Gemini 2.5 Flash Image (Nano Banana) API

google/gemini-2.5-flash-image
Gemini 2.
Output
$0.0507 / gen
Released
Feb 23, 2026

Overview

What is Gemini 2.5 Flash Image API?

Gemini 2.5 Flash Image is a text-to-image model powered by Gemini 2.5 Flash for fast, high-quality image generation.

Technical Specifications
- Supported inputs: Image, Text
- Output: Image
- Endpoint: /images/generations

Performance Benchmarks
[embed]

Gemini 2.5 Flash Image API Pricing
- Input: $0 / 1M tokens
- Output: $0 / 1M tokens
- Output images: $0 / 1M tokens

Where to Use Gemini 2.5 Flash Image

High-volume image generation
Produce product visuals, thumbnails, and marketing assets programmatically at scale.

Creative and concept art
Turn text prompts into illustrations, mockups, and design explorations.

Image editing and variations
Provide a reference image to guide edits, restyles, or variations.

Code Sample
[embed]

Uptime and performance

  • Uptime (24h): 100%
  • Uptime (7d): 100%
  • Availability (24h): 89.0%
  • Error rate (24h): 11.0%

Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.

Use cases

  • Professional product photography editing
  • AI influencer and UGC content creation
  • Marketing and social media creative workflows
  • Architectural and environmental renderings with layout-aware outpainting
  • Complex multi-step visual content editing (face, object, background)
  • Film, game assets post-production and style transfer
  • Real-time, iterative image refinement in creative applications

How to use Gemini 2.5 Flash Image (Nano Banana) API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to google/gemini-2.5-flash-image.
import requests

r = requests.post(
    "https://api.aimlapi.com/v1/images/generations",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "google/gemini-2.5-flash-image",
      "prompt": "A cat holding a sign that says hello"
    },
)
print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/images/generations", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "google/gemini-2.5-flash-image",
    "prompt": "A cat holding a sign that says hello"
  }),
});
console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/images/generations \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"google/gemini-2.5-flash-image","prompt":"A cat holding a sign that says hello"}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Gemini 2.5 Flash Image (Nano Banana) API Pricing

TypePrice
Input
$0.702 / 1M tokens
Output
$0.0507 / gen
Cached input
$0.0742716 / 1M tokens

Gemini 2.5 Flash Image (Nano Banana) vs other models

ModelInputOutputContextBest for
$0.702 / 1M tokens
$0.0507 / gen
Image generation at scale
$0.325 / 1M tokens
$78 / 1M tokens
128K tokens
Image generation at scale
$6.5 / 1M tokens
$39 / 1M tokens
Image generation at scale
$0.325 / gen
Image generation at scale
$0.0195 / MP (variable)
Image generation at scale

Frequently asked questions

Gemini 2.5 Flash Image (Nano Banana) takes image, text as input and returns image.

Gemini 2.5 Flash Image (Nano Banana) became available on February 23, 2026.

Gemini 2.5 Flash Image (Nano Banana) is priced at $5.85 / 1M tokens.

Gemini 2.5 Flash Image (Nano Banana) is billed per generation — a fixed charge per output rather than by prompt length.

Yes, Gemini 2.5 Flash Image (Nano Banana) accepts image input as well as a text prompt.

Gemini 2.5 Flash Image (Nano Banana) was built by Google.

Send a request to https://api.aimlapi.com/v1/images/generations with google/gemini-2.5-flash-image as the model id.

Yes. Gemini 2.5 Flash Image (Nano Banana) is served through AI/ML API, so the same key and endpoint format used for other models applies.

Start building with Gemini 2.5 Flash Image (Nano Banana)

Get API Key
1000+ models, one API.