. 33
    Phi-4-Reasoning

    Microsoft · 128,000 context

    Input

    $0/M

    Output

    $0/M

  34. 34
    Phi-4-multimodal-instruct

    Microsoft · 128,000 context

    Input

    $0/M

    Output

    $0/M

  35. 35
    Mistral Large 24.11

    Mistral Ai · 128,000 context

    Input

    $0/M

    Output

    $0/M

  36. 36
    Mistral Large 3 675B Instruct 2512

    Mistral · 262,144 context

    Input

    $0/M

    Output

    $0/M

  37. 37
    Cohere Command R 08-2024

    Cohere · 128,000 context

    Input

    $0/M

    Output

    $0/M

  38. 38
    Cohere Command R+ 08-2024

    Cohere · 128,000 context

    Input

    $0/M

    Output

    $0/M

  39. 39
    Cohere Command R+

    Cohere · 128,000 context

    Input

    $0/M

    Output

    $0/M

  40. 40
    Cohere Command R

    Cohere · 128,000 context

    Input

    $0/M

    Output

    $0/M

Full long context leaderboard → All models