Compare model prices
Input, output, cached and batch prices, every route and a month of tokens, side by side.
GPT-5.4 NanoA month of tokens
100M input and 20M output tokens, list price. Use your own numbers.
Side by side
| GPT-5.4 Nano | |
|---|---|
| Input per 1M | $0.2 |
| Output per 1M | $1.25 |
| Cached input | $0.02 |
| Batch in / out | $0.1 / $0.625 |
| Blended (3:1) | $0.463 |
| Context | 400K |
| Routes | 4 |
| Released | Mar 17, 2026 |
| Leadersboard score | n/a |
On the price map
Size: context window, 8K to 2MEqual blended cost (3:1) 243 models, lower left is cheaper
Every route
GPT-5.4 Nano
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| OpenAI flex, cheapest · cached $0.01 | $0.1 | $0.625 | $0.1 / $0.625-50% vs list | $0.01 | -50% vs list |
| OpenAI API The lab's own API · cached $0.02 | $0.2 | $1.25 | $0.2 / $1.25List price | $0.02 | List price |
 Azure AI FoundryDefault region · cached $0.02 | $0.2 | $1.25 | $0.2 / $1.25Same as list | $0.02 | Same as list |
| Azure AI Foundry us · cached $0.022 | $0.22 | $1.38 | $0.22 / $1.38+10% vs list | $0.022 | +10% vs list |
List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.