← Back to AI Models

GPT-OSS 120B

OpenAI's most powerful open-weight model, fits on H100 GPU

Overview

OpenAI's most powerful open-weight model, fits on H100 GPU It is an open-weight model released under the Apache 2.0 licence.

Key Capabilities

Code Generation — suited for tasks requiring code generation proficiency
Reasoning — suited for tasks requiring reasoning proficiency
Analysis — suited for tasks requiring analysis proficiency
Function Calling — suited for tasks requiring function calling proficiency

Recommended Use Cases

Self Hosted Migration
Private Deployment
Enterprise On Prem

Technical Specifications

Context Window: 128K tokens
Max Output Tokens: 33K tokens
Open Weight: Yes
Licence: Apache 2.0
Release Date: December 01, 2025

Provider

GPT-OSS 120B is developed by OpenAI. For the latest information, visit the official documentation.