gpt-oss-120b
gpt-oss-120b is a downloadable text reasoning model with 117 billion total parameters and about 5.1 billion active parameters. It uses Apache 2.0 licensing.
Active parameters are not the model storage size
OpenAI describes the release as fitting on one H100 GPU. It supports three reasoning levels, customization through fine-tuning and tool-oriented output. The documented context is 131,072 tokens. The download route gives the operator responsibility for serving the model.gpt-oss-120b official model documentation
Size the full serving workload
Practical guidance. Review memory use with the chosen precision, context length and number of simultaneous requests. A small active-parameter count does not remove the need to store the other weights. Compare sustained throughput and task quality on the intended hardware.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | gpt-oss-120b |
| Context window | 131,072 tokens Published model context; input and output share this budget gpt-oss-120b official model documentation |
| Input and output | text in; text outgpt-oss-120b official model documentation |
| License | Apache 2.0gpt-oss-120b official model documentation |
Related models
- gpt-oss-20b
OpenAI ยท gpt-oss
A downloadable text reasoning model with 21 billion total parameters and about 3.6 billion active parameters.
Launch date not confirmedDownloadable