Authentication

OpenModels authenticates API requests with an OpenModels API key in the Authorization header. API keys use the ale-... format.

API key format

ale-your-api-key

Keys are shown once when created. Store them in a secrets manager or environment variable before leaving the creation screen.

Authorization header

Send the key as a Bearer token:

curl https://api.getopenmodels.com/v1/chat/completions \
  -H "Authorization: Bearer $OM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.5-flash",
    "route": { "provider": "<provider-for-this-model>" },
    "route_mode": "balanced",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

Environment variables

Use an environment variable for local development:

export OM_API_KEY="ale-your-api-key"

Then pass it to an OpenAI-compatible SDK:

import os
from openai import OpenAI
client = OpenAI(
    base_url="https://api.getopenmodels.com/v1",
    api_key=os.environ["OM_API_KEY"],
)

Key management

Use separate keys for development, staging, and production. This makes it easier to rotate a key without disrupting every environment.

Recommended practices:

• Store keys in a secrets manager.
• Do not commit keys to source control.
• Rotate a key immediately if it may have leaked.
• Revoke unused keys.
• Use monthly spend limits to cap the maximum spend for each key.
• Use separate keys for different applications or workloads when you need cleaner usage tracking.

Common authentication errors

If a request fails with 401, check that the Authorization header uses the exact Bearer <key> format and that the key still exists in the OpenModels dashboard.

If authentication succeeds but a request is blocked by credits or spend limits, see Credits & Billing, Rate Limits, and Errors.