Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/cloudwaddie/lmarenabridge/llms.txt

Use this file to discover all available pages before exploring further.

API keys let you authenticate clients that call the bridge’s OpenAI-compatible endpoint. Each key is independent: it has its own name, secret value, rate limit, and usage counter visible in the dashboard. You can create as many keys as you need — one per application, per user, or per environment.

​
How clients use API keys

Clients send the key in the standard Authorization header: 
POST /api/v1/chat/completions HTTP/1.1
Host: localhost:8000
Authorization: Bearer sk-abc123def456
Content-Type: application/json
This is identical to how OpenAI API keys are used, so any OpenAI-compatible client works without modification.

​
Key structure

Each entry in the api_keys array has four fields:
FieldTypeDescription
namestringHuman-readable label shown in the dashboard.
keystringThe secret bearer token. Auto-generated when created via the dashboard.
rpmintegerRequests per minute allowed for this key. Defaults to 60.
createdintegerUnix timestamp (seconds) when the key was created.
The rate limiter uses a rolling 60-second window (RATE_LIMIT_WINDOW_SECONDS = 60). When a key exceeds its rpm limit within that window, the bridge returns 429 Too Many Requests. 
"api_keys": [
    {
        "name": "Production App",
        "key": "sk-abc123def456",
        "rpm": 120,
        "created": 1717200000
    },
    {
        "name": "Dev / Testing",
        "key": "sk-xyz789",
        "rpm": 10,
        "created": 1717200001
    }
]

​
Creating keys

  1. Open the dashboard at http://localhost:8000/dashboard and log in.
  2. Find the API Keys section.
  3. Enter a name for the new key and click Create Key.
  4. The dashboard sends POST /create-key with the name, generates a random key value, and immediately saves it to config.json.
  5. Copy the generated key — it is shown once on creation.
The key value is a securely generated random string. You cannot choose your own value through the dashboard; edit config.json directly if you need a specific value.

​
Deleting keys

  1. Open the API Keys section in the dashboard.
  2. Click Delete next to the key you want to remove.
  3. The dashboard sends POST /delete-key and the entry is removed from config.json immediately.

​
Rotating keys

There is no built-in rotation endpoint. To rotate a key:
  1. Create a new key via the dashboard or config.json.
  2. Update your clients to use the new key.
  3. Delete the old key once traffic has migrated.

​
Rate limits

Each key enforces its own request rate independently. The default limit is 60 requests per minute, controlled by two constants in the bridge: 
DEFAULT_RATE_LIMIT_RPM = 60        # default rpm for new keys
RATE_LIMIT_WINDOW_SECONDS = 60     # rolling window length
To change the rate limit for a specific key, either edit the rpm field in config.json or use the dashboard. Changes take effect on the next request without a server restart.
Setting rpm to 0 effectively blocks the key. Make sure to set a positive integer value for any key you intend to use.

​
Usage statistics

Per-key request counts are stored in the usage_stats field of config.json and are visible in the dashboard. The dashboard shows the total request count and top models used per key. To reset counters, set "usage_stats": {} in config.json while the server is stopped, then restart.

Build docs developers (and LLMs) love

Get started for freeTalk to us