gpt-oss-120b

Available

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...

Context
131.1K tokens
Max output
65.5K tokens
Input / 1M tokens
$0per 1M tokens
Output / 1M tokens
$0per 1M tokens
Listed since
Aug 5, 2025

Prices and model data from OpenRouter

Where it's availableProviders · 2

ProviderInput / 1M tokensOutput / 1M tokensStatus
GroqFreeFreeAvailable
OpenRouter$0.15$0.60Available

Published benchmark results

From independent leaderboards, each credited to its publisher.