# GPT Image 2
Source: https://docs.imini.ai/en/api-reference/images/gpt-image-2
en/openapi/images/gpt-image-2.yaml POST /v1/images/generate
OpenAI gpt-image-2 image generation model. 1K / 2K / 4K resolutions with three quality tiers, up to 6 reference images.
# Nano Banana
Source: https://docs.imini.ai/en/api-reference/images/nano-banana
en/openapi/images/nano-banana.yaml POST /v1/images/generate
Google Gemini 2.5 Flash image generation model. Fast and low-cost, supporting both text-to-image and image-to-image.
# Nano Banana 2
Source: https://docs.imini.ai/en/api-reference/images/nano-banana-2
en/openapi/images/nano-banana-2.yaml POST /v1/images/generate
Google Gemini 3.1 Flash Image — the most fully featured Flash model, with 14 aspect ratios and 512p to 4K resolutions.
# Nano Banana Pro
Source: https://docs.imini.ai/en/api-reference/images/nano-banana-pro
en/openapi/images/nano-banana-pro.yaml POST /v1/images/generate
Google Gemini 3 Pro image generation model. Up to 4K output and up to 14 reference images.
# Get Task
Source: https://docs.imini.ai/en/api-reference/images/task-query
en/openapi/images/task-query.yaml GET /v1/images/tasks/{task_id}
Query the status and result of an asynchronous image generation task.
# HappyHorse 1.0
Source: https://docs.imini.ai/en/api-reference/videos/happyhorse-1-0
en/openapi/videos/happyhorse-1-0.yaml POST /v1/videos/generate
HappyHorse 1.0 video generation model. Supports text-to-video, image-to-video (first frame), reference-to-video (multi-image), and video editing (video + reference images).
# Kling v3
Source: https://docs.imini.ai/en/api-reference/videos/kling-v3
en/openapi/videos/kling-v3.yaml POST /v1/videos/generate
Kling 3.0 video generation model. Supports text-to-video, image-to-video, first/last-frame interpolation, and multi-reference image-to-video.
# Kling v3 Motion Control
Source: https://docs.imini.ai/en/api-reference/videos/kling-v3-motion-control
en/openapi/videos/kling-v3-motion-control.yaml POST /v1/videos/generate
Kling 3.0 motion control — use a character from a reference image and replicate motion from a reference video
# Kling v3 Omni
Source: https://docs.imini.ai/en/api-reference/videos/kling-v3-omni
en/openapi/videos/kling-v3-omni.yaml POST /v1/videos/generate
Kling 3.0-Omni supports asset video references and edit_source video editing, both with up to 4 accompanying asset images.
# Seedance 2.0
Source: https://docs.imini.ai/en/api-reference/videos/seedance-2-0
en/openapi/videos/seedance-2-0.yaml POST /v1/videos/generate
Seedance 2.0 video generation model (with or without audio). Supports text-to-video, image-to-video (first frame / first and last frame), and multimodal reference-to-video (image + video + audio).
For editing, mark exactly one video as `reference_type=edit_source`; auxiliary videos, images and audios use `asset`. All input videos together allow up to 3 clips, 2–15 seconds each and at most 15 seconds in total. Identify the target in the prompt using its position in the video array.
Editing supports an explicit `duration` of 4–15 seconds and an `aspect_ratio`; neither must match the source. imini does not expose smart duration `-1`. Existing credit rules remain unchanged.
# Seedance 2.0 Fast
Source: https://docs.imini.ai/en/api-reference/videos/seedance-2-0-fast
en/openapi/videos/seedance-2-0-fast.yaml POST /v1/videos/generate
Seedance 2.0 Fast video generation model (with or without audio). A lightweight, faster variant of Seedance 2.0 with identical capabilities and parameters.
For editing, mark exactly one video as `reference_type=edit_source`; auxiliary videos, images and audios use `asset`. All input videos together allow up to 3 clips, 2–15 seconds each and at most 15 seconds in total. Identify the target in the prompt using its position in the video array.
Editing supports an explicit `duration` of 4–15 seconds and an `aspect_ratio`; neither must match the source. imini does not expose smart duration `-1`. Existing credit rules remain unchanged.
# Get Task
Source: https://docs.imini.ai/en/api-reference/videos/task-query
en/openapi/videos/task-query.yaml GET /v1/videos/tasks/{task_id}
Query the status and result of an asynchronous video generation task.
# Wan 3.0 Video
Source: https://docs.imini.ai/en/api-reference/videos/wan3-0-video
en/openapi/videos/wan3-0-video.yaml POST /v1/videos/generate
Wan 3.0 standard: text-to-video, first/last frames and multimodal references.
# Changelog
Source: https://docs.imini.ai/en/changelog/index
### Wan 3.0 Video Standard
Added `wan3.0-video` for text, first/last frames and multimodal references. Defaults to 720P and 5 seconds, with output duration of 2-30 seconds.
480P / 720P / 1080P cost 80 / 160 / 280 credits per requested output second. Reference video and audio generation add no surcharge.
Independent video editing and audio-only references are not available in this release. See [Wan 3.0 Video](/en/api-reference/videos/wan3-0-video).
### Unified Video Material Fields
Image, video and audio inputs in video-generation requests now use `reference_type`, defaulting to `asset`.
Editing requires an explicit `reference_type: edit_source`. Frame roles remain `first_frame` and `last_frame`.
The old `refer_type` field no longer selects the material's purpose. Omitted, null, empty or unknown types are treated as `asset`.
Update your requests, especially those relying on the old `base` default to trigger editing.
`keep_original_sound` remains a per-video property. Consult each model's API page for supported inputs and combinations.
Credit unit prices are unchanged.
