by Openai
Developed by OpenAI, gpt-oss-20b-free is an open-weight 21B parameter model released under the Apache 2.0 license. This model utilizes a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass. It supports an expansive context window of up to 131,072 tokens, making it well-suited for long-context tasks.
| Context window | 131,072 tokens |
| Modalities | text |
| Features | reasoning, tool_calling, long_context |
| Endpoints | chat_completions |
Paid version: gpt-oss-20b
Use gpt-oss-20b-free via the AIHubMix unified API — one interface for every major LLM.