Gemini 3.1 Flash Lite Image — Google's fastest image model
Gemini 3.1 Flash Lite Image is the speed and cost pick of Google's image family: 1K images, 14 aspect ratios and a thinking level you control. Keep your generateContent body. About $0.02565 per image, billed by tokens.
- Text to image
- Image editing
- 1K output
- 14 aspect ratios
- Thinking level
- Video and PDF input
Try Gemini 3.1 Flash Lite Image before you write any code
Run Gemini 3.1 Flash Lite Image with the exact JSON your code will send. Every generateContent field the endpoint takes is here.
gemini-3.1-flash-lite-image-official$22.50 / 1M image output tokens
Describe an image, add references if you have them, and submit once. The result appears when the task completes.
What to create or change. Subject, setting, lighting and style.
Images, videos or PDFs the model should read. Files are uploaded and sent as URLs.
Up to 14, sent as fileData URLs.
Default matches your first reference, otherwise 1:1.
Output resolution. 1K is the default.
Image only, or image with a short text reply.
Standing rules for the model, such as a house style.
Blocking threshold for this category.
Greyed-out options relax content filtering. They are available through the API only, not in the playground.
Blocking threshold for this category.
Greyed-out options relax content filtering. They are available through the API only, not in the playground.
Blocking threshold for this category.
Greyed-out options relax content filtering. They are available through the API only, not in the playground.
Blocking threshold for this category.
Greyed-out options relax content filtering. They are available through the API only, not in the playground.
0–2. Leave empty for the model default.
0–1. Leave empty for the model default.
Whole number, 1 or more.
Whole number. Reuse it to reproduce a result more closely.
Caps text and thinking output.
One per line, up to 5.
Only 1: one request returns one image.
How many tokens each reference uses. Lower is cheaper.
Return the model's thought summary with the image.
MINIMAL is fastest; HIGH reasons more before drawing.
Estimated at current rates from the image tokens of the selected size plus a measured sample of text and thinking tokens. Reference inputs add a little on Official.
Try one of these prompts
Sample images generated with Gemini 3.1 Flash Lite Image through this API
Gemini 3.1 Flash Lite Image pricing
Gemini 3.1 Flash Lite Image is billed by the tokens each render reports, at the lowest token rates in the family. Every image is 1K, so the cost per image stays close to one figure.
- Official
- $0.02565/image
- Official
- 779images
Both prices come from the rates that bill your account. Failed requests are not charged.
Official estimates use the image tokens Google publishes for each size, plus a measured sample of 398 text and thinking tokens and 11 prompt tokens.
Gemini 3.1 Flash Lite Image cost by image size
Gemini 3.1 Flash Lite Image renders one size: 1K, which Google counts as 1,120 image tokens. The Official price below adds a measured text and thinking sample.
| Image size | Image tokens | Price · Official |
|---|---|---|
| 1K | 1,120 | $0.02565 |
Every image is 1K, so the image tokens are the same for each render; text and thinking vary a little with the prompt.
Price your own Gemini 3.1 Flash Lite Image request
Pick a size and watch the figure. It is computed from the live rate and the image tokens Google publishes for each size, so it moves when the price does.
A pre-submit estimate. Official bills image output, text and thinking output, and input at their own rates.
| Item | How it is measured | Rate | Billing |
|---|---|---|---|
| Official · Image output | Image tokens reported for the render | $22.50 / 1M$30.00 / 1M | Charged from real usage |
| Official · Text and thinking output | Text and thinking tokens reported for the render | $1.125 / 1M$1.50 / 1M | Charged from real usage |
| Official · Input | Prompt and reference tokens | $0.1875 / 1M$0.25 / 1M | Charged from real usage |
| Failed requests | Any task that ends failed | Free | Nothing is charged |
What is Gemini 3.1 Flash Lite Image?
Gemini 3.1 Flash Lite Image is Google's fastest and cheapest Gemini image model, sold under the name Nano Banana 2 Lite. Google built it for speed and scale, where latency and cost matter most.
On SeedRouter you call Gemini 3.1 Flash Lite Image with Google's own generateContent request body plus a model field. Submit once, keep the task ID, and read a hosted image URL when the task completes.
Model ID: gemini-3.1-flash-lite-image · Token billing ID: gemini-3.1-flash-lite-image-official · Input limit: 65,536 tokens.
Two ways to use Gemini 3.1 Flash Lite Image
Call the API from your backend, or hand the job to a coding agent.
Call the API
Send the Gemini 3.1 Flash Lite Image request from your server, keep the task ID, and read the finished image from the task.
- 1Create an API key
- 2POST the request body
- 3Poll the task until it completes
Let an agent do it
Copy a ready prompt into Claude Code, Codex or Cursor. It asks before spending and downloads the result.
- 1Copy the prompt
- 2Fill in what you want
- 3Approve the request
Why developers pick Gemini 3.1 Flash Lite Image
The Gemini image model for volume and speed, where 1K is enough.
Google's request body
Gemini 3.1 Flash Lite Image takes the same contents and generationConfig you would send to Google. Add a model field and you are done.
Built for latency
Google designed Gemini 3.1 Flash Lite Image for ultra-low latency, so users wait less.
You set the thinking
Choose thinkingLevel MINIMAL for speed or HIGH for a harder prompt.
Lowest token rates
Google's token rates for Gemini 3.1 Flash Lite Image are half those of Gemini 3.1 Flash Image.
14 aspect ratios
Square thumbnails, stories and wide banners at 1K with Gemini 3.1 Flash Lite Image.
Task-based
Submit a Gemini 3.1 Flash Lite Image request, keep the task ID and read the URL when it is done.
