Openai
OpenAI: gpt-oss-20b (free)
Chamber
Symphonietta
Symphony
REGULAR
Data Collection
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.
Input Price
Free
per million tokens
Output Price
Free
per million tokens
Context Window
131,072
tokens
Capabilities
Input
TEXT
Output
TEXT
Section Leaderboards
See how OpenAI: gpt-oss-20b (free) ranks against all other models across each section
Data Collection Notice
The model provider may use your prompts for model training according to their terms of service. Partitura retains no user prompts - data collection is strictly at the provider level.