Inference keys

Creating a key

Under Inference API → Keys, choose a project and create a key. The full secret is shown once at creation — copy it immediately into your secret manager. Afterwards only a masked prefix is visible. The same screen shows the base URL to call, https://llm.upgreat.ai/v1, with a link to the LLM quickstart.

curl -X POST https://api.upgreat.ai/v1/projects/{projectId}/inference/keys \
  -H "Authorization: Bearer <access-token>" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "production-backend",
    "rpm": 600,
    "tpm": 200000,
    "token_limit": 5000000,
    "token_limit_period": "month",
    "allowed_models": ["qwen3.8-27b", "bge-m3"]
  }'

Scoping a key

Each key can be constrained so a leak or a runaway job is contained:

• rpm — maximum requests per minute.
• tpm — maximum tokens per minute.
• token_limit with token_limit_period — a hard token budget per minute, hour, day, week or month.
• allowed_models — restrict the key to specific model IDs. Omit to allow every model the project can access.
• expires_at — an optional expiry timestamp, after which the key stops working.

Editing a key

A key's name, model allowlist, limits and expiry can be changed after creation, in the Console (the pencil on an active key) or with PATCH /v1/inference/keys/{keyId}. Changes reach the LLM API within seconds — no redeploy, and the secret in your service stays the same.

curl -X PATCH https://api.upgreat.ai/v1/inference/keys/{keyId} \
  -H "Authorization: Bearer <access-token>" \
  -H "Content-Type: application/json" \
  -d '{
    "rpm": 120,
    "token_limit": 1000000,
    "token_limit_period": "day",
    "allowed_models": ["qwen3.8-27b"],
    "expires_at": null
  }'

• Send only the fields you want to change; anything you omit is left as it is.
• Send null for rpm, tpm, token_limit or expires_at to clear it (unlimited, or no expiry).
• allowed_models: [] re-grants every model the project can access today. A model that was retired after you allowlisted it stays on the key until you remove it.
• expires_at must be in the future. Only active keys can be edited; revoked keys are read-only.

Using a key

Send the key to the LLM API as a bearer token. See the LLM quickstart for full examples.

curl https://llm.upgreat.ai/v1/chat/completions \
  -H "Authorization: Bearer <inference-key>" \
  -H "Content-Type: application/json" \
  -d '{ "model": "qwen3.8-27b", "messages": [{"role": "user", "content": "Hi"}] }'

Rotating and revoking

To rotate, create a new key, deploy it, then revoke the old one with DELETE /v1/inference/keys/{keyId}. Revocation is immediate. A revoked key can be archived to hide it from the default list, and unarchived later if you need its history back.