### New video model: HappyHorse 1.0
Released `dashscope/happyhorse-1.0` — a single model ID that covers text-to-video, image-to-video (first frame), reference-to-video (multi-image), and video editing (video + reference images), auto-dispatched by input shape.
* Supports 720P / 1080P output, duration 3s–15s (video-edit mode follows the source video length, capped at 15s);
* In reference-to-video mode, refer to the N-th image with `character1`, `character2`, … in the prompt;
* Video-edit mode exposes `extra_params.audio_setting` (`auto` / `origin`) for audio handling;
* Pricing: 720P `180 credits/second`, 1080P `300 credits/second`.
For full parameter details, see [HappyHorse 1.0](/en/api-reference/videos/happyhorse-1-0). For credit consumption, see [Pricing](/en/guide/pricing#dashscope-happyhorse-1-0).
### New video model: Kling v3 Motion Control
Released `kling/kling-v3-motion-control` — use the character from a reference image as the subject and replicate the motion from a reference video.
* Requires both 1 character reference image and 1 motion reference video;
* Supports 720P / 1080P output; the output duration equals the reference video duration;
* Reference video duration: 3s–30s (depending on `extra_params.character_orientation`: `video` allows up to 30s, `image` up to 10s);
* Pricing: 720P `180 credits/second`, 1080P `220 credits/second`.
For full parameter details, see [Kling v3 Motion Control](/en/api-reference/videos/kling-v3-motion-control). For credit consumption, see [Pricing](/en/guide/pricing#kling-kling-v3-motion-control).
### First batch of Open Platform models now live
imini Open Platform is officially live, with the first wave of image and video generation models available.
#### Image models
* `google/nano-banana`: Based on Gemini 2.5 Flash Image. Fast and low-cost, supports up to 3 reference images.
* `google/nano-banana-pro`: Based on Gemini 3 Pro Image. Supports up to 14 reference images, output up to 4K.
* `google/nano-banana-2`: Based on Gemini 3.1 Flash Image. Supports up to 14 reference images, with 512 / 1K / 2K / 4K output.
#### Video models
* `kling/kling-v3`: Kling 3.0 video generation. Supports 720P / 1080P with optional audio.
* `kling/kling-v3-omni`: Kling 3.0 full-modality variant. Supports reference video input.
* `doubao/seedance-2.0`: Doubao Seedance 2.0. Supports text-to-video, image-to-video, and multimodal references (image + video + audio).
* `doubao/seedance-2.0-fast`: Seedance 2.0 Fast — the same capabilities at a lower cost.
For detailed parameter documentation, see the [API Reference](/en/api-reference/images/nano-banana). For credit consumption, see [Pricing](/en/guide/pricing).
# Quickstart
Source: https://docs.imini.ai/en/guide/getting-started
Learn how to onboard to imini Open Platform and make your first API call.
This guide walks you through the full flow from setting up your account to making your first API call. It takes about 5 minutes.
## Prerequisites
Before you start, please confirm the following:
Visit [imini.ai](https://imini.ai) to register and verify your email.
All API calls are billed in credits. See [Pricing](/en/guide/pricing) for each model's consumption rules. Please top up at [Credits](https://imini.ai/credits) before making any calls.
Go to the [**API Keys management page**](https://imini.ai/api-keys), create an API Key for server-side use, and store it securely.
## Base URL
All imini Open Platform endpoints share the same base URL:
```
https://openapi.imini.ai/imini/router
```
The relative paths in the examples below (such as `/v1/images/generate`) should be appended to this base URL.
## Authentication
Every request authenticates via an HTTP header using the Bearer Token standard:
```http theme={null}
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
```
**API Key security**: Only use your API Key on the server side. Never commit it to a code repository, ship it in frontend code or mobile apps, or expose it in any other way. If you suspect a key has leaked, rotate it immediately on the [API Keys management page](https://imini.ai/api-keys).
## Asynchronous Task Model
All generation endpoints on imini (image and video) use an asynchronous task model. A complete generation flow is two steps:
```
┌──────────────────────────────────────────┐
│ 1. Submit the generation task │
│ POST /v1/images/generate │
│ → synchronously returns { task_id } │
└────────────────┬─────────────────────────┘
│
▼
┌──────────────────────────────────────────┐
│ 2. Poll the task status │
│ GET /v1/images/tasks/{task_id} │
│ → status: queued → processing │
│ → succeeded (with images[].url) │
│ → failed (with error object) │
└──────────────────────────────────────────┘
```
The image task query endpoint is `/v1/images/tasks/{task_id}`; the video task query endpoint is `/v1/videos/tasks/{task_id}`. A polling interval of **2 seconds** is recommended. Image tasks typically complete within **10–30 seconds**.
