OpenAI: gpt-oss-20b logo

OpenAI: gpt-oss-20b

OpenAIllm

Published August 5, 2025

About

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.

Try OpenAI: gpt-oss-20b

Test this model in the Sandbase Playground with your own prompts.

Open in Playground

Related Models