Image model for prompt-driven generation, editing, and visual design workflows
Nano Banana 2 by google is offered by 12 providers on this page. Its official list price is $0.50 per 1M input tokens and $60.00 per 1M output tokens.
The context window is 65,536 tokens at the reference host, but hosts report different limits, from 32,768 to 1,048,576, so the usable window depends on the provider you pick. It supports reasoning and structured output. Accepted input modalities are Image, Text, PDF, and Video. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-01.
Select one official tariff and enter the directly billed image count or image-token quantity. Size and quality are selected in the tariff.
| Billed media | Conditions | Official price |
|---|---|---|
| Output images | 512 | $0.045 / image |
| Output images | 1K | $0.067 / image |
| Output images | 2K | $0.10 / image |
| Output images | 4K | $0.15 / image |
Image prices use the vendor's published billing unit. Text or image input tokens may be billed separately where the tariff notes this.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Requesty | Gateway | $0.50 | $2.00 | — | — | 131,072 ⚠ | 32,768 | |
| Kilo Gateway | Gateway | $0.50 | $3.00 | — | — | 131,072 ⚠ | 32,768 | |
| Abacus | Gateway | $0.50 | $3.00 | — | — | 1,048,576 ⚠ | 32,768 | |
| OpenRouter | Gateway | $0.50 | $3.00 | — | — | 131,072 ⚠ | 32,768 | |
| Vercel AI Gateway | Cloud | $0.50 | $3.00 | $0.05 | — | 131,072 ⚠ | 32,768 | |
| AIHubMix | Gateway | $0.50 | $3.00 | — | — | 131,072 ⚠ | 32,768 | |
| Eden AI | Gateway | $0.50 | $3.00 | — | — | 65,536 | 32,768 | |
| Merge Gateway | Gateway | $0.50 | $3.00 | — | — | 32,768 ⚠ | 32,768 | |
| Eden AI | Gateway | $0.50 | $3.00 | — | — | 131,072 ⚠ | 32,768 | |
| GoogleOfficial gemini-3.1-flash-image-preview | First-party | $0.50 | $60.00 | — | — | 65,536 | 65,536 | |
| GoogleOfficial | First-party | $0.50 | $60.00 | — | — | 131,072 ⚠ | 32,768 | |
| VertexOfficial | Cloud | $0.50 | $60.00 | $0.05 | — | 131,072 ⚠ | 32,768 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 1 of 12 providers.
2 / 12 providers expose no reasoning control (reasoning_options: []).
Elo from human preference matchups run by Artificial Analysis. Each arena is anchored separately, so Elo is only comparable within one arena, against the other models on that board, and the 95% confidence interval (shown as ±) indicates how much of a gap is noise. Rank is over the whole arena, including models not listed here.