Service status
For each model: how many of the requests that reached it came back with an image, and how long an image took. The figures are read from real requests when you open the page.
Reading the current figures…
| Model | Last hour | Last 24 hours | Time per image |
|---|---|---|---|
| gpt-image-2 | — | — | — |
| gpt-image-2-adobe | — | — | — |
| gpt-image-2.5 | — | — | — |
| gpt-image-2.5-flare | — | — | — |
| gpt-image-2.5-sunburst | — | — | — |
| gpt-image-2.6 | — | — | — |
| gpt-image-2.6-flare | — | — | — |
| gpt-image-2.6-sunburst | — | — | — |
| nano-banana-2 | — | — | — |
| nano-banana-2.1 | — | — | — |
| nano-banana-pro | — | — | — |
| nano-banana-2-1k | — | — | — |
| nano-banana-2-2k | — | — | — |
| nano-banana-2-4k | — | — | — |
| nano-banana-pro-1k | — | — | — |
| nano-banana-pro-2k | — | — | — |
| nano-banana-pro-4k | — | — | — |
How to read this
- A request counts when it ended with an image or with an error from the model. A request that failed is never charged.
- Not counted: requests still running, requests refused for their content, and requests the caller cancelled.
- Normal means 95% or more succeeded, degraded 80% or more, failing less than that. With fewer than 3 finished requests in a window there is no rate, and the model shows “no recent requests”.
- Time per image is the average over the successful requests of the last 24 hours, from the request to the finished image.
When something is wrong
A failed request can be sent again; with an Idempotency-Key it is never charged twice. If a model stays degraded, write to support@cheapestimagen.com.