LangDB · Rate Limits

Langdb Rate Limits

LangDB enforces project- and user-scoped limits at the gateway. Beyond request/token throughput, it offers cost-based controls: per-user and per-group spend limits, project budgets, and cost groups (available in Business and Enterprise tiers) that throttle or block requests once a configured budget is exceeded. Underlying model providers also enforce their own rate limits, which the gateway surfaces. Specific numeric per-tier limits are not published and are not reconciled in this artifact.

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

It captures 5 rate-limit definitions, measuring requests, tokens, and cost.

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

Tagged areas include AI, LLM, AI Gateway, Routing, and Governance.

5 Limits Throttle: 429
AILLMAI GatewayRoutingGovernanceMCPRate LimitingQuotasThrottling

Limits

Requests Per Minute (RPM) project
requests
see provider documentation
Gateway throughput limit; varies by tier and routed provider.
Tokens Per Minute (TPM) project
tokens
see provider documentation
Aggregate token throughput; also bounded by the underlying provider's limits.
Per-User Spend Limit user
cost
configurable
User-level budget cap (Business / Enterprise); requests blocked when exceeded.
Per-Group Spend Limit group
cost
configurable
Group/team budget cap via cost groups (Business / Enterprise).
Project Budget project
cost
configurable
Project-level spend cap; throttles or blocks once the budget is reached.

Policies

Cost-Based Throttling
Requests can be blocked or throttled when a user, group, or project budget is exceeded.
Provider Limit Pass-Through
Underlying model provider rate limits apply and are surfaced through the gateway.
Backoff Strategy
Clients should implement exponential backoff with jitter and honor Retry-After on 429 responses.

Sources