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

Other Variants

Actual Usage Statistics

No recent usage data available.

Models by Same Author (openai)

GPT-4o Audio
128,000 tokens
$2.50 / $10.00
GPT-5 Chat
128,000 tokens
$1.25 / $10.00
GPT-5
400,000 tokens
$1.25 / $10.00
GPT-5 Mini
400,000 tokens
$0.25 / $2.00
GPT-5 Nano
400,000 tokens
$0.05 / $0.40