GPT-OSS-20B
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.
File Support: Text, Markdown, Image and PDF files
Context window: 131k tokens
Powered by a server managed by @novitaai. Learn more
Build with GPT-OSS-20B using the Poe API
Start by creating an API key, for use with any bot on Poe:
See the full documentation for comprehensive guidance on getting started.
More from Novita AI
New
Hy3-N
GLM-5.2
DeepSeek-V4-Flash-N
DeepSeek-V4-Pro-N
Kimi-K2.7-Code
Minimax-M3-N
Kimi-K2.6
Gemma-4-26B-A4B
Gemma-4-31B-N
MiniMax-Speech-2.8