## Step 1: Submit the Generation Task
The example below uses the `google/nano-banana` model to generate a 1:1 image:
```bash cURL theme={null}
curl -X POST https://openapi.imini.ai/imini/router/v1/images/generate \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/nano-banana",
"prompt": "An orange cat napping under a cherry blossom tree, watercolor style",
"aspect_ratio": "1:1"
}'
```
```python Python theme={null}
import requests
BASE_URL = "https://openapi.imini.ai/imini/router"
API_KEY = "YOUR_API_KEY"
response = requests.post(
f"{BASE_URL}/v1/images/generate",
headers={
"Authorization": f"Bearer {API_KEY}",
"Content-Type": "application/json",
},
json={
"model": "google/nano-banana",
"prompt": "An orange cat napping under a cherry blossom tree, watercolor style",
"aspect_ratio": "1:1",
},
timeout=30,
)
response.raise_for_status()
task_id = response.json()["task_id"]
print(f"Submitted task: {task_id}")
```
```javascript Node.js theme={null}
const BASE_URL = 'https://openapi.imini.ai/imini/router';
const API_KEY = 'YOUR_API_KEY';
const response = await fetch(`${BASE_URL}/v1/images/generate`, {
method: 'POST',
headers: {
Authorization: `Bearer ${API_KEY}`,
'Content-Type': 'application/json',
},
body: JSON.stringify({
model: 'google/nano-banana',
prompt: 'An orange cat napping under a cherry blossom tree, watercolor style',
aspect_ratio: '1:1',
}),
});
if (!response.ok) {
throw new Error(`Submit failed: ${response.status}`);
}
const { task_id } = await response.json();
console.log(`Submitted task: ${task_id}`);
```
**Successful response** (HTTP 200):
```json theme={null}
{
"task_id": "task_2041350318103396352",
"model": "google/nano-banana",
"created_at": "2026-04-07T03:00:17.062Z",
"request_id": "285f20ce-8158-401b-945c-7bc6a7ef6ead"
}
```
## Step 2: Poll the Task Result
Use the `task_id` returned above to poll until `status` becomes `succeeded` or `failed`:
```bash cURL theme={null}
curl https://openapi.imini.ai/imini/router/v1/images/tasks/TASK_ID \
-H "Authorization: Bearer YOUR_API_KEY"
```
```python Python theme={null}
import time
def wait_for_result(task_id: str, interval: int = 2, timeout: int = 120):
"""Poll the task result, waiting up to `timeout` seconds."""
deadline = time.time() + timeout
while time.time() < deadline:
result = requests.get(
f"{BASE_URL}/v1/images/tasks/{task_id}",
headers={"Authorization": f"Bearer {API_KEY}"},
timeout=10,
).json()
status = result["status"]
if status == "succeeded":
return result["images"]
if status == "failed":
raise RuntimeError(f"Task failed: {result['error']}")
time.sleep(interval)
raise TimeoutError(f"Task {task_id} timed out after {timeout}s")
images = wait_for_result(task_id)
print(images[0]["url"])
```
```javascript Node.js theme={null}
async function waitForResult(taskId, { intervalMs = 2000, timeoutMs = 120_000 } = {}) {
const deadline = Date.now() + timeoutMs;
while (Date.now() < deadline) {
const res = await fetch(`${BASE_URL}/v1/images/tasks/${taskId}`, {
headers: { Authorization: `Bearer ${API_KEY}` },
});
const data = await res.json();
if (data.status === 'succeeded') return data.images;
if (data.status === 'failed') throw new Error(`Task failed: ${JSON.stringify(data.error)}`);
await new Promise(r => setTimeout(r, intervalMs));
}
throw new Error(`Task ${taskId} timed out`);
}
const images = await waitForResult(task_id);
console.log(images[0].url);
```
**Task status values**:
| Status | Meaning |
| ------------ | ------------------------------------------------------- |
| `queued` | Task submitted, waiting to enter the processing queue |
| `processing` | Model is generating |
| `succeeded` | Generation succeeded, result is in the `images[]` field |
| `failed` | Generation failed, details in the `error` object |
**Successful response example** (`status: succeeded`):
```json theme={null}
{
"task_id": "task_2041350318103396352",
"status": "succeeded",
"model": "google/nano-banana",
"created_at": "2026-04-07T03:00:17.062Z",
"completed_at": "2026-04-07T03:00:29.418Z",
"images": [
{
"url": "https://file.iminicdn.com/file/2026/04/07/xxxx.png",
"width": 1024,
"height": 1024
}
],
"error": null,
"request_id": "285f20ce-8158-401b-945c-7bc6a7ef6ead"
}
```
## Error Handling
All error responses share a unified structure:
```json theme={null}
{
"error": {
"code": "INVALID_PARAMETER",
"message": "aspect_ratio must be one of: 1:1, 2:3, ...",
"status": 400,
"request_id": "req_abc123"
}
}
```
**Common HTTP status codes**:
| Status | Meaning | Typical cause |
| ------ | -------------------------- | ------------------------------------------------------------------------------- |
| `400` | Invalid request parameters | Missing required field, invalid enum value, or prompt flagged by content safety |
| `401` | Authentication failed | API Key missing, invalid, or revoked |
| `402` | Insufficient credits | Account balance cannot cover this call |
| `404` | Resource not found | The specified `task_id` does not exist or has expired |
| `429` | Rate limit exceeded | Exceeded your account's rate quota; back off and retry |
| `500` | Internal platform error | Platform-side issue; please retry later |
| `502` | Upstream model error | Underlying model service unavailable; usually safe to retry immediately |
Every response includes a `request_id`. Please include it when submitting tickets or contacting support so we can investigate quickly.
## Production Integration Tips
Before integrating imini into production, review the following practices:
* **Set reasonable polling intervals**: We recommend a first poll at 2 seconds, then exponential backoff (2s / 3s / 5s) to reduce pressure on the query endpoint.
* **Configure sensible timeouts**: Use a 30-second timeout for submission calls. Set overall polling timeouts based on the model (e.g., 2 minutes for image, 10 minutes for video).
* **Error retry strategy**: For `429`, `500`, and `502`, retry 2–3 times with random jitter. Do not retry `400`, `401`, or `402`.
* **API Key rotation**: Store API Keys in a secrets manager (KMS / Secrets Manager), rotate them regularly, and use separate keys per business scenario for observability and isolation.
* **Idempotency and request tracing**: Record the submitted `task_id` and `request_id` on your side to reconcile against platform logs.
* **Content safety**: We recommend pre-screening user-supplied prompts and reference images on your side to reduce the likelihood of triggering `400` content-violation errors.
## Next Steps
Full parameter definitions and an interactive Playground for each model
Credit consumption rules by model, resolution, and scenario
Track new model launches, parameter changes, and service updates
Please read the Terms of Service and Privacy Policy before onboarding
# Introduction
Source: https://docs.imini.ai/en/guide/introduction
Get to know imini Open Platform — a one-stop AIGC image and video generation API for developers.
