Back to models
GPT-5 nano
Fastest, most cost-efficient version of GPT-5
| Context window | 128,000 tokens |
| Max output tokens | 128,000 tokens |
Pricing
| Type | Input | Output |
|---|---|---|
| Standard | $0.05 / 1M tokens | $0.40 / 1M tokens |
| Cached input | $0.01 / 1M tokens | |
Parameters
| Parameter | Default | Range |
|---|---|---|
| Max stop sequences | 0 | — |
Supported features
Capabilities
- Streaming
- Reasoning
- System Prompt
Endpoints
- Chat Completions
- Batch
Use cases
- text-chat
Model specifications
| Model ID | gpt-5-nano |
| Family | Other |
| Access type | Closed |
| Input modalities | text |
| Output modalities | text |
| Last updated | January 3, 2026 |