What teams build with Gemini 3.1 Flash Lite Image
Thumbnails
Gemini 3.1 Flash Lite Image covers feeds and listings at 1K.
In-chat images
Answer a user with a Gemini 3.1 Flash Lite Image picture while they wait.
Previews
Show a quick Gemini 3.1 Flash Lite Image draft before a larger render.
High volume
Generate large batches where cost per image decides.
Social formats
Square, vertical and wide Gemini 3.1 Flash Lite Image versions from one prompt.
From documents
Turn a PDF or a clip into a quick Gemini 3.1 Flash Lite Image visual.
Start with Gemini 3.1 Flash Lite Image in four steps
- 01
Create a key
Sign in, top up any amount, and create an API key. Credits never expire.
- 02
Send one request
POST the Gemini 3.1 Flash Lite Image body to /v1/images/generations with your prompt and any reference URLs.
- 03
Poll the task
Keep the task ID and check it every few seconds until the status is completed.
- 04
Download the image
Save the hosted image URL from the task output to your own storage.
Gemini 3.1 Flash Lite Image at a glance
The facts that decide whether Gemini 3.1 Flash Lite Image fits the job.
| Feature | Gemini 3.1 Flash Lite Image |
|---|---|
| Model ID | gemini-3.1-flash-lite-image |
| Output size | 1K only |
| Aspect ratios | 14 (1:8 to 8:1) |
| Thinking level | MINIMAL or HIGH |
| Reference types | Image, video, PDF |
| Billing | Per token (Official) |
Need 2K or 4K output? See Gemini 3.1 Flash Image or Gemini 3 Pro Image.
Before you move Gemini 3.1 Flash Lite Image code over
1K only
Gemini 3.1 Flash Lite Image renders 1K. Use Gemini 3.1 Flash Image for 2K or 4K.
Few references work best
Google says Gemini 3.1 Flash Lite Image is not optimized for many references or multi-turn editing.
URLs, not inlineData
Send Gemini 3.1 Flash Lite Image references as fileData URLs. Base64 inlineData is refused before anything is charged.
No Search grounding yet
Gemini 3.1 Flash Lite Image requests with tools are refused for now.
Why run Gemini 3.1 Flash Lite Image on SeedRouter
Pay for what each render uses
Gemini 3.1 Flash Lite Image is billed by the tokens each render reports, at the lowest token rates of the family. Same key and request body as the other models.
Failed requests are free
If a task ends failed, nothing is charged. You only pay for images that are delivered.
Credits never expire
Top up once and use the balance whenever you need it. No subscription.
Hosted results
Finished images come back as URLs on our CDN. Keep a copy of anything you need long term.
One key for every model
The same key and balance work for the other image models in the catalogue.
Other image models on SeedRouter
Same key, same balance, same task API.
Create and edit images with GPT Image 2 on SeedRouter. Use text prompts, reference images and transparent backgrounds, with a live playground and usage-based pricing.
View pricingGenerate and edit images with GPT Image 2.5 Flare or Sunburst on SeedRouter. Six quality steps up to max, transparent backgrounds, a live playground and pay-as-you-go pricing.
View pricingUse Gemini 3.1 Flash Image (gemini-3.1-flash-image) with Google's generateContent body: 512px to 4K, 14 aspect ratios, 14 references. Pay per image.
View pricingUse Gemini 3 Pro Image (gemini-3-pro-image) with Google's generateContent body: 1K to 4K, built-in thinking, 14 references. Pay per image or per token.
View pricingGemini 3.1 Flash Lite Image guides
Practical guides to choosing, pricing and integrating the model.
Use the Nano Banana 2 API step by step: create a key, send a generateContent request, poll the task, add reference images, and let a coding agent run it.
Compare Nano Banana 2, Nano Banana Pro and Nano Banana 2 Lite on image size, aspect ratios, references, thinking and billing, and pick one per job.
Current Nano Banana API pricing for Nano Banana 2, Pro and 2 Lite: flat per-image and token billing, cost by resolution, and when each billing fits.
Gemini 3.1 Flash Lite Image FAQ
Is Gemini 3.1 Flash Lite Image the same as Nano Banana 2 Lite?+
Yes. Nano Banana 2 Lite is Google's product name for Gemini 3.1 Flash Lite Image, and the model ID is gemini-3.1-flash-lite-image. The Nano Banana 2 Lite page covers the same model from a product angle.
How much does Gemini 3.1 Flash Lite Image cost?+
Gemini 3.1 Flash Lite Image is billed by the tokens each render reports; a typical 1K render comes to about $0.02565. The pricing section shows the live rates.
Is Gemini 3.1 Flash Lite Image free?+
Google's pricing page lists no free tier for Gemini 3.1 Flash Lite Image on the Gemini API. On SeedRouter you top up once, credits never expire, and failed requests are not charged.
Can Gemini 3.1 Flash Lite Image make 2K or 4K images?+
No. Gemini 3.1 Flash Lite Image renders 1K only. Use Gemini 3.1 Flash Image with the same request body for 2K or 4K.
What does thinkingLevel do on Gemini 3.1 Flash Lite Image?+
MINIMAL returns fastest. HIGH spends more reasoning on a harder prompt. Thinking tokens are billed on Official only.
Do I need to change my Gemini request?+
Keep contents, systemInstruction, safetySettings and generationConfig as they are. Add a model field, send it to /v1/images/generations, and read the Gemini 3.1 Flash Lite Image result from the task.
How do I get an API key for Gemini 3.1 Flash Lite Image?+
Sign in, top up any amount and create a key on the API keys page. The same key works for Gemini 3.1 Flash Lite Image and every other model here.
Send your first Gemini 3.1 Flash Lite Image request
Try Gemini 3.1 Flash Lite Image in the Playground, then paste the same JSON into your code.