**imini Open Platform** is an AIGC aggregation gateway built for developers. We expose industry-leading image and video generation models — including Google Gemini, Kling, and ByteDance Doubao — through **imini's own unified API protocol**, so you **don't need to integrate each model vendor separately. A single API Key gives you access to all capabilities.**
From rapid prototypes to production at scale, imini lets you skip the repetitive work of model evaluation, authentication plumbing, SDK wrapping, and async task orchestration — so you can focus on your product.
## Core Capabilities
Text-to-image and image-to-image (edit / outfit change / style transfer). Up to **14 reference images**, output up to **4K resolution**, and 14 aspect ratios to choose from.
Text-to-video, image-to-video, first/last-frame interpolation, and multimodal references (image + video + audio). Supports **720P / 1080P** output with optional audio.
Uses `Authorization: Bearer` standard authentication. **cURL, Postman, and any HTTP client work out of the box.** Request parameters follow imini's own protocol, keeping the interface consistent across models.
Every generation endpoint returns a `task_id` immediately on submission, and you poll for the result. **Ideal for batch concurrency and production-grade integration** without blocking your main workflow.
## Why imini
* **One key, all models**: No need to register and maintain separate accounts with multiple vendors. Switching models is just a matter of changing the `model` field in your request body.
* **Pay per call, no subscription lock-in**: Prepaid credit model — use what you need, with no monthly fees, no minimum spend, and no tiered pricing tricks. See [Pricing](/en/guide/pricing).
* **Standard HTTP access**: Bearer Token authentication means cURL, Postman, and any language's HTTP library can call directly — integrate in 5 minutes.
* **Unified protocol**: All models share the same request/response structure, error code conventions, and task query endpoint, reducing maintenance overhead.
* **Continuously updated model library**: New mainstream models are integrated shortly after their upstream release — no need to rewrite code for every new generation.
* **Production-grade reliability**: Global CDN plus multi-region routing. Every error response includes a `request_id` for easy traceability.
## API Architecture Overview
All imini endpoints follow three consistent conventions:
All models share the same base URL:
```
https://openapi.imini.ai/imini/router
```
Every request passes the API Key via HTTP header:
```http theme={null}
Authorization: Bearer YOUR_API_KEY
```
Submit → receive `task_id` → poll → get result URL. Ideal for long-running generation.
All errors share the same shape: `{ error: { code, message, status, request_id } }`, so you can handle them uniformly.
## The Call Flow in 30 Seconds
```bash theme={null}
# 1. Submit an image generation task
curl -X POST https://openapi.imini.ai/imini/router/v1/images/generate \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/nano-banana",
"prompt": "A shiba inu in a spacesuit floating inside a space station, cinematic lighting",
"aspect_ratio": "16:9"
}'
# → returns { "task_id": "tsk_abc123" }
# 2. Poll the task result
curl https://openapi.imini.ai/imini/router/v1/images/tasks/tsk_abc123 \
-H "Authorization: Bearer YOUR_API_KEY"
# → returns { "status": "succeeded", "images": [{ "url": "..." }] }
```
To switch models, just change `model` to `google/nano-banana-pro`, `kling/kling-v3`, etc. — the parameter structure stays compatible.
## Typical Use Cases
* **Creative design SaaS**: Integrate AI image generation into Figma/Canva-style products, letting users upload reference images for stylistic remixing.
* **E-commerce marketing automation**: Batch-generate product hero shots, white-background images, and campaign posters based on product attributes, ready to feed into your layout tool.
* **Short video and UGC platforms**: Text-to-video templates, AI effects, user avatar generation, and other social features.
* **Games and digital content**: Character splash art, scene concept art, NPC portraits — bulk-produced to dramatically cut pre-production art costs.
* **AI workflows and agents**: Plug into workflow platforms like Dify, Coze, Make, Zapier, and n8n as an image/video generation node.
* **Internal enterprise tools**: Training materials, slide visuals, marketing-copy illustrations, and other non-public asset production.
## Next Steps
Get an API Key and make your first call in 5 minutes
Per-scenario, per-resolution credit cost breakdown for each model
Complete API documentation with an interactive Playground
New model launches, feature updates, and change notices
# Pricing
Source: https://docs.imini.ai/en/guide/pricing
Credit consumption details for each model's API calls.
## Image Models
### google/nano-banana
Based on Gemini 2.5 Flash Image — fast and low-cost.
| Scenario | Credits per image |
| ------------- | ----------------- |
| Text to Image | 50 credits |
| Image Edit | 100 credits |
### google/nano-banana-pro
Based on Gemini 3 Pro Image — supports up to 4K output.
| Resolution | Credits per image |
| ---------- | ----------------- |
| 1K | 120 credits |
| 2K | 120 credits |
| 4K | 200 credits |
### google/nano-banana-2
Based on Gemini 3.1 Flash Image — the most fully featured model in the Flash series, supporting 512p to 4K.
| Resolution | Credits per image |
| ---------- | ----------------- |
| 512 | 50 credits |
| 1K | 75 credits |
| 2K | 100 credits |
| 4K | 150 credits |
### openai/gpt-image-2
Based on OpenAI gpt-image-2 — supports 1K / 2K / 4K, with three quality tiers (low / medium / high) at each resolution. Quality is orthogonal to resolution.
| Resolution | Quality | Credits per image |
| ---------- | ------- | ----------------- |
| 1K | low | 60 credits |
| 1K | medium | 120 credits |
| 1K | high | 350 credits |
| 2K | low | 70 credits |
| 2K | medium | 180 credits |
| 2K | high | 600 credits |
| 4K | low | 80 credits |
| 4K | medium | 300 credits |
| 4K | high | 1000 credits |
## Video Models
### wan3.0-video
| Resolution | Credits per requested output second | 5-second example |
| ---------- | ----------------------------------- | ---------------- |
| 480P | 80 | 400 |
| 720P | 160 | 800 |
| 1080P | 280 | 1400 |
Defaults to 720P and 5 seconds; output duration is 2-30 seconds. Reference video duration adds no charge, and audio generation does not change the price. Billing uses requested output duration, without a true-up against the actual output duration.
