Favicon for openai

OpenAI: gpt-oss-20b

openai/gpt-oss-20b:free

Model weights

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.

Modalities
Price
Free
Context
131K
Released
Aug 5, 2025
Knowledge cutoff
Jun 2024

Activity

Token volume and request traffic to this model over time.

Not currently available through EU in-region routing. In-region routing docs

Frequently asked questions