AI Model Watch
Models / Google

Gemini 3.1 Flash Image (Nano Banana 2)

Deprecated

Image generation/editing. Two output rates: text and thinking tokens $3.00/1M, image tokens $60.00/1M — price_output_per_mtok holds the image rate (the model's product). Google states the per-image equivalents: $0.045 per 0.5K (512px, 747 tokens), $0.067 per 1K (1024px, 1120 tokens), $0.101 per 2K, $0.151 per 4K (2520 tokens). Batch tier $0.25 in / $1.50 text out / $30.00 image out. Grounding with Google Web and Image Search: 5,000 free requests per month shared across all Gemini 3.x models, then $14 per 1,000 requests. DEPRECATED 2026-10-06: Google's release notes for that date state "The gemini-3.1-flash-image model is deprecated (no shutdown date announced). Migrate to gemini-nano-banana-2.1", and the deprecations table names gemini-nano-banana-2.1 as its replacement with "No shutdown date announced", so retires_on stays null. Until 2026-10-06 Google named this model as the recommended replacement for all three Imagen 4 models; the table now points those at gemini-nano-banana-2.1. No context window or max output published for this model.

Gemini 3.1 Flash Image (Nano Banana 2) by Google costs $0.5 per 1M input tokens and $60 per 1M output tokens ($15.38/1M blended). It is deprecated; the recommended replacement is Gemini Nano Banana 2.1.

Last verified: 24 Oct 2026 · sourced from official provider documentation

Lifecycle warning

This model is deprecated. Recommended migration: Gemini Nano Banana 2.1.

Read the Gemini 3.1 Flash Image (Nano Banana 2) migration guide → replacement & cheapest alternatives

Provider
Google
Status
Deprecated
Input price
$0.5 / 1M tokens
Output price
$60 / 1M tokens
Cached input
—
Blended price
$15.38 / 1M tokens
Context window
—
Max output
—
Modality
text, image, image-out
Open weights
No — API only
Knowledge cutoff
—
Released
28 May 2026
API string
gemini-3.1-flash-image

Source: Google official documentation ↗

See also

Explore more

All Google models→

Prices, context windows and lifecycle status for every Google model we track.

Compare models head-to-head→

Side-by-side price, context and status for the models developers weigh against each other.

FAQ

Gemini 3.1 Flash Image (Nano Banana 2) — questions & answers

How much does Gemini 3.1 Flash Image (Nano Banana 2) cost?

Gemini 3.1 Flash Image (Nano Banana 2) is priced at $0.5 per 1M input tokens and $60 per 1M output tokens ($15.38/1M blended at a 3:1 input-to-output ratio).

Is Gemini 3.1 Flash Image (Nano Banana 2) being deprecated or retired?

Gemini 3.1 Flash Image (Nano Banana 2) is deprecated. The recommended migration is Gemini Nano Banana 2.1.

Does Gemini 3.1 Flash Image (Nano Banana 2) support image or vision input?

Yes — Gemini 3.1 Flash Image (Nano Banana 2) accepts image input. Listed modalities: text, image, image-out.

Can I self-host Gemini 3.1 Flash Image (Nano Banana 2)?

No — Gemini 3.1 Flash Image (Nano Banana 2) is proprietary. Its weights are not publicly released, so it is available only through Google's API (or hosted partners), not for self-hosting.

What is the API model string for Gemini 3.1 Flash Image (Nano Banana 2)?

The API model identifier for Gemini 3.1 Flash Image (Nano Banana 2) is "gemini-3.1-flash-image" when calling Google's API.