CentML · Pricing Plans

Centml Plans Pricing

CentML uses a credit-based, pay-as-you-go pricing model where 1 CentML credit equals 1 USD. Serverless endpoints are billed by the total number of input and output tokens processed, with per-token rates that vary by model. Dedicated deployments (dedicated