---
title: "Nano Banana Pro"
description: "Nano Banana Pro makes photoreal still images from text and from references. It is the best roasOS image model for identity, product placement and rendered typography."
url: https://docs.roasos.com/models/image/nano-banana-pro
---
# Nano Banana Pro
Family
`image`
· model
`nano-banana-pro`
· catalog
`model-catalog@2026-10-06.v5`
· pricing
`customer-pricing@2026-11-05.v15`
.
## Endpoint
```http
POST https://api.roasos.com/v1/image/nano-banana-pro
```
Send your API key as a bearer token. The key needs the scope `api:write`. Every paid request also needs an `Idempotency-Key` header.
The envelope fields `quote_only`, `quote_id`, `webhook_url` and `wait_timeout_seconds` behave the same on each model endpoint. Refer to [Jobs](/concepts/jobs) and [Quotes and credits](/concepts/quotes-and-credits).
## Good at
Nano Banana Pro is Google's state-of-the-art image generation and editing model (fal tags: realism, typography). Use it for the final hero image, for a person who must look the same across images, and for a product that must keep its exact label and shape. It holds up to 14 reference images and it follows a long scene description with camera, light and material named. It renders 4K when fine detail matters. It is the only image model that the scene and avatar endpoints use. It does not do masked inpaint; use /v1/image-edit/gpt-image-2.5 for that.
## Pricing
The unit is one **image**. Pricing key: `nano-banana-pro`.
| Request | Credits |
| ------------- | ------- |
| `1_image_2K` | 2 |
| `1_image_1K` | 2 |
| `1_image_4K` | 4 |
| `4_images_4K` | 15 |
The credits come from the roasOS pricing table. No other field changes the price. To get the exact price of your request, send it with `quote_only: true` first.
## Modes
* `text-to-image`
* `edit`
roasOS selects the mode from the media fields of your request. You do not send a mode.
Provider endpoints: `fal-ai/nano-banana-pro` · `fal-ai/nano-banana-pro/edit`.
## Request fields
| Field | Type | Required | Default | Rule |
| ---------------------- | --------- | -------- | ------- | ------------------------------------------------------------------------------- |
| `ad_look` | enum | no | — | `designed`, `native`, `ui` |
| `ad_set` | object | no | — | `{ id, index, total }` |
| `alter` | object | no | — | `{ mode, who, new_person, clothes, outfit, object, product, keep, multi_shot }` |
| `aspect_ratio` | enum | no | `1:1` | `auto`, `21:9`, `16:9`, `3:2`, `4:3`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16` |
| `avatar_id` | string | no | — | UUID |
| `avatar_outfit` | string | no | — | ≤ 500 characters |
| `num_images` | integer | no | `1` | 1–4 |
| `product_id` | string | no | — | UUID |
| `product_images` | string\[] | no | — | ≤ 14 items; only in `edit` |
| `prompt` | string | no | — | ≥ 1 character; ≤ 8,000 characters |
| `prompt_mode` | enum | no | — | `wrapped`, `exact` |
| `quote_id` | string | no | — | UUID |
| `quote_only` | boolean | no | `false` | — |
| `references` | string\[] | no | — | ≤ 14 items; only in `edit` |
| `resolution` | enum | no | `2K` | `1K`, `2K`, `4K` |
| `seed` | integer | no | — | -2147483648–2147483647 |
| `source_image` | string | no | — | https URL; ≤ 4,096 characters |
| `wait_timeout_seconds` | integer | no | `0` | 0–60 |
| `webhook_url` | string | no | — | https URL; ≤ 4,096 characters |
The schema is strict. A field that is not in this table gets `400 unsupported_option`. The field names are the roasOS role names. One role has one name in every family.
