Compare models
Put up to 4 models beside each other — token prices, context windows, capabilities and provider, from the same catalogue the model pages read.
- GPT-5 NanoOpenAIRemove
| Attribute | GPT-5 Nanogpt-5-nano-2025-08-07 |
|---|---|
| Pricing | |
| Input | $0.0175 / 1M |
| Output | $0.14 / 1M |
| Cache Write (5m) | $0.0175 / 1M |
| Cache Write (1h) | $0.0175 / 1M |
| Cache Read | $0.0175 / 1M |
| Web Search | $0 / 1M |
| Context | |
| Max context | 400K |
| Max output | N/A |
| Capabilities | |
| Vision | No |
| Function Calling | Yes |
| JSON Mode | Yes |
| Streaming | Yes |
| Catalogue | |
| Provider | OpenAI |
| Category | chat |
| Charge type | Pay As You Go |
| Released | — |
| Description | |
| Summary | GPT-5-Nano is the smallest and fastest GPT-5 variant, built for ultra-low latency and cost-sensitive use cases like developer tools and real-time interactions. While it offers shallower reasoning than larger GPT-5 models, it preserves core instruction-following and safety features and succeeds GPT-4.1-nano as a lightweight option. |