gpt-oss-120b
OpenAI馃嚭馃嚫
openai/gpt-oss-120bGPT-OSS-120B is OpenAI's open-weight mixture-of-experts model (around 120B parameters) released under a permissive license for self-hosted deployment. It offers strong reasoning and coding performance for teams that need to run OpenAI-quality models on their own infrastructure.
Cost rate
0.1x
Context
131K
Released
Aug 5, 2025
Input
Text
Output
Text
Support
ReasoningTool callingStructured outputs
Best at
The categories where this model ranks highest.
Mathematical
#172 路 top 45%
Business, Management, & Finance
#199 路 top 50%
Medicine & Healthcare
#201 路 top 54%
Software & IT Services
#204 路 top 51%
Performance
Median latency and throughput measured across recent requests.
Throughput226 tok/s
Latency