OpenAI: gpt-oss-120b (free)

Description

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...

Availability

Pricing for this model is operator-dependent. Open the chat to route a request — the response includes the resolved per-token cost.

Modalities