Quick start

1. Get an API key
2. Generate images, videos, and text with any model available on ImageRouter.

Text to Image example:

Curl

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

Javascript

const url = 'https://api.imagerouter.io/v1/openai/images/generations';
const payload = {
  prompt: 'YOUR_PROMPT',
  model: 'test/test'
};

const response = await fetch(url, {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify(payload)
});

const data = await response.json();
console.log(data);

Python

import requests

url = "https://api.imagerouter.io/v1/openai/images/generations"
payload = {
  "prompt": "YOUR_PROMPT",
  "model": "test/test"
}
headers = {
  "Authorization": "Bearer YOUR_API_KEY"
}

response = requests.post(url, json=payload, headers=headers)
print(response.json())

Chat completion (text) example:

Curl

curl 'https://api.imagerouter.io/v1/openai/chat/completions' \
-H 'Authorization: Bearer YOUR_API_KEY' \
--json '{
  "model": "openai/gpt-4o-mini",
  "messages": [{ "role": "user", "content": "Hello!" }]
}'

Javascript

import OpenAI from 'openai';

const client = new OpenAI({
apiKey: 'YOUR_API_KEY',
baseURL: 'https://api.imagerouter.io/v1/openai',
});

const completion = await client.chat.completions.create({
model: 'openai/gpt-4o-mini',
messages: [{ role: 'user', content: 'Hello!' }],
});

console.log(completion.choices[0].message.content);

Python

from openai import OpenAI

client = OpenAI(
  api_key="YOUR_API_KEY",
  base_url="https://api.imagerouter.io/v1/openai",
)

completion = client.chat.completions.create(
  model="openai/gpt-4o-mini",
  messages=[{"role": "user", "content": "Hello!"}],
)

print(completion.choices[0].message.content)

Detailed API Reference:

• Image generation
• Text to video
• Image to Video
• Chat completions (text)
• Responses (text)

For AI agents

Machine-readable resources for coding agents and LLMs. Note the endpoint path is /v1/openai/... (not the bare OpenAI /v1/... path), and model IDs should be read from the models API rather than guessed.

• llms.txt — index of all docs and API resources
• SKILL.md — curl-based quick-start skill file
• OpenAPI spec — full machine-readable API description