Skip to main content
The MeiGen API allows you to generate images programmatically. All endpoints are available at https://www.meigen.ai/api/.
Prefer natural language? If you use Claude Code, Cursor, or OpenClaw, try the MCP Server for AI-native image generation without writing HTTP code.

​
Authentication

API requests require a Bearer token. There are two authentication methods: Use an API key that starts with meigen_sk_. Create one from your account settings under API Keys. 
Authorization: Bearer meigen_sk_YOUR_API_KEY
API tokens can only use purchased credits. Daily free credits are not available for API calls. Ensure your account has purchased credits before making API requests.

​
Session Token

For browser-based integrations, you can use a Supabase session access token. This method uses both daily and purchased credits.

​
Base URL

https://www.meigen.ai/api

​
Request Format

All request bodies must be sent as JSON with the Content-Type: application/json header. 
curl -X POST https://www.meigen.ai/api/generate/v2 \
  -H "Authorization: Bearer meigen_sk_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "a minimalist logo", "modelId": "gemini-3-pro-image-preview"}'

​
Response Format

All responses return JSON. Successful responses include a success: true field: 
{
  "success": true,
  "generationId": "abc-123",
  "status": "processing"
}
Error responses include an error field: 
{
  "error": "Error description"
}

​
Asynchronous Generation

Image generation is asynchronous. The flow is:
  1. Submit a generation request → POST /api/generate/v2
  2. Poll the status endpoint → GET /api/generate/v2/status/:id
  3. Retrieve the completed image → GET /api/images/:id

​
Polling Best Practices

  • Recommended interval: 3 seconds between status checks
  • Stop when: status is completed or failed
  • Timeout: consider giving up after 5 minutes for image models, 10 minutes for video

​
Typical Generation Times

ModelTypical Time
Z Image Turbo~5 seconds
Nanobanana 2, Seedream~15 seconds
Nanobanana Pro~15 seconds
GPT image1.5~20 seconds
Midjourney V7 / Niji 7~60 seconds
Seedance 2.0 (video)~1–3 minutes
Veo 3.1 (video)2–6 minutes

​
Rate Limits

API requests are subject to rate limiting. If you receive a 429 Too Many Requests response:
  • Wait 10–30 seconds before retrying
  • Implement exponential backoff for repeated failures
  • Specific rate limits may vary based on server load

​
Caching

Some GET endpoints return cached responses:
EndpointCache Duration
GET /api/models5 minutes
GET /api/images/:id1 hour
POST endpointsNo caching

​
Credits

Each generation consumes credits based on the model used. Check the Models page for per-model pricing.
ModelCredits
Z Image Turbo2
GPT image1.52
Nanobanana 25
Seedream 5.0 Lite5
Seedream 4.55
Nanobanana Pro10
Midjourney V715
Niji 715
Seedance 2.0Per-second (see Models)
Veo 3.120

​
Error Responses

Status CodeMeaning
400Bad request — invalid parameters
401Unauthorized — invalid or missing token
402Payment required — insufficient credits
404Not found
429Rate limited — wait and retry
500Server error

​
Endpoints

Generate Image

POST /api/generate/v2

List Models

GET /api/models

Get Image

GET /api/images/:id

Manage Tokens

POST/GET/DELETE /api/tokens