## Media
This endpoint accepts these media roles:
* `avatar_id` — identity; the saved character reference sheet, with a derived portrait only where the model requires a single face or source frame
* `product_id` — product; resolves to the product image list
* `product_images` — product reference images
* `references` — style and appearance references
| Role | Items | Maximum size | Content types | Duration |
| ---------------- | ----- | ------------ | --------------------------------------- | -------- |
| `product_images` | ≤ 14 | 10 MB | `image/jpeg`, `image/png`, `image/webp` | — |
| `references` | ≤ 14 | 10 MB | `image/jpeg`, `image/png`, `image/webp` | — |
Every other role is refused: `elements`, `reference_images`, `image_url`, `end_image_url`, `scene_id`, `scene_image`, `video_urls`, `video_url`, `audio_urls`, `audio_url`, `voice_id`. A refused role gets `400 unsupported_option`.
Each media URL must be an immutable object on
`https://cdn.roasos.com`
that your workspace owns. Any other URL gets
`400 reference_media_not_workspace_owned`
. Refer to
[Reference media and uploads](/concepts/reference-media)
to learn how to put a file there.
## Prompt
Limit: 8,000 characters for the caller. The worker wrapper counts toward the 10,000-character engine cap. No tag syntax; the worker orders the references and names the roles.
* Write one scene: subject, action, setting, light, camera, material.
* Put identity and product rules in the media roles, not in the prompt text. The wrapper tells the model which image is the person, which is the product, and which is style only.
* Say what the person does and where the product is; do not describe the person's face.
* Give the exact text to render inside quotation marks.
* State the framing (close-up, half body, full body) and the aspect ratio in words when it matters.
* On a bad result, write a new prompt that names the fix; do not resend the same payload.
## Not exposed
These catalog entries describe omitted inputs, pinned values and source constraints. They do not imply that the provider accepts every listed field.
* `output_format` — pinned to `png`.
* `safety_tolerance` — pinned to `4`.
* `enable_web_search` — pinned to `false`.
* `limit_generations` — pinned to `true`.
* `system_prompt` — not accepted by this public endpoint.
* `sync_mode` — not accepted by this public endpoint.
## Result
The result kind is `image`. Always present: nothing. Present when the run makes it: `avatar_id`, `full_body_url`, `images`, `portrait_url`, `provider_seed`, `reference_sheet`, `url`.
```json
{
"data": {
"id": "gen_…",
"kind": "image",
"model": "nano-banana-pro",
"status": "completed",
"result": {
"avatar_id": "00000000-0000-4000-8000-000000000000",
"full_body_url": "https://cdn.roasos.com/workspaces/ws_01/full_body_url",
"images": [
"https://cdn.roasos.com/workspaces/ws_01/images-1.png"
],
"portrait_url": "https://cdn.roasos.com/workspaces/ws_01/portrait_url",
"provider_seed": 0,
"reference_sheet": "https://cdn.roasos.com/workspaces/ws_01/reference_sheet",
"url": "https://cdn.roasos.com/workspaces/ws_01/result"
}
}
}
```
The files are immutable objects on `https://cdn.roasos.com`. A result URL is a valid media input for your next request.
## Example
The three steps are always the same: quote, run, poll.
cURL
JavaScript
Python
```bash
# 1. Quote. Nothing is spent.
curl -X POST https://api.roasos.com/v1/image/nano-banana-pro \
-H "Authorization: Bearer roasos_sk_live_..." \
-H "Idempotency-Key: 0f1c9e2a-nano-banana-pro-0001" \
-H "Content-Type: application/json" \
-d '{"quote_only":true,"prompt":"A woman holds the bottle at eye level in a bright kitchen, morning light, static camera."}'
# 200 { "data": { "kind": "quote", "quote_id": "q_7Hk...", "credits": 2, "expires_at": "...",
# "confirmation": { "model": "nano-banana-pro", "example": "1_image_2K" } } }
# 2. Run. Same body, same Idempotency-Key, quote_id in place of quote_only.
curl -X POST https://api.roasos.com/v1/image/nano-banana-pro \
-H "Authorization: Bearer roasos_sk_live_..." \
-H "Idempotency-Key: 0f1c9e2a-nano-banana-pro-0001" \
-H "Content-Type: application/json" \
-d '{"quote_id":"q_7Hk...","prompt":"A woman holds the bottle at eye level in a bright kitchen, morning light, static camera."}'
# 201 { "data": { "id": "gen_...", "status": "queued", "credits_reserved": 2 } }
# 3. Poll, then read the result.
curl https://api.roasos.com/v1/jobs/gen_.../status -H "Authorization: Bearer roasos_sk_live_..."
curl https://api.roasos.com/v1/jobs/gen_.../result -H "Authorization: Bearer roasos_sk_live_..."
