Appndo
All models

Libertai API pricing

Hosted11 language models

As of Oct 14, 2026, Libertai lists 11 language models through its API. Its cheapest language model is Gemma 4 31B IT at $0.15 input / $0.40 output per million tokens.

Language models (11)

Prices per million tokens.

  • DeepSeek V4 Flash

    libertai/deepseek-v4-flash

    Input
    $0.25
    Output
    $1.75
    Context
    200K

  • Gemma 4 31B IT

    libertai/gemma-4-31b-it

    Input
    $0.15
    Output
    $0.40
    Context
    262K

  • Qwen3.5 122B A10B

    libertai/qwen3.5-122b-a10b

    Input
    $0.25
    Output
    $1.75
    Context
    262K

  • Qwen3.6 27B

    libertai/qwen3.6-27b

    Input
    $0.15
    Output
    $0.50
    Context
    262K

  • Qwen3.6 35B A3B

    libertai/qwen3.6-35b-a3b

    Input
    $0.15
    Output
    $0.50
    Context
    262K

  • DeepSeek V4 Flash Thinking

    libertai/deepseek-v4-flash-thinking

    Input
    $0.25
    Output
    $1.75
    Context
    200K

  • Gemma 4 31B IT Thinking

    libertai/gemma-4-31b-it-thinking

    Input
    $0.15
    Output
    $0.40
    Context
    262K

  • Hermes 3 8B Tee

    libertai/hermes-3-8b-tee

    Input
    $0.15
    Output
    $0.60
    Context
    16K

  • Qwen3.5 122B A10B Thinking

    libertai/qwen3.5-122b-a10b-thinking

    Input
    $0.25
    Output
    $1.75
    Context
    262K

  • Qwen3.6 27B Thinking

    libertai/qwen3.6-27b-thinking

    Input
    $0.15
    Output
    $0.50
    Context
    262K

  • Qwen3.6 35B A3B Thinking

    libertai/qwen3.6-35b-a3b-thinking

    Input
    $0.15
    Output
    $0.50
    Context
    262K

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