Back to models
gpt-oss-120bMos
T powerful open-weight model, fits into an H100 GPU
| Context window | 131,072 tokens |
| Max output tokens | 131,072 tokens |
Pricing
| Type | Input | Output |
|---|
Parameters
| Parameter | Default | Range |
|---|---|---|
| Max stop sequences | 0 | — |
Supported features
Capabilities
- Streaming
- System Prompt
Endpoints
- Chat Completions
- Batch
Use cases
- text-chat
Model specifications
| Model ID | gpt-oss-120b |
| Family | Other |
| Access type | Open Weights |
| Input modalities | text |
| Output modalities | text |
| Last updated | January 3, 2026 |