HAMi · Rate Limits
Hami Rate Limits
Hami Rate Limits is the rate-limit profile for HAMi on the APIs.io network.
The provider publishes no rate limits that could be read; the profile records that absence rather than inventing a ceiling.
Tagged areas include AI Computing, CNCF, GPU Virtualization, Kubernetes, and GPU Sharing.
0 Limits
Transcribed from the provider's documentation on 2026-09-12 — project-hami.io/docs/ (full docs tree via project-hami.io....
View Source
Limits
HAMi publishes no rate limits that could be read; the profile records that absence rather than inventing a ceiling.
No rate limits are published and none are implementable as a vendor policy: both HAMi surfaces are operator-run. The HAMi WebUI API runs inside the customer's own Kubernetes cluster, so any throttling is whatever that operator puts in front of it; the only timeouts declared in the shipped config are server.http.timeout 60s, server.grpc.timeout 60s, prometheus.timeout 1m and exporter.timeout 60s, which are request deadlines, not quotas. The HAMi Website Discovery API is four static documents on Netlify's CDN with no published quota. No X-RateLimit-*, RateLimit-* or Retry-After header was observed on any response fetched during this pass.
AI ComputingCNCFGPU VirtualizationKubernetesGPU SharingSchedulingOpen SourceInfrastructureObservabilityHeterogeneous Computing
Work with this as data
Every rate limit here is available over the APIs.io API and to AI agents over MCP.