OpenAIOfficial

OpenAI: gpt-oss-120b

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...

Pricing

Input

$0.039/1M tokens

Output

$0.18/1M tokens

Capabilities

Context Window131K tokens

SpeedMedium

Release2025-08

Vision

Tool Use

API Access

Local / Open

API Access

Official API

Official Links

Official Website

Compare OpenAI: gpt-oss-120b

See how it stacks up side by side.

Compare Models →