openai/gpt-oss-120b
groq/openai/gpt-oss-120b
Context
131K
Max output
65K
Input / 1M
—
Output / 1M
—
Modality
Chat
Cutoff
Jun 2024
About this model
GPT-oss-120b is the most powerful open-weight model. A 120B-parameter open-weight Mixture-of-Experts model delivering state-of-the-art reasoning, coding, and tool-use performance
Best suited for
- Production, general purpose, high reasoning use cases.
Built-in tools
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_levelControls 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 LimitSpecifies 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_penaltyThe `frequency_penalty` controls how often the model repeats itself, with higher positive values reducing repetition and negative values encouraging it.
novelty_penaltyDiscourages responses that are too similar to previous ones.
stopThis parameter tells the model to stop generating text when it reaches any of the specified sequences (like a word or punctuation)
toolsLists tool definitions or capabilities available to the model.
tool_choiceDecides whether to use tools or just the model for generating responses.
parallel_tool_callsEnables parallel execution of tools, allowing multiple tools to run simultaneously.
response_typeDefines the format or type of the generated response.
streamSends the response in real-time as it's being generated.