ImageRouter

Generate AI images with any model using ImageRouter API (requires API key).

Security Scan

The skill's instructions match an image-generation API, but the runtime instructions expect an API key and use tools not declared in the metadata — the declared requirements are incomplete and inconsistent with the documented usage.

Purpose & Capability

The name and description (ImageRouter image generation) match the curl-based examples in SKILL.md that call imagerouter.io endpoints. However, the SKILL.md repeatedly shows an Authorization: Bearer YOUR_API_KEY header while the registry metadata lists no required environment variables or primary credential. That is an inconsistency: an API key is clearly needed for practical use but the skill does not declare it as a required credential.

Instruction Scope

The instructions are limited to calling ImageRouter endpoints and uploading local image files for image-to-image edits. They do not ask the agent to read unrelated system files or secrets. Two minor scope issues: (1) several examples pipe output through jq and xargs (jq is not declared as a required binary), and (2) examples instruct uploading local files (image[]=@/path/...) which transmits user files to the external API — a normal behavior for an image service but a privacy surface the user should be aware of.

Install Mechanism

No install spec and no code files (instruction-only). That minimizes local persistence and disk writes; risk from arbitrary installs is low.

Credentials

The skill does not declare any required environment variables, yet all authenticated API examples require an ImageRouter API key in an Authorization header. The absence of a declared primaryEnv or requires.env is disproportionate to the documented usage and creates ambiguity about how the agent will obtain/store the API key (user prompt, env var, or other).

Persistence & Privilege

The skill is not always-on, does not request elevated persistence, and is instruction-only. It does not request system-wide config changes or other skills' credentials.

What to consider before installing

This skill appears to be a straightforward curl-based guide for the ImageRouter API, but it has important inconsistencies you should address before installing: (1) it shows using an Authorization: Bearer <API_KEY> in every authenticated example yet declares no required credential — ask the publisher to declare a primaryEnv (e.g., IMAGEROUTER_API_KEY) or explain how the key is provided. (2) Examples use jq/xargs but jq is not listed as a required binary — ensure your environment has the tools the skill expects. (3) Using the skill will upload local image files to a third-party service (imagerouter.io); consider privacy implications and verify the service's trustworthiness and terms. If you plan to use this skill, require explicit handling of the API key (not placing it in logs/history), confirm where credentials come from, and prefer ephemeral or scoped keys where possible.

ImageRouter Image Generation

Generate images with any model available on ImageRouter using curl commands.

Available models

The test/test model is a free dummy model that is used for testing the API. It is not a real model, therefore you should use other models for image generation.

Get top 10 most popular models:

curl -X POST 'https://backend.imagerouter.io/operations/get-popular-models'

Search available models by name:

curl "https://api.imagerouter.io/v1/models?type=image&sort=date&name=gemini"

Get all available models:

curl "https://api.imagerouter.io/v1/models?type=image&sort=date&limit=1000"

Quick Start - Text-to-Image

Basic generation with JSON endpoint:

curl 'https://api.imagerouter.io/v1/openai/images/generations' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  --json '{
    "prompt": "a serene mountain landscape at sunset",
    "model": "test/test",
    "quality": "auto",
    "size": "auto",
    "response_format": "url",
    "output_format": "webp"
  }'

Unified Endpoint (Text-to-Image & Image-to-Image)

Text-to-Image with multipart/form-data:

curl 'https://api.imagerouter.io/v1/openai/images/edits' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -F 'prompt=a cyberpunk city at night' \
  -F 'model=test/test' \
  -F 'quality=high' \
  -F 'size=1024x1024' \
  -F 'response_format=url' \
  -F 'output_format=webp'

Image-to-Image (with input images):

curl 'https://api.imagerouter.io/v1/openai/images/edits' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -F 'prompt=transform this into a watercolor painting' \
  -F 'model=test/test' \
  -F 'quality=auto' \
  -F 'size=auto' \
  -F 'response_format=url' \
  -F 'output_format=webp' \
  -F 'image[]=@/path/to/your/image.webp'

Multiple images (up to 16):

curl 'https://api.imagerouter.io/v1/openai/images/edits' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -F 'prompt=combine these images' \
  -F 'model=test/test' \
  -F 'image[]=@image1.webp' \
  -F 'image[]=@image2.webp' \
  -F 'image[]=@image3.webp'

With mask (some models require mask for inpainting):

curl 'https://api.imagerouter.io/v1/openai/images/edits' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  -F 'prompt=fill the masked area with flowers' \
  -F 'model=test/test' \
  -F 'image[]=@original.webp' \
  -F 'mask[]=@mask.webp'

Parameters

• model (required): Image model to use (see https://imagerouter.io/models)
• prompt (optional): Text description for generation. Most models require a text prompt, but not all.
• quality (optional): auto (default), low, medium, high
• size (optional): auto (default) or WIDTHxHEIGHT (e.g., 1024x1024).
• response_format (optional):
  • url (default) - Returns hosted URL
  • b64_json - Returns base64-encoded image
  • b64_ephemeral - Base64 without saving to logs
• output_format (optional): webp (default), jpeg, png
• image[] (optional): Input file for Image-to-Image (multipart only)
• mask[] (optional): Editing mask for inpainting (multipart only)

Response Format

{
  "created": 1769286389027,
  "data": [
    {
      "url": "https://storage.imagerouter.io/fffb4426-efbd-4bcc-87d5-47e6936bf0bb.webp"
    }
  ],
  "latency": 6942,
  "cost": 0.004
}

Endpoint Comparison

Feature	Unified (/edits)	JSON (/generations)
Text-to-Image	✅	✅
Image-to-Image	✅	❌
Encoding	multipart/form-data	application/json

Tips

• Both /v1/openai/images/generations and /v1/openai/images/edits are the same for the unified endpoint
• Use JSON endpoint for simple text-to-image when you don't need file uploads
• Use unified endpoint when you need Image-to-Image capabilities
• Check model features at https://imagerouter.io/models (quality support, edit support, etc.)
• Get your API key at https://imagerouter.io/api-keys

Examples by Use Case

Quick test generation:

curl 'https://api.imagerouter.io/v1/openai/images/generations' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  --json '{"prompt":"test image","model":"test/test"}'

Download image directly:

curl 'https://api.imagerouter.io/v1/openai/images/generations' \
  -H 'Authorization: Bearer YOUR_API_KEY' \
  --json '{"prompt":"abstract art","model":"test/test"}' \
  | jq -r '.data[0].url' \
  | xargs curl -o output.webp