OpenAIGPT-4.1 nano
OpenAI's cheapest model, with a 1M-token context window for high-volume, latency-sensitive tasks.
Source: OpenAI models, OpenAI pricing
Pricing
Every billing leg from the live catalog, in USD per 1M tokens.
| Billing leg | Rate | Batch |
|---|---|---|
| Input | $0.1 / M | $0.05 / M |
| Output | $0.4 / M | $0.2 / M |
| Cache read | $0.025 / M | n/a |
Cost calculator
Billing-grade math over the rate card above, including the thinking tokens most estimates miss.
Compare providers
The same model, priced across every platform that serves it. Lowest combined in/out rate is flagged.
| Platform | Input / M | Output / M | Cache read / M | Batch | Access |
|---|---|---|---|---|---|
OpenAILowest | $0.1 | $0.4 | $0.025 | ✓ | First-party API |
Azure OpenAI | $0.1 | $0.4 | $0.025 | ✓ | Direct |
Azure OpenAI · Data zone | $0.11 | $0.44 | $0.028 | ✓ | Direct |
Azure OpenAI · Regional | from$0.11 | $0.44 | $0.028 | — | Direct |
Regional deployments are priced per region; the lowest available region rate is shown.
Price history
Has this model gotten cheaper or more expensive?
| Effective | Input / Output | Status |
|---|---|---|
| April 20, 2026 – July 10, 2026 | $0.1 / $0.4 | past |
| July 10, 2026 | $0.1 / $0.4 | current |
More from OpenAI
Other models from the same provider.
Stop estimating. Track it.
SuperPenguin meters every GPT-4.1 nano call your team makes, prices it with this exact rate card, and shows spend by feature, customer, and team.
Rates are generated from SuperPenguin's live pricing catalog.