Gemini 3.1 Flash Image (Nano Banana 2)
Gemini 3.1 Flash Image (Nano Banana 2) by Google AI: $0.50 per 1M input and $3 per 1M output tokens. Call it with one OpenAI-compatible API key, compare it with similar models, start free.
Gemini 3.1 Flash Image (Nano Banana 2) is served by Google AI and called through odnoga on /v1/images/generations, in the same OpenAI-compatible shape every other model on that endpoint uses. It is a reasoning model, so it spends extra output tokens working through a problem before answering — budget for higher output cost on hard tasks. It accepts images alongside text.
Specification and price
| Vendor | Google AI |
|---|---|
| Model ID | gemini-3.1-flash-image |
| Served on | /v1/images/generations |
| Capabilities | Reasoning, Reads images, Batch |
| Per 1M tokens | Vendor cost | Your price on Free+7% |
|---|---|---|
| Input | $0.5 | $0.538 |
| Output | $3 | $3.23 |
| Cached input | — | — |
Vendor cost is the list price per million tokens as recorded in the odnoga catalog; your price applies your plan margin with the same formula that bills every request — see pricing. Pricing
Call it through odnoga
const res = await fetch("https://api.odnoga.com/v1/images/generations", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.ODNOGA_API_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "gemini-3.1-flash-image",
prompt: "A red bicycle against a white wall",
n: 1,
size: "1024x1024",
}),
});
One endpoint, one key, one bill — /v1/images/generations takes the same shape whichever vendor is behind it. Swap the model id and odnoga handles keys, routing, limits and cost accounting.
What Gemini 3.1 Flash Image (Nano Banana 2) can do
Everything below is what the model itself supports. Ask for something it does not do and odnoga tells you before the request reaches the provider, instead of returning a worse answer.
Works through a problem step by step before answering, which costs more tokens and buys accuracy on hard tasks.
Send a screenshot, a photo or a scan in the same message as your text.
Work that can wait goes through at a lower price.
Beyond text
Produces pictures rather than describing them.
How to use Gemini 3.1 Flash Image (Nano Banana 2)
Derived from the odnoga catalog record for this model.
Best for
- Generating and editing images from a text prompt, billed per image rather than per token.
Not the right pick when
- Simple, high-frequency calls — reasoning spends extra output tokens, so a non-reasoning model in the same catalog is usually cheaper and faster.
- Agent loops that must call your functions — tool calling is not available here.
- Pipelines that require guaranteed JSON — parse defensively or pick a model with enforced JSON.
- Anything where a wrong answer is costly without a human check — no model in the catalog removes that requirement.
Practical tips through odnoga
- 01Pin the model id in a managed prompt version, so a model swap is a version change you can compare and roll back, not an edit in application code.
- 02Compare it against 2–8 other models on the same frozen test cases in the evaluation laboratory before you make it the production default.
- 03For repeated identical deterministic calls, odnoga answer reuse returns the stored answer and bills no vendor tokens — turn it off for creative output.
- 04Budget for output tokens: reasoning happens on the output side, so a short answer can still be an expensive call.
- 05Set a fallback model on the route so a vendor incident degrades quality instead of returning an error, and a per-tenant budget so one caller cannot spend the month.
What a month costs
1,000 calls a month, 10,000 input tokens and 2,000 output tokens each, at your Free price (vendor cost +7%):
| Input (10M tokens) | $5.38 |
|---|---|
| Output (2M tokens) | $6.45 |
| Your cost per month on Free | $11.83 |
Vendor list cost $11.00 + odnoga margin $0.828 (+7%). Cached input or answer reuse lowers it; odnoga records both numbers per request.
If Gemini 3.1 Flash Image (Nano Banana 2) is not the one
Models that take the same kind of input, are priced the same way, and do the closest thing to what this one does. Not a quality ranking — odnoga does not benchmark models.
| Model | Context | Input / 1M | Output / 1M | Capabilities |
|---|---|---|---|---|
| Gemini 3.1 Flash Image (Nano Banana 2) | 66K | $0.5 | $3 | Reasoning, Reads images, Batch |
| Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite) | 66K | $0.25 | $1.50 | Reasoning, Reads images, Batch |
| Gemini 3 Pro Image (Nano Banana Pro) | 131K | $2 | $12 | Reasoning, Reads images, Batch |
| GPT Image 1 mini | — | $2 | $8 | Reads images, Prompt caching, Batch |
Questions
- How much does Gemini 3.1 Flash Image (Nano Banana 2) cost per 1M tokens?
- Google AI lists $0.5 / $3 per 1M input / output tokens in the odnoga catalog. Through odnoga you pay that vendor price plus your plan margin, and every request is recorded with both numbers.
- What is Gemini 3.1 Flash Image (Nano Banana 2) best for?
- Generating and editing images from a text prompt, billed per image rather than per token.
- Can I switch to Gemini 3.1 Flash Image (Nano Banana 2) without changing my code?
- Yes. odnoga exposes one OpenAI-compatible endpoint, so switching means sending "gemini-3.1-flash-image" as the model id — or changing it in the managed prompt version, with no application deploy.
- How large is the Gemini 3.1 Flash Image (Nano Banana 2) context window?
- 66K tokens of input, with up to 66K tokens of output per response.
All models · Pricing · Docs · Compare models in the evaluation lab
Where this model sits
Other Google AI models
Gemini 2.5 Flash Native Audio (Live)
$0.5 / $2 per 1M
Gemini 2.5 Flash TTS
$0.5 / $10 per 1M
Gemini 2.5 Pro TTS
$1 / $20 per 1M
Gemini 3 Flash Preview
$0.5 / $3 per 1M
Gemini 3 Pro Image (Nano Banana Pro)
$2 / $12 per 1M
Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)
$0.25 / $1.50 per 1M
Gemini 3.1 Flash Live
$0.75 / $4.50 per 1M
Gemini 3.1 Flash TTS
$1 / $20 per 1M