Literal AI · Rate Limits

Literalai Rate Limits

Literal AI meters API usage primarily through monthly "Log Units" of ingestion that vary by plan, plus data-retention windows and seat counts. The GraphQL endpoint and OTEL ingestion path are also subject to per-account request throttling to protect the platform. Specific request thresholds and Log Unit conversions are not published as fixed numbers and are not reconciled in this artifact.

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

It captures 5 rate-limit definitions, measuring log_units, days, seats, requests, and spans.

The profile also includes 2 backoff/retry policies defined and response codes documented for throttled.

Tagged areas include AI, LLM, Observability, Evaluation, and Monitoring.

5 Limits Throttle: 429
AILLMObservabilityEvaluationMonitoringRate LimitingQuotasThrottling

Limits

Log Units (Monthly Ingestion) account
log_units
see provider documentation
Primary metering unit; 10,000/month on Basic, higher on Pro/Enterprise.
Data Retention account
days
see provider documentation
30 days on Basic; extended on paid tiers.
Team Members (Seats) account
seats
see provider documentation
Up to 3 on Basic; more on Pro/Enterprise.
GraphQL Requests account
requests
see provider documentation
Per-account throttling on the /api/graphql endpoint.
OTEL Ingestion account
spans
see provider documentation
OpenTelemetry (OTLP) trace ingestion counts toward Log Unit usage.

Policies

Tiered Limits
Log Unit quotas, retention, and seats increase from Basic to Pro to Enterprise.
Backoff Strategy
Clients should implement exponential backoff with jitter and honor Retry-After on 429 responses.

Sources