All models

Sail API pricing

Hosted12 language models

As of Oct 14, 2026, Sail lists 12 language models through its API. Its cheapest language model is DeepSeek V4 Flash 0731 at $0.09 input / $0.18 output per million tokens.

Language models (12)

Prices per million tokens.

  • DeepSeek V4 Flash 0731

    sail/deepseek-ai/DeepSeek-V4-Flash-0731

    Input
    $0.09
    Output
    $0.18
    Context
    1.05M
  • DeepSeek V4 Pro 0813

    sail/deepseek-ai/DeepSeek-V4-Pro-0813

    Input
    $0.92
    Output
    $2.77
    Context
    1.05M
  • DeepSeek V4.1 Flash

    sail/deepseek-ai/DeepSeek-V4.1-Flash

    Input
    $0.15
    Output
    $0.60
    Context
    1.05M
  • Gemma 4 31B IT

    sail/google/gemma-4-31B-it

    Input
    $0.40
    Output
    $0.60
    Context
    256K
  • GLM 5.3

    sail/zai-org/GLM-5.3

    Input
    $0.98
    Output
    $3.08
    Context
    1.05M
  • GLM 5.3 Flash

    sail/zai-org/GLM-5.3-Flash

    Input
    $0.11
    Output
    $0.35
    Context
    1.05M
  • gpt-oss-120b

    sail/openai/gpt-oss-120b

    Input
    $0.06
    Output
    $0.40
    Context
    131K
  • Kimi K2.6

    sail/moonshotai/Kimi-K2.6

    Input
    $1.00
    Output
    $4.00
    Context
    262K
  • Kimi K3

    sail/moonshotai/Kimi-K3

    Input
    $2.50
    Output
    $12.50
    Context
    1.05M
  • Qwen3.6 35B A3B

    sail/Qwen/Qwen3.6-35B-A3B

    Input
    $0.05
    Output
    $0.40
    Context
    262K
  • Gemma 4 12B IT

    sail/google/gemma-4-12B-it

    Input
    $0.30
    Output
    $2.00
    Context
    16K
  • Gemma 4 31B IT Nvfp4

    sail/nvidia/Gemma-4-31B-IT-NVFP4

    Input
    $0.14
    Output
    $0.40
    Context
    262K

Prices in USD from LiteLLM and models.dev, checked daily; confirm on Sail's pricing page before you rely on a number.