Letta · Rate Limits

Letta Rate Limits

Letta Cloud allows unlimited agents per account. Specific HTTP RPS limits are not publicly documented; Enterprise contracts unlock increased quotas. Self-hosted Letta has no Letta-imposed rate limits (only your infra capacity and downstream LLM provider limits).

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

It captures 2 rate-limit definitions, measuring agents and requests.

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

Tagged areas include AI, Agents, Memory, MemGPT, and Stateful.

2 Limits Throttle: 429
AIAgentsMemoryMemGPTStatefulRate LimitingQuotasThrottling

Limits

Agents account
agents
unlimited
Unlimited agents on API Plan (each active agent billed at $0.10/month).
HTTP Requests account
requests
not publicly documented
Standard 429 backoff applies on Letta Cloud.

Policies

Backoff Strategy
Clients should implement exponential backoff with jitter and honor any Retry-After header.
Self-Host for Bursty Workloads
Run the open-source Letta server on your own infrastructure to avoid Cloud quotas.

Sources