Livepeer · Rate Limits

Livepeer Com Rate Limits

Documented and observed rate-limit surface for Livepeer Studio's REST API and Livepeer AI Network gateways. Studio does not publish a fixed per-key RPS in its API reference; tier-based limits apply on top of plan minimums.

Livepeer Com Rate Limits is the machine-readable rate-limit profile for Livepeer on the APIs.io network, conforming to the API Commons Rate Limits specification.

It captures 8 rate-limit definitions, measuring concurrent_viewers, requests_per_second, bytes, requests_per_minute, and concurrent_predictions.

The profile also includes response codes documented for throttled and unauthorized.

Tagged areas include Rate Limiting, Video Streaming, and AI Inference.

8 Limits Throttle: 429
Rate LimitingVideo StreamingAI Inference

Limits

Studio concurrent viewers (Sandbox) account
concurrent_viewers · instant
30
Studio concurrent viewers (Growth) account
concurrent_viewers · instant
50000
Studio concurrent viewers (Enterprise) account
concurrent_viewers · instant
-1
Unlimited subject to capacity planning.
Studio API requests per key (default) api-key
requests_per_second · second
100
Soft default; tier and use case may raise/lower this on request.
Asset direct upload size request
bytes · request
10737418240
10 GB hard cap per direct upload; use multipart for larger.
AI Gateway predictions (community gateway) ip
requests_per_minute · minute
60
dream-gateway.livepeer.cloud applies fair-use throttling per source IP.
AI Gateway predictions (Studio beta) api-key
concurrent_predictions · instant
4
Per-key concurrent AI prediction soft cap on Studio /api/beta/generate.
Webhook delivery retry budget webhook
retries · hour
5
Failed deliveries retried with exponential backoff up to 5 attempts.

Sources