Models
Image models
Image generation is billed per image, listed separately from text and video models. Call POST /v1/images/generations; images come back in the response as base64 (b64_json). Failed requests are not charged.
| Model | Lab | Spec | Price |
|---|---|---|---|
nano-banana-2-lite | 1K class (aspect chosen by the model, e.g. 1408×768, JPEG) | $0.037 / image | |
muse-image | Meta | 1600×1600 (WebP) | $0.011 / image |
nano-banana-2.1 | per image (1K) | $0.0319 / image | |
gpt-image-2.5-flare | OpenAI | low quality · 1024×1024 | $0.0056 / image |
| medium quality · 1024×1024 (default) | $0.0125 / image | ||
| high quality · 1024×1024 | $0.05 / image | ||
| xhigh quality · 1024×1024 | $0.089 / image | ||
| max quality · 1024×1024 | $0.2002 / image | ||
| Prompt text | $4.75 / 1M tokens | ||
gpt-image-2.5-sunburst | OpenAI | low quality · 1024×1024 | $0.0056 / image |
| medium quality · 1024×1024 (default) | $0.0125 / image | ||
| high quality · 1024×1024 | $0.05 / image | ||
| xhigh quality · 1024×1024 | $0.089 / image | ||
| max quality · 1024×1024 | $0.2002 / image | ||
| Prompt text | $4.75 / 1M tokens |
No model matches this filter.
How to read these prices
- Each model is offered at the single size listed in the table; other size parameters are rejected rather than billed at a different rate. Models priced by quality take quality = low, medium, high, xhigh or max; leaving it out or sending auto generates and bills at medium, and prompt text is billed per token. Requests are synchronous only. Prices as published; the console shows the hold and settlement for every request.
Pricing and billing →Business pricing →Estimate monthly cost →
Last updated: 2026-10-03