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.
With CoreAI, you can start chatting with OpenAI: gpt-oss-20b (free) instantly — no separate subscription needed. CoreAI bundles access to OpenAI: gpt-oss-20b (free) along with 300+ other AI models from OpenAI and other providers like OpenAI, Anthropic, Google, Meta, and more.
Chat with OpenAI: gpt-oss-20b (free) and 300+ other AI models — all in one app.