API Documentation
OpenAPI specs, supported AI models matrix, code snippets, and live test runner.
AI Image Detector
/api/v1/detect
Analyzes input images using our Deep Scan AI Image Detector API to determine whether an image was generated by AI or captured by a human camera. Supports both `application/json` (with base64/url) and `multipart/form-data` (for direct file uploads).
Supported AI Models & Action Capabilities Matrix
Complete list of models, resolutions, aspect ratios & quality options synced from Generate App UI.
Curator Image Authenticity Detectorcurator-detectorPOST /api/v1/detect▼
Deep neural image classifier detecting synthetic artifacts, noise distribution, and diffusion patterns.
- Authenticity classification (AI vs Human camera)
- Confidence score calculation (0.00 - 1.00)
- Public HTTP/HTTPS Image URL input
- Base64 byte stream image input
GPT Image 2gpt-image-2POST /api/v1/generate▼
Flagship photorealistic image model optimized for crisp lighting, cinematic textures, and detailed object composition.
- Text-to-Image prompt generation
- Image-to-Image with base64Refs
- Quality selection (low, medium)
- Resolution control (1K, 2K, 4K)
Grok Imaginegrok-imaginePOST /api/v1/generate▼
Ultra-fast generation model engineered for maximum throughput and rapid prototyping with vibrant contrast.
- Ultra-fast prompt execution (< 3s latency)
- Wide aspect ratio support (21:9, 9:20, 1:2, 2:1)
- High contrast artistic rendering
Z-Image-Turboz-image-turboPOST /api/v1/generate▼
Turbo-charged fast model designed for high-frequency interactive applications and instant thumbnail generation.
- Sub-second image generation pipeline
- Low latency real-time prompt rendering
- Ultra-wide 21:9 and vertical 9:21 ratios
Nano Banana Pronano-banana-proPOST /api/v1/generate▼
Compact pro model specializing in punchy graphics, high-definition character design, and vivid contrast.
- Sharp edge rendering & high contrast
- 4K Resolution output support
- Multi-ratio aspect ratio formatting
Nano Banana 2.0nano-banana-2.0POST /api/v1/generate▼
Second generation Nano model featuring upgraded prompt adherence and smoother color blending.
- Enhanced prompt adherence
- Subtle gradient lighting simulation
- 4K Resolution output support
Nano Banananano-bananaPOST /api/v1/generate▼
Lightweight entry model suited for fast wireframing, draft mockups, and low-overhead generation.
- Lightweight draft generation
- 2K Resolution default output
Seedream 5.0 Liteseedream-5.0-litePOST /api/v1/generate▼
Creative illustration model tailored for anime characters, digital art, concept design, and fantasy landscapes.
- Anime & manga style generation
- 3K High-Definition digital art
- Stylized color palette rendering
Seedream 4.5seedream-4.5POST /api/v1/generate▼
Digital art generation model specializing in oil painting textures, fantasy environments, and concept design.
- Digital fantasy artwork synthesis
- Concept art brushstroke rendering
- 4K Ultra-Resolution output
Seedream 4.0seedream-4.0POST /api/v1/generate▼
Legacy 4.0 illustration engine suited for classic 2D drawings and graphic sketches.
- Classic 2D illustration rendering
- 1K / 2K / 4K Multi-resolution support
Qwen Image 2.0qwen-image-2.0POST /api/v1/generate▼
Advanced Qwen model with superior multi-lingual text comprehension and photorealistic scene composition.
- Multi-lingual prompt understanding
- Photorealistic object synthesis
- Complex multi-subject composition
Qwen Image 2.0 Proqwen-image-2.0-proPOST /api/v1/generate▼
Professional Qwen tier offering enhanced prompt fidelity, intricate material details, and studio quality.
- High-precision multi-subject prompt alignment
- Ultra-detailed skin and material textures
- 4K Ultra-resolution output
Wanx 2.7wanx-2.7POST /api/v1/generate▼
Cinematic image generation model focused on dramatic lighting, architectural precision, and artistic atmosphere.
- Cinematic lighting & color grading
- Atmospheric landscape rendering
- 4K Architectural design synthesis
Flux Schnell (Fast)flux-schnellPOST /api/v1/generate▼
State-of-the-art Flux Schnell model providing elite detail rendering, accurate prompt following, and realistic human anatomy.
- Next-gen Flux Schnell generation
- Complex prompt alignment & spatial accuracy
- Human anatomy & hand rendering
Auto-Filled Code Snippets
Copy ready-to-run request code
curl -X POST "https://curator-ai-detector.vercel.app/api/v1/detect" \
-H "Authorization: Bearer curator_live_9x8a..." \
-H "Content-Type: application/json" \
-d '{
"imageUrl": "https://tmpfiles.org/dl/18413490/sample.jpg"
}'Live Test Runner Console
Send request & inspect output
Authentication & Security
How to securely authenticate your API requests
Curator API uses API keys for authentication. You must include your API key in the Authorization HTTP header as a Bearer token.
- Keep your API keys secure and never expose them in client-side code (browsers, mobile apps).
- All API requests must be made over HTTPS. Calls made over plain HTTP will fail.
- If you suspect your key has been compromised, you can revoke it immediately from the Dashboard.
Rate Limits & Quota
Understanding request limits and tiers
To ensure fair usage and maintain high availability, API requests are subject to rate limiting based on your subscription tier.
Free Tier (Starter)
- Batas Harian: 10 Requests / Hari
- Integrasi: Standard API Key
- Priority: Standard processing
Pro Unlimited
- Batas Harian: 999.999 Requests / Hari
- Integrasi: Custom Branded API Key
- Priority: Dedicated GPU cluster
Note: Exceeding your daily quota will result in a 429 Too Many Requests response.
Error Dictionary
Standardized API error codes and their meanings
| HTTP Status | Code | Description |
|---|---|---|
| 400 | BAD_REQUEST | The request was invalid or missing required parameters (e.g., missing prompt or invalid image format). |
| 401 | UNAUTHORIZED | No API key provided, or the API key is invalid/revoked. |
| 403 | FORBIDDEN | The API key does not have permission for this endpoint (scope restriction). |
| 429 | RATE_LIMIT_EXCEEDED | You have hit your request rate limit or monthly quota. Please upgrade your tier or wait. |
| 500 | INTERNAL_SERVER_ERROR | An unexpected error occurred on our AI infrastructure. We are automatically notified. |