OpenRouter Image Gen API Bearer Auth

A thin Hono service over OpenRouter. /generate wraps image generation on google/gemini-3.1-flash-image-preview; /v1/chat/completions is a transparent proxy to OpenRouter's chat completions API (any model).

Authentication

Every request to /generate or /v1/chat/completions must include an Authorization header:

Authorization: Bearer <API_TOKEN>

The token is configured server-side via the API_TOKEN environment variable. Requests without a valid token receive 401 Unauthorized.

POST /generate

Generate one or more images from a text prompt.

Request body (JSON)

Example — JSON response

curl -X POST https://your-host/generate \
  -H "Authorization: Bearer $API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "a serene mountain lake at sunrise, photorealistic",
    "aspect_ratio": "16:9",
    "image_size": "2K"
  }'

Response:

{
  "model": "google/gemini-3.1-flash-image-preview",
  "text": "Here is your image.",
  "images": ["data:image/png;base64,iVBORw0KGgo..."]
}

Example — raw image bytes

Set format: "image" to get the raw image (handy for <img src> proxies or saving to disk):

curl -X POST https://your-host/generate \
  -H "Authorization: Bearer $API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"a red panda astronaut","format":"image"}' \
  --output panda.png

POST /v1/chat/completions

Transparent proxy to OpenRouter's chat completions API. The request body is forwarded as-is (including model, stream, tools, images, etc.), and the response (including SSE streams) is piped back unchanged. Use the same Authorization: Bearer <API_TOKEN> header as /generate; the upstream OPENROUTER_API_KEY is injected server-side.

curl -X POST https://your-host/v1/chat/completions \
  -H "Authorization: Bearer $API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Errors