Tabby · Rate Limits

Tabby Ml Rate Limits

Tabby does not publish fixed numeric API rate limits. Because the server is self-hosted, throughput is bounded by your own hardware - primarily the GPU (or CPU) serving the completion and chat models - rather than by a vendor-imposed per-minute request cap. Completion latency and tokens-per-second depend on the model size and device you configure. On hosted Team and Enterprise plans, capacity is governed by seat count and the managed infrastructure rather than a documented request-rate limit.

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

It captures 4 rate-limit definitions, measuring requests, documents, and users.

The profile also includes 3 backoff/retry policies defined and response codes documented for notImplemented.

Tagged areas include AI Coding Assistant, Code Completion, Open Source, Rate Limiting, and Quotas.

4 Limits
AI Coding AssistantCode CompletionOpen SourceRate LimitingQuotas

Limits

Completion / Chat Throughput deployment
requests
hardware-bound
Constrained by your own GPU/CPU and the configured model, not by TabbyML.
API Request Rate account
requests
not published
No fixed numeric request-rate limit is documented for the server API.
Doc Ingestion deployment
documents
not published
Documents are indexed asynchronously; throughput depends on your indexing resources.
Hosted Seats account
users
per plan
Community up to 5 users; Team up to 50 users; Enterprise unlimited.

Policies

Self-Hosted Scaling
Scale by selecting a larger device/model or running multiple Tabby instances behind a load balancer.
Model Not Configured
Completion and chat endpoints return 501 Not Implemented when their model is not configured, rather than throttling.
Backoff Strategy
Clients should implement exponential backoff with jitter when the server is saturated on constrained hardware.

Sources