Poolside · Rate Limits

Poolside Ai Rate Limits

Poolside publishes no numeric public rate limits for its OpenAI-compatible API or its Identity Management / SCIM API. That is consistent with the product: each API only exists inside a customer's own Poolside deployment (Cloud VPC or on-prem/air-gapped), so throughput is bounded by the compute the customer provisions - either Poolside's pre-provisioned hardware (sized for "hundreds of developers" per node) or the customer's own NVIDIA GPU cluster - rather than by a shared multi-tenant quota Poolside enforces centrally.

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

It captures 3 rate-limit definitions, measuring requests and keys.

Tagged areas include AI, Foundation Models, Enterprise, On-Prem, and Rate Limiting.

3 Limits
AIFoundation ModelsEnterpriseOn-PremRate Limiting

Limits

Chat / Completions Throughput deployment
requests
hardware-bound (sized per deployment; not published)
Governed by the GPU capacity provisioned for the customer's deployment, not a Poolside-enforced quota.
Identity Management / SCIM API Requests account
requests
not published
No fixed numeric limit documented for /poolside/v1 or /scim endpoints.
API Keys per Tenant account
keys
not published
Developer keys are self-issued per user with deployment access; service-account keys require the tenant-admin role.

Sources