API keys
Create API keys
Log in to your innoGPT account
Go to Settings → API Keys
Click on Create API Key
Enter a meaningful name (e.g., "Backend-Prod," "CI-Pipeline")
Set a monthly limit (see below — important!)
Optional: Configure the IP allowlist
Copy the key immediately — it will only be displayed once
Use the API key
In every request in the Authorization header:
Authorization: Bearer sk_live_************************ Example:
curl -X POST \ -H "Authorization: Bearer sk_live_dein_key" \ -H "Content-Type: application/json" \ https://app.innogpt.de/api/ext/v1/chat/completions \ -d '{ "model": "gpt-5", "messages": [{"role": "user", "content": "Hallo!"}] }' ⚠️ Important: Always set a limit for your API key
When creating a new API key, be sure to define a monthly usage limit. This protects you from:
Accidental overuse — e.g., if a script gets stuck in an infinite loop
Misuse if the key is compromised — in case your key ends up in a public repo
Uncontrolled costs due to premium models in long sessions
Here’s how to set the limit:
When creating → Fill in the "Monthly Limit" field
Later → Settings → API Keys → 3-dot menu → Edit Limit
Note: Currently, you must contact innoGPT support to increase your API limit.
Security Best Practices
Keep keys secret
❌ Never commit API keys to Git
✅ Use environment variables (
.envfile in.gitignore)✅ Rotate keys regularly (recommended every 90 days)
✅ Use separate keys for development and production
Key rotation
Via the API endpoint:
curl -X POST \ -H "Authorization: Bearer $OLD_KEY" \ https://app.innogpt.de/api/ext/v1/api-keys/rotate Or in the account: Settings → API Keys → 3-dot menu → Rotate Key.
IP allowlists
For added security: Restrict API key usage to specific IP addresses.
Go to Settings → API Keys
Select the key → Edit
Add allowed IP addresses or CIDR ranges
Save
Requests from unauthorized IPs will be rejected with a 403 Forbidden error.
Rate Limits
Each API key has configurable limits:
Limits are specified in the response headers:
X-RateLimit-Limit: 100 X-RateLimit-Remaining: 95 X-RateLimit-Reset: 1699999999 Error responses
Invalid API key (401)
{ "error": { "message": "Invalid API key provided", "type": "authentication_error", "code": "invalid_api_key" } } Missing API key (401)
{ "error": { "message": "No API key provided", "type": "authentication_error", "code": "missing_api_key" } } IP not allowed (403)
{ "error": { "message": "Request IP not in allowlist", "type": "authentication_error", "code": "ip_not_allowed" } } Team API access
API keys are team-specific. Requirements:
✅ Active subscription with API access
✅ At least one API key created
✅ Sufficient budget (if limits are set)
Contact your workspace admin if you don’t have access yet.
Was this helpful?
More in API
innoGPT API - Introduction & QuickstartAPI integration with n8nFunction calling & tool integration with the innoGPT APIStill need help? Ask the team