See [Wan 3.0 Video](/en/api-reference/videos/wan3-0-video).
### kling/kling-v3
| Resolution | Audio generated | Credits per second |
| ---------- | --------------- | ------------------ |
| 720P | No | 120 credits |
| 720P | Yes | 170 credits |
| 1080P | No | 160 credits |
| 1080P | Yes | 220 credits |
### kling/kling-v3-omni
| Resolution | Audio generated | Reference video | Credits per second |
| ---------- | --------------- | --------------- | ------------------ |
| 720P | No | No | 120 credits |
| 720P | Yes | No | 160 credits |
| 720P | No | Yes | 170 credits |
| 1080P | No | No | 160 credits |
| 1080P | Yes | No | 200 credits |
| 1080P | No | Yes | 220 credits |
### kling/kling-v3-motion-control
| Resolution | Credits per second |
| ---------- | ------------------ |
| 720P | 180 credits |
| 1080P | 220 credits |
### doubao/seedance-2.0
**Without a reference video**
| Resolution | Credits per output second |
| ---------- | ------------------------- |
| 480P | 100 credits |
| 720P | 200 credits |
**With a reference video**
Consumption depends on the total length of the reference videos and the output duration. Typical ranges:
| Resolution | Cost range |
| ---------- | ------------------- |
| 480P | 310 – 1,530 credits |
| 720P | 660 – 3,290 credits |
Common scenario examples:
| Total reference video length | Output duration | 480P | 720P |
| ---------------------------- | --------------- | ----- | ----- |
| 2s | 5s | 360 | 770 |
| 5s | 5s | 510 | 1,100 |
| 5s | 10s | 770 | 1,650 |
| 10s | 5s | 920 | 1,980 |
| 15s | 15s | 1,530 | 3,290 |
### doubao/seedance-2.0-fast
**Without a reference video**
| Resolution | Credits per output second |
| ---------- | ------------------------- |
| 480P | 80 credits |
| 720P | 160 credits |
**With a reference video**
Consumption depends on the total length of the reference videos and the output duration. Typical ranges:
| Resolution | Cost range |
| ---------- | ------------------- |
| 480P | 250 – 1,210 credits |
| 720P | 520 – 2,590 credits |
Common scenario examples:
| Total reference video length | Output duration | 480P | 720P |
| ---------------------------- | --------------- | ----- | ----- |
| 2s | 5s | 290 | 610 |
| 5s | 5s | 410 | 870 |
| 5s | 10s | 610 | 1,300 |
| 10s | 5s | 730 | 1,550 |
| 15s | 15s | 1,210 | 2,590 |
### dashscope/happyhorse-1.0
| Resolution | Credits per second |
| ---------- | ------------------ |
| 720P | 180 credits |
| 1080P | 300 credits |
# Privacy Policy
Source: https://docs.imini.ai/en/legal/privacy
imini Open Platform Privacy Policy
Welcome to imini Open Platform (hereinafter "**imini**", "**the Platform**", "**we**", or "**us**"). We understand the importance of personal information and respect and protect the personal information and data security of all users (hereinafter "**you**") of this Platform. This Privacy Policy (hereinafter "this Policy") explains how we collect, use, store, share, and protect your information, as well as the rights you have with respect to your personal information.
**Please read and fully understand this Policy before using the Platform.** By using the Platform's services, you acknowledge that you have read and agree to all the terms of this Policy. If you do not agree with any part of this Policy, please discontinue use of the Platform's services immediately.
## 1. Scope
This Policy applies to all services provided by imini Open Platform (collectively, the "**Services**"), including AIGC image generation, video generation, task management, and account management, accessed via the website, API, SDK, developer console, or other means.
This Policy does not apply to products or services independently provided to you by third parties (including but not limited to underlying model providers, payment institutions, or identity verification providers). When using such third-party services, you should read and comply with their respective privacy policies.
## 2. Definitions
* **Personal Information**: Information that, alone or in combination with other information, can identify a specific natural person.
* **Interaction Data**: The input content you submit to the Platform through the API (prompts, reference images, reference videos) and the output content returned by the underlying models (generated images, videos, etc.).
## 3. Information We Collect
### 3.1 Information you provide to us
* **Account information**: Email, password (encrypted), company/team name (if applicable).
* **Payment and billing information**: Top-up records, invoice title, tax ID. We **do not store** your full bank card number or payment password; such information is handled by third-party payment institutions.
* **Contact and feedback information**: Content you voluntarily provide when submitting tickets or contacting support.
### 3.2 Information we collect automatically when you use the Services
* **Device and log information**: IP address, access time, API call records, error logs, User-Agent, request origin.
* **Usage data**: API Key usage, models called, credits consumed, task status, and summaries of request parameters.
### 3.3 Interaction data
The **prompts, reference images, and reference videos** you submit via the API, along with the **images and videos** generated by the models, constitute interaction data. Our handling of interaction data follows these principles:
* We only process it to the extent necessary to provide you with the Services, including forwarding requests to the underlying models, returning results to you, and short-term caching as needed;
* Interaction data will be sent to the underlying model providers for processing, which is also subject to their respective privacy policies;
* We **do not** use your interaction data to train our own models, nor do we use it for purposes unrelated to providing the Services.