```
```javascript
const key = process.env.ROASOS_API_KEY;
const url = "https://api.roasos.com/v1/image/nano-banana-pro";
const idempotencyKey = "0f1c9e2a-nano-banana-pro-0001";
const input = {
"prompt": "A woman holds the bottle at eye level in a bright kitchen, morning light, static camera."
};
const post = (payload) =>
fetch(url, {
method: "POST",
headers: {
Authorization: `Bearer ${key}`,
"Idempotency-Key": idempotencyKey,
"Content-Type": "application/json",
},
body: JSON.stringify(payload),
}).then((response) => response.json());
// 1. Quote. Nothing is spent.
const quote = await post({ quote_only: true, ...input });
console.log(quote.data.credits);
// 2. Run.
const job = await post({ quote_id: quote.data.quote_id, ...input });
// 3. Poll, then read the result.
let status = "queued";
while (status !== "completed" && status !== "failed" && status !== "canceled") {
await new Promise((done) => setTimeout(done, 3000));
const poll = await fetch(`${url.split("/v1")[0]}/v1/jobs/${job.data.id}/status`, {
headers: { Authorization: `Bearer ${key}` },
}).then((response) => response.json());
status = poll.data.status;
}
const result = await fetch(`${url.split("/v1")[0]}/v1/jobs/${job.data.id}/result`, {
headers: { Authorization: `Bearer ${key}` },
}).then((response) => response.json());
console.log(result.data.result);
```
```python
import os, time, requests
key = os.environ["ROASOS_API_KEY"]
url = "https://api.roasos.com/v1/image/nano-banana-pro"
headers = {
"Authorization": f"Bearer {key}",
"Idempotency-Key": "0f1c9e2a-nano-banana-pro-0001",
}
payload = {
"prompt": "A woman holds the bottle at eye level in a bright kitchen, morning light, static camera."
}
# 1. Quote. Nothing is spent.
quote = requests.post(url, headers=headers, json={"quote_only": True, **payload}).json()
print(quote["data"]["credits"])
# 2. Run.
job = requests.post(url, headers=headers, json={"quote_id": quote["data"]["quote_id"], **payload}).json()
job_id = job["data"]["id"]
# 3. Poll, then read the result.
jobs = "https://api.roasos.com/v1/jobs"
status = "queued"
while status not in ("completed", "failed", "canceled"):
time.sleep(3)
status = requests.get(f"{jobs}/{job_id}/status", headers=headers).json()["data"]["status"]
result = requests.get(f"{jobs}/{job_id}/result", headers=headers).json()
print(result["data"]["result"])
```
## The deprecated path
`POST /v1/generations` still reaches this model for one minor version. It is deprecated. This is how it maps:
POST /v1/generations `{ "type": "image", "model": "nano-banana-pro", "prompt": "…", "options": { "aspect_ratio", "resolution", "num_outputs", "reference_images" (≤ 9), "seed" } }`. Today's public API has no `avatar_id`, `product_images` or `product_id` role, and it sends the prompt raw (no placement wrapper). `aspect_ratio` on today's path is `1:1, 16:9, 9:16, 4:3, 3:4, 21:9` (no `auto`, `4:5`, `5:4`, `3:2`, `2:3`).
## See also
* [`llms.txt` for this model](https://docs.roasos.com/models/image/nano-banana-pro/llms.txt) — the same facts as one plain-text file for an agent.
* `GET https://api.roasos.com/v1/catalog/nano-banana-pro` — the machine-readable form: enums, defaults, limits and prices. Refer to the [API reference](/api-reference/overview).
* [Jobs](/concepts/jobs) — how to poll a job and read its result.
* Provider endpoints: `fal-ai/nano-banana-pro` · `fal-ai/nano-banana-pro/edit`.