GMI Cloud · Rate Limits
Gmi Cloud Rate Limits
Organization-level limits: TPM for LLM models, RPH for video models (RPH values not published). Tiers auto-upgrade on credit purchase: Tier 2 $50, Tier 3 $500, Tier 4 $1000; 429 on excess.
Gmi Cloud Rate Limits is the machine-readable rate-limit profile for GMI Cloud on the APIs.io network, in the API Commons Rate Limits shape.
It captures 5 rate-limit definitions.
Tagged areas include Company, Artificial Intelligence, Inference, GPU Cloud, and LLM.
5 Limits
Transcribed from the provider's documentation on 2026-10-13 — docs.gmicloud.ai/inference-engine/api-reference/rate-limi....
View Source
CompanyArtificial IntelligenceInferenceGPU CloudLLMModel RoutingSandboxInfrastructure
Limits
Tier 1 TPM (all models) organization
Tier 2 TPM (all models) organization
Tier 3 TPM (all models) organization
Tier 4 TPM (all models) organization
Tier 5 TPM (all models) organization
Work with this as data
Every rate limit here is available over the APIs.io API and to AI agents over MCP.