Migrate from OpenRouter¶

IndoxHub uses the same OpenAI-compatible API format as OpenRouter. Switching takes minimal code changes.

What Changes¶

	OpenRouter	IndoxHub
Base URL	`https://openrouter.ai/api/v1`	`https://api.indoxhub.com/api/v1`
Auth Header	`Authorization: Bearer OR_KEY`	`Authorization: Bearer INDOX_KEY`
Model Format	`provider/model`	`provider/model` (same)
Response Format	OpenAI-compatible	OpenAI-compatible + usage/cost

Step 1: Get an IndoxHub API Key¶

Sign up at indoxhub.com and create an API key from the dashboard.

Step 2: Update Your Code¶

OpenAI SDK¶

Change two lines:

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_INDOXHUB_KEY",           # was: OpenRouter key
    base_url="https://api.indoxhub.com/v1"  # was: https://openrouter.ai/api/v1
)

# Everything else stays the same
response = client.chat.completions.create(
    model="openai/gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello!"}]
)

Direct API¶

curl https://api.indoxhub.com/api/v1/chat/completions \
  -H "Authorization: Bearer YOUR_INDOXHUB_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "openai/gpt-4o-mini", "messages": [{"role": "user", "content": "Hello!"}]}'

Step 3: Verify¶

Test with a simple request. The response format is OpenAI-compatible with additional usage fields including cost tracking.

What You Get Extra¶

Built-in cost tracking — every response includes token counts and cost
BYOK support — use your own provider API keys
Video generation — Luma, Google Veo support
Speech endpoints — TTS and STT included

Model Name Compatibility¶

Most model names are identical between OpenRouter and IndoxHub. Use the same provider/model format.

Browse available models: Models