## 4. How We Use Information
We collect information for the following purposes:
* **Providing and maintaining the Services**: Registration, API call routing, task scheduling, and billing settlement.
* **Securing accounts and the Services**: Detecting abnormal logins, preventing malicious calls, and identifying and handling abuse.
* **Improving the service experience**: Analyzing usage data to optimize interface performance and to detect and fix defects.
* **Service notifications**: Sending necessary maintenance announcements, change notices, billing reminders, and similar communications (you may unsubscribe from non-essential notifications).
* **Fulfilling legal obligations**: Retaining logs and cooperating with lawful investigations as required by applicable laws, regulations, and regulatory requirements.
## 5. How We Share Information
We pledge not to **sell** your personal information to any third party. We may share your information only in the following circumstances:
* **Where we have your explicit consent**.
* **Where necessary to provide the Services**: Forwarding interaction data to underlying model providers; forwarding payment information to payment institutions.
* **Sharing with affiliates**: Limited to what is necessary to provide the Services, subject to the same restrictions as this Policy.
* **Sharing with service vendors**: For example, cloud computing, data storage, SMS services, or identity verification providers. We require them to maintain confidentiality and take appropriate security measures.
* **Legal requirements**: Pursuant to laws, regulations, legal proceedings, or mandatory government requests.
* **Business changes**: In the event of a merger, acquisition, or asset transfer, we will require the new holder to continue to be bound by this Policy.
## 6. Data Storage and Cross-Border Transfer
### 6.1 Storage locations
Our servers are deployed in the Operator's place of registration and the regions of its partner cloud providers (which may include but are not limited to Hong Kong, Singapore, the United States, and the European Union). Your information may be transferred and stored between these regions.
### 6.2 Retention periods
We only retain your personal information for as long as necessary to achieve the purposes described in this Policy. Typical retention periods are:
| Information category | Retention period |
| -------------------------------------------------------- | ---------------------------------------------------------------------------------------------- |
| Account registration information (email, password, etc.) | Duration of the account plus the statutory retention period after account deletion |
| Transaction and billing information | As required by applicable tax and accounting laws (typically no less than 7 years) |
| API call logs and usage data | Generally no more than 3 months; abnormal or security logs may be extended to 12 months |
| Support tickets and correspondence | Duration of the account, for after-sales and dispute handling |
| Interaction data (prompts, generated content) | Short-term caching after task completion and delivery; not retained long-term unless necessary |
Where otherwise required by laws or regulations, those requirements prevail. After the retention period, we will delete or anonymize your personal information.
### 6.3 Cross-border transfer
Because underlying model providers and cloud infrastructure are distributed across multiple countries/regions, your interaction data and some personal information may be transferred outside the Operator's place of registration for processing. We will use lawful mechanisms consistent with applicable law (such as standard contractual clauses or user consent) to secure such transfers.
## 7. Data Security
We take industry-standard technical and organizational measures to protect your information, including but not limited to:
* HTTPS / TLS encryption at the transport layer;
* One-way encryption or segmented storage of sensitive fields (such as passwords and API Keys);
* Role-based access control and the principle of least privilege;
* Regular security audits, vulnerability scans, and penetration testing;
* Employee confidentiality agreements and data access logging.
Despite our best commercial efforts, please understand that the internet environment is not absolutely secure. In the event of a personal information security incident, we will notify you and the regulator as required by law.
## 8. Your Rights
Within the limits allowed by laws and regulations, you have the following rights with respect to your personal information:
* **Right of access**: View your account information, call records, and billing details.
* **Right of rectification**: Correct inaccurate or incomplete personal information.
* **Right of deletion**: Request deletion of your personal information where legally permitted.
* **Right to withdraw consent**: For information processed on the basis of consent, you may withdraw consent at any time.
* **Right to close your account**: You may close your account at any time via the console or by contacting support. After closure, except as required by law, we will delete or anonymize your personal information.
* **Right to complain and report**: If you believe your lawful rights have been infringed, you may lodge a complaint with us or report it to the competent authority.
You may exercise the above rights through the methods provided in the "Contact Us" section of this Policy. We will verify and handle your request within 15 business days of receipt.
## 9. Third-Party Services
The underlying models integrated into the Platform are operated by third-party model providers. When interaction data is forwarded to them for processing, it is also subject to their respective privacy policies. We evaluate the security and compliance posture of third-party providers when selecting them, but we are not liable for their independent actions.
## 10. Minors
The Platform is intended for developers and business customers only, and is not provided to minors under 18. If we learn that an account is actually used by a minor, we reserve the right to suspend the account and delete the related information.
## 11. Changes to This Policy
We may revise this Policy from time to time. For material changes, we will notify you through in-product notices, email, or prominent announcements. If you continue to use the Services after the changes take effect, you will be deemed to accept the revised Policy.
## 12. Contact Us
If you have any questions, comments, or suggestions regarding this Policy, or wish to exercise your rights over your personal information, please contact us through the following channels:
* **Email**: `support@imini.com`
* **Website**: [https://imini.ai](https://imini.ai)
We will respond as soon as possible after receiving your request.
# Terms of Service
Source: https://docs.imini.ai/en/legal/terms
imini Open Platform Terms of Service
Welcome to imini Open Platform (hereinafter "**imini**", "**the Platform**", "**we**", or "**us**"). These Terms of Service (hereinafter "these Terms") form a binding agreement between you (hereinafter "**you**" or "**User**") and the Operator regarding your use of the Platform's services.
**Please read these Terms carefully before using the Platform, paying particular attention to clauses that exclude or limit liability, govern dispute resolution, or designate the applicable law (shown in bold).** By registering an account, calling the API, or otherwise using the Platform, you acknowledge that you have read, understood, and accepted all of these Terms. If you do not agree with these Terms, please discontinue use of the Platform immediately.
