gpt-oss-120b

OpenAI · openai/gpt-oss-120b

← Back to leaderboard

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...

open weightstexttext->text

Context

Max context: 131072
Max output:

Pricing

Input / 1M: 0.04
Output / 1M: 0.18
Blend / 1M: 0.11

Quality

Quality index:

Provider

Provider: OpenAI
Moderated: no