Skip to main content
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

Image generation

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.

Video generation

Text-to-video, image-to-video, first/last-frame interpolation, and multimodal references (image + video + audio). Supports 720P / 1080P output with optional audio.

Standard HTTP access

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.

Asynchronous task model

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.
  • 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:

Unified endpoint

All models share the same base URL:
https://openapi.imini.ai/imini/router

Unified authentication

Every request passes the API Key via HTTP header:
Authorization: Bearer YOUR_API_KEY

Unified task model

Submit → receive task_id → poll → get result URL. Ideal for long-running generation.

Unified error structure

All errors share the same shape: { error: { code, message, status, request_id } }, so you can handle them uniformly.

​
The Call Flow in 30 Seconds

# 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

Quickstart

Get an API Key and make your first call in 5 minutes

Pricing

Per-scenario, per-resolution credit cost breakdown for each model

API Reference

Complete API documentation with an interactive Playground

Changelog

New model launches, feature updates, and change notices