## 1. Definitions
* **Services**: All functionality provided by the Platform, including AIGC image generation, video generation, task queries, and account management.
* **Account**: Your identity on the Platform, including the web console account and API Keys.
* **Interaction Data**: The prompts, reference images, and reference videos you submit to the Platform, together with the images and videos generated by the models.
* **Underlying Models**: AI models developed by third-party model providers and made available through the Platform.
* **Credits**: The Platform's billing unit, used to settle API call charges.
## 2. Description of the Services
The Platform is an AIGC model aggregation gateway that provides access to multiple underlying models through a unified API protocol. **You understand and agree that**:
* The actual inference capabilities, output quality, and availability of the underlying models are determined by the model providers; the Platform only provides access, routing, billing, and operational support.
* Different models may have their own usage restrictions, content policies, and SLAs. When using them, you must also comply with the model providers' relevant terms.
* We may launch, retire, or adjust models as business needs require. Relevant changes will be announced in the [Changelog](/en/changelog/index).
## 3. Account Registration and Management
### 3.1 Registration
You must provide truthful, accurate, and complete registration information, and promptly update it when it changes. Using a false identity or another person's identity to register is prohibited.
### 3.2 Account security
* You must safeguard your account password and API Keys, and bear full responsibility for all actions taken under your account.
* If you discover an API Key leak or account anomaly, you should rotate the key immediately and notify us.
* We reserve the right to suspend or restrict your account if we detect abnormal logins, malicious calls, or violations.
### 3.3 Account closure
You may apply to close your account at any time via the console or by contacting support. After closure, unused credits will be forfeited, and related data will be handled according to the Platform's [Privacy Policy](/en/legal/privacy).
## 4. License
Subject to your compliance with these Terms, the Platform grants you a limited, revocable, non-exclusive, non-transferable, and non-sublicensable right to access and use the Services. Without our written permission, you must not:
* Reverse engineer, decompile, or otherwise attempt to obtain the source code of the Platform;
* Use crawlers, scripts, or other automated tools to scrape data from the Platform in bulk;
* Resell, sublicense, or repackage the Platform's API as a service that competes with imini;
* Circumvent or compromise any security or billing mechanism of the Platform.
## 5. User Obligations and Prohibited Conduct
### 5.1 Legal compliance
You agree that, in using the Platform, you will comply with applicable laws and regulations (including those of your jurisdiction, the Operator's place of registration, and the service locations of the underlying model providers) and with the underlying model providers' usage policies.
### 5.2 Prohibited content
**You must not use the Platform to generate, distribute, or store any of the following content**:
* Content involving child sexual exploitation or sexualizing minors (CSAM);
* Content that incites or assists violence, terrorism, self-harm, or serious physical harm to others;
* Hate speech or discriminatory content targeting protected groups;
* Unauthorized fabrication or deepfake of real persons' likenesses, voices, or identities for the purposes of fraud, harassment, defamation, or the like;
* Fraudulent, phishing, malware, or other illegally motivated content;
* Content that infringes others' intellectual property, trade secrets, privacy, or likeness rights;
* Any other content that violates applicable laws or the usage policies of the underlying model providers.
### 5.3 Prohibited conduct
* Using the Platform to train AI models that compete with the Platform or the underlying model providers;
* Using the Platform for unauthorized face recognition or biometric identification;
* Interfering with the normal operation of the Platform, circumventing rate limits, or affecting other users' quality of service in any way;
* Circumventing the Platform's moderation or interception mechanisms for prohibited content;
* Repackaging the Platform's API and offering it as a service in direct competition with imini.
### 5.4 Enforcement
Upon discovering a violation, we may take the following measures in proportion to its severity, **without prior notice**:
* Refuse to process relevant requests or intercept violating outputs;
* Freeze associated credits, suspend, or terminate API Keys;
* Suspend or close your account;
* Preserve logs and report to the competent authorities;
* Require you to compensate for all losses caused to the Platform or third parties.
### 5.5 Appeals
If you disagree with the enforcement measures above, you may appeal within **7 days** of receiving notice by emailing `support@imini.com`. We will review the matter within a reasonable time and notify you of the outcome. If no appeal is filed within the period, the decision will be deemed final.
## 6. Fees and Credits
### 6.1 Billing rules
The Platform uses a prepaid credit model. You top up to obtain credits, and each API call consumes credits at each model's [Pricing](/en/guide/pricing).
### 6.2 Price adjustments
We reserve the right to adjust the unit price of credits and the pricing of models in response to market, cost, and underlying model pricing changes. Adjustments will be announced in advance in the [Changelog](/en/changelog/index) and will apply from the effective date.
### 6.3 Refund policy
* **Topped-up credits and subscription fees**: Unless otherwise mandated by law, these are **non-refundable** once paid. If platform-side reasons prevent credits or subscription benefits from being used normally, we will verify and provide compensation or refund as appropriate.
* **Consumed credits**: Credits that have been successfully used and returned a result (including partial failures where fees were already charged) are non-refundable.
* **Dispute handling**: If you dispute a bill, please raise the issue within **30 days** of the bill's generation by emailing `support@imini.com`. Otherwise, the bill will be deemed correct.
### 6.4 Overdue balances and suspension
If you have a credit line, you must promptly top up to cover any overdue balance. During the overdue period, we may suspend the Services until the balance is cleared.
## 7. Interaction Data and Intellectual Property
### 7.1 Your interaction data
* You must have all necessary rights to the **prompts, reference images, and reference videos** you submit, and ensure that they do not infringe any lawful rights of third parties.
* We only process interaction data to the extent necessary to provide the Services. See the Privacy Policy for details.
### 7.2 Ownership of generated content
* Subject to your compliance with these Terms and the applicable underlying model terms, you have the right to use the images and videos generated through the Platform.
* **You understand and agree** that copyright attribution of AI-generated content varies by jurisdiction. In some jurisdictions, rights in generated content may be **jointly held by you, the Operator, and the underlying model providers**. The Platform makes no warranty that generated content constitutes a copyrightable work, qualifies for copyright, or may be used commercially without restriction.
* Your use of generated content must comply with the **underlying model providers' terms**, including but not limited to attribution requirements, commercial-use restrictions, and prohibitions on claiming human authorship.
### 7.3 Platform intellectual property
The intellectual property rights of the Platform (including but not limited to domain names, trademarks, logos, software code, API protocols, and documentation content) belong to the Platform. Without our written permission, you may not copy, modify, distribute, or otherwise use them.
### 7.4 Feedback
Any opinions, suggestions, or feedback (excluding interaction data) you provide to us may be used freely by us without compensation and without attributing you.
## 8. Third-Party Models and Services
### 8.1 Disclaimer regarding third-party models
The underlying models integrated into the Platform are developed and operated by third parties. **You understand and agree that**:
* The output quality, accuracy, and stability of the underlying models are determined by the model providers, and the Platform makes no express or implied warranties in this regard;
* The underlying models may produce errors, biases, "hallucinations", or results that do not meet expectations. You should evaluate and decide whether to adopt them yourself;
* The underlying model providers may unilaterally change their terms, retire models, or restrict specific uses. The Platform will make reasonable efforts to inform you, but is not liable for such actions.
### 8.2 Third-party links
The Platform may contain links to third-party websites. Such links are provided for your convenience only, and the Platform is not responsible for the content or services of third-party websites.
## 9. Service Availability and Disclaimer
### 9.1 Service availability
* We will use commercially reasonable efforts to keep the Services continuously available, but **do not guarantee** uninterrupted, error-free service or that the Services will meet all of your expectations.
* The Platform is not liable for service interruptions caused by system maintenance, upgrades, network failures, force majeure (including natural disasters, war, strikes, government actions, power outages, carrier failures, etc.), cyberattacks, or third-party causes.
### 9.2 Disclaimer
**To the fullest extent permitted by law, the Services are provided on an "as is" and "as available" basis, and the Platform expressly disclaims all express or implied warranties**, including but not limited to merchantability, fitness for a particular purpose, non-infringement, accuracy, completeness, and uninterrupted operation.
## 10. Limitation of Liability
**To the fullest extent permitted by law**:
* The Platform is not liable for any indirect, incidental, special, or punitive damages (including but not limited to lost profits, loss of goodwill, data loss, or business interruption);
* The Platform's aggregate liability to you under these Terms is limited to **the total amount of fees you actually paid to the Platform in the 12 months preceding the dispute**;
* You are responsible for compensating the Platform or third parties for any losses (including reasonable attorneys' fees) caused by your breach of these Terms, infringement of third-party rights, or unlawful conduct.
## 11. Modification and Termination
### 11.1 Modification
We may revise these Terms from time to time. Material changes will be announced through in-product notices, email, or prominent announcements. If you continue to use the Services after the changes take effect, you will be deemed to accept the revised Terms.
### 11.2 Termination
These Terms terminate upon any of the following:
* You close your account;
* You materially breach these Terms, and we decide to terminate the Services provided to you;
* The Platform is unable to continue providing the Services due to laws, regulations, or regulatory requirements.
Termination does not affect rights and obligations that arose before termination. Sections 5, 7, 9, 10, and 12 survive any termination of these Terms.
## 12. Governing Law and Dispute Resolution
### 12.1 Governing law
**The formation, validity, performance, interpretation, and dispute resolution of these Terms are governed by the laws of the State of Delaware, USA** (excluding its conflict-of-laws rules). The United Nations Convention on Contracts for the International Sale of Goods (CISG) does not apply to these Terms.
### 12.2 Arbitration
Any dispute arising out of or in connection with these Terms shall first be resolved through friendly negotiation. If negotiation fails, **either party may submit the dispute to the American Arbitration Association ("AAA") for institutional arbitration under the AAA Commercial Arbitration Rules in effect at the time of submission.** The seat of arbitration shall be the State of Delaware, USA, the language of arbitration shall be English, and the tribunal shall consist of one arbitrator. The arbitration award shall be final and binding on both parties.
### 12.3 Class action waiver
**You and the Platform agree that any dispute under these Terms shall be brought only in an individual capacity in arbitration or litigation, and shall not be asserted as a class action, class arbitration, or representative action**, nor consolidated with claims of other users.
### 12.4 Exception for injunctive relief
Notwithstanding Section 12.2, either party may seek temporary or injunctive relief before **a state or federal court of competent jurisdiction in the State of Delaware, USA** for the following matters:
* Actual or threatened infringement of intellectual property, trade secrets, or confidential information;
* Unauthorized access to the Platform or misuse of data.
The parties consent in advance to the personal jurisdiction of the foregoing courts for such matters.
## 13. Miscellaneous
* **Entire agreement**: These Terms, together with the Privacy Policy and other rules published by the Platform, constitute the entire agreement between you and the Platform.
* **Severability**: If any provision of these Terms is held invalid or unenforceable, the remaining provisions shall remain in full force and effect.
* **No waiver**: The Platform's failure or delay in exercising any right under these Terms does not constitute a waiver of that right.
* **Notice**: Any notice sent by the Platform via in-product notice, email, SMS, or announcement is deemed delivered upon being sent.
## 14. Contact Us
If you have any questions about these Terms, please contact us through the following channels:
* **Email**: `support@imini.com`
* **Website**: [https://imini.ai](https://imini.ai)