Rate Limits

Edge Rate Limits

Rate limits for the Skytells Edge API and streaming endpoints.

Edge Rate Limits

The Edge API (edge.skytells.ai) is designed for low-latency inference and real-time streaming. It operates under separate, more conservative limits to protect the shared edge infrastructure.


Edge vs Standard API

Standard API (api.skytells.ai)Edge API (edge.skytells.ai)
Optimized forBatch workloads, async predictionsLow-latency, streaming output
RPM limitTier-based (25–150+)Tier-based (see below)
Concurrent streamsN/ATier-based per account
Max stream durationN/A300 seconds
Webhooks supportedYesNo — use streaming directly

Streaming Limits

Yes No Yes No Connect to stream Concurrent streams ≤ 3? Stream opened 429 RATE_LIMIT_EXCEEDED Duration ≤ 300s? Data flowing Stream closed by server

Each open stream counts as one concurrent stream slot. Slots are released when the stream closes — either because the prediction completed, was cancelled, or timed out.


Limits by Account Tier

Edge API limits follow the same spend-based tier system as the Standard API, but with more conservative RPM and stream ceilings to protect shared edge infrastructure.

TierMonthly SpendEdge RPMConcurrent Streams
Tier 1$0 – $100102
Tier 2$100 – $500255
Tier 3$500 – $2,0007510
Tier 4$2,000+HigherHigher
EnterprisePer contractCustomCustom

Edge Rate Limit Headers

Every Edge API response includes the same rate limit headers as the Standard API, plus stream-specific headers:

X-RateLimit-Limit-RPM: 30
X-RateLimit-Remaining-RPM: 22
X-RateLimit-Limit-Streams: 3
X-RateLimit-Remaining-Streams: 2
X-RateLimit-Reset: 1741910220

Best Practices for Edge

PracticeWhy
Close streams as soon as output is completeFrees concurrent stream slots immediately
Do not open speculative streamsOnly open a stream when you intend to consume all output
Use the Standard API for non-real-time workloadsReserves edge capacity for latency-sensitive use cases
Handle stream closed gracefullyThe server may close the stream on timeout — always handle end events

How is this guide?

On this page