Appndo
All models

Groq API pricing

Hosted9 language models

As of Oct 14, 2026, Groq lists 9 language models through its API. Its cheapest language model is gpt-oss-20b at $0.075 input / $0.30 output per million tokens.

Language models (9)

Prices per million tokens.

  • gpt-oss-20b

    groq/openai/gpt-oss-20b

    Input
    $0.075
    Output
    $0.30
    Context
    131K

  • gpt-oss-120b

    groq/openai/gpt-oss-120b

    Input
    $0.15
    Output
    $0.60
    Context
    131K

  • gpt-oss-safeguard-20b

    groq/openai/gpt-oss-safeguard-20b

    Input
    $0.075
    Output
    $0.30
    Context
    131K

  • Qwen 3.8 27B

    groq/qwen/qwen3.8-27b

    Input
    $0.80
    Output
    $4.00
    Context
    131K

  • Qwen3.6 27B

    qwen/qwen3.6-27b

    Input
    $0.60
    Output
    $3.00
    Context
    131K

  • Llama 3.1 8B Instant

    llama-3.1-8b-instant

    Input
    $0.05
    Output
    $0.08
    Context
    131K

  • Llama 3.3 70B Versatile

    llama-3.3-70b-versatile

    Input
    $0.59
    Output
    $0.79
    Context
    131K

  • Llama Prompt Guard 2 22M

    groq/meta-llama/llama-prompt-guard-2-22m

    Input
    $0.03
    Output
    $0.03
    Context
    512

  • Llama Prompt Guard 2 86M

    groq/meta-llama/llama-prompt-guard-2-86m

    Input
    $0.04
    Output
    $0.04
    Context
    512

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