Llamaindex Rate Limits
LlamaIndex / LlamaCloud rate limits are not publicly enumerated as per-second numbers on the pricing page; tiered limits scale with plan and Enterprise gets 5x Pro. Limits are enforced per API key. Detailed per-endpoint throttling is documented inside the LlamaCloud product after sign-in.
Llamaindex Rate Limits is the machine-readable rate-limit profile for Llamaindex on the APIs.io network, conforming to the API Commons Rate Limits specification.
It captures 4 rate-limit definitions, measuring varies.
The profile also includes 3 backoff/retry policies defined and response codes documented for throttled and quotaExceeded.
Tagged areas include Rate Limiting, LLM, and RAG.
Limits
Policies
Sources
Work with this as data
Every rate limit here is available over the APIs.io API and to AI agents over MCP.