imagen-3.0-generate-002 to gemini-2.5-flash-image
Some values not published Checked 2026-10-24.
Price per 1M tokens
| Field | Old | New | Change |
|---|---|---|---|
| Input | Not published | $0.3 | Not published |
| Output | Not published | $2.5 | Not published |
| Cached input | Not published | Not published | Not published |
| Example monthly cost | Not published | $8 | Example only |
Context and max output
| Limit | Old | New | Change |
|---|---|---|---|
| Context window | Not published | 32,768 | Not published |
| Max output | Not published | 32,768 | Not published |
Capabilities that differ
No differing capability values are published for both models.
Endpoint changes
- The Imagen page says Imagen models are shut down and to use Nano Banana. It says to call client.models.generate_content instead of client.models.generate_images, and it names gemini-2.5-flash-image or gemini-3.1-flash-image. It does not show a sample that only swaps the model id. Source
- The image generation guide's text-to-image sample for gemini-nano-banana-2.1 uses client.interactions.create and POST https://generativelanguage.googleapis.com/v1beta/interactions. That method is not the generate_content call named on the Imagen page, so this page does not show a before and after code swap. Source
Checklist
- Read the shutdown date for imagen-3.0-generate-002 on the linked official page.
- Point your requests at gemini-2.5-flash-image.
- Re-check price, context, and parameters on the provider pages linked here.
- Ship the change before the published shutdown date.