Groq logoGroq

    openai/gpt-oss-20b

    groq/openai/gpt-oss-20b

    ChatToolsSystem prompt
    Use this model

    Context

    131K

    Max output

    66K

    Input / 1M

    $0.075

    Output / 1M

    $0.30

    Modality

    Chat

    Cutoff

    Jun 2024

    About this model

    GPT-oss-20b is a 20B-parameter open-weight Mixture-of-Experts model delivering strong reasoning, coding, and tool-use performance at low cost.

    Best suited for

    • Production, general purpose, high reasoning use cases.

    Built-in tools

    Gtwy web search

    Hosted by the gateway — enable them per request without wiring your own endpoint.

    Capabilities

    Tools

    Native function calling, so agents can invoke your endpoints.

    System prompt

    Honours a dedicated system role, separate from the user turn.

    Supported parameters

    creativity_level

    Controls the creativity of responses. Higher values (e.g., 0.7) increase creativity; lower values (e.g., 0.2) make responses more predictable.

    max_tokensMax Tokens Limit

    Specifies the maximum number of text units (tokens) allowed in a response, limiting its length.

    probability_cutoffProbability Cutoff (Top P)

    Focuses on the most likely words based on a percentage of probability.

    repetition_penalty

    The `frequency_penalty` controls how often the model repeats itself, with higher positive values reducing repetition and negative values encouraging it.

    novelty_penalty

    Discourages responses that are too similar to previous ones.

    stop

    This parameter tells the model to stop generating text when it reaches any of the specified sequences (like a word or punctuation)

    tools

    Lists tool definitions or capabilities available to the model.

    tool_choice

    Decides whether to use tools or just the model for generating responses.

    parallel_tool_calls

    Enables parallel execution of tools, allowing multiple tools to run simultaneously.

    response_type

    Defines the format or type of the generated response.

    stream

    Sends the response in real-time as it's being generated.

    Use this model

    OpenAI-SDK compatible, with gateway fallback and routing across providers.

    Other Groq models

    ModelContextMax outputInputOutputCapabilities
    qwen/qwen3.8-27b

    Chat

    131K16K$0.80$4.00Files, Tools, System prompt, Reasoning
    openai/gpt-oss-safeguard-20b

    Chat

    131K66K$0.075$0.30System prompt
    openai/gpt-oss-120b

    Chat

    131K66K$0.15$0.60Tools, System prompt

    Pricing & provider details

    Groq logo

    Groq

    groq/openai/gpt-oss-20b

    Input · per 1M
    $0.075
    Output · per 1M
    $0.30
    Cached input · per 1M
    —
    Context window
    131,072 tokens
    Max output
    65,536 tokens
    Knowledge cutoff
    Jun 2024
    Auto-router
    Not supported

    Start building today

    Route openai/gpt-oss-20b — and every other model in the catalogue — through one endpoint, with failover built in.