gpt-oss-120b (free) Check detailed information and pricing for AI models
Context Length 32,768 tokens, openai from provided
32,768
Context Tokens
Free
Prompt Price
Free
Output Price
2/16
Feature Support
Model Overview
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.
Basic Information
Developer
openai
Model Series
GPT
Release Date
2025-08-05
Context Length
32,768 tokens
Variant
free
Pricing Information
This model is free to use
Data Policy
Supported Features
Supported (2)
Seed
Reasoning
Unsupported (14)
Image Input
Top K
Frequency Penalty
Presence Penalty
Repetition Penalty
Response Format
Min P
Logit Bias
Tool Usage
Logprobs
Top Logprobs
Structured Outputs
Web Search Options
Top A