Skip to main content
The VLM Run Gateway applies per-tier rate limits on POST /v1/openai/chat/completions. Limits are enforced in memory; when you exceed a bucket, the API returns 429 Too Many Requests. See Authentication for how tiers are determined.

​
Limits by Tier

TierHow it is identifiedRate limitBucket key
AnonymousNo Authorization header, or Bearer "" / Bearer vlmrun60 requests/min, 1000 requests/hrClient IP
AuthenticatedValid VLM Run API key (Authorization: Bearer <VLMRUN_API_KEY>)60 requests/min, 1000 requests/hrUser ID
Anonymous and authenticated users share the same numeric limits today. The difference is how traffic is attributed: anonymous requests are capped per IP, while authenticated requests are capped per user account.
Sign up at app.vlm.run for a free API key. An API key lets you attribute usage to your account and avoids sharing a rate limit bucket with other users on the same IP.
When a limit is exceeded, the Gateway returns HTTP 429. See Error Codes for the response body and handling guidance.

​
Tips

  • Back off and retry after a short delay when you receive a 429.
  • Prefer URL-based document inputs over large base64 payloads to keep request latency predictable under load.
  • For production document workloads, use an authenticated API key so limits apply to your account rather than a shared IP bucket.
If you need higher limits, contact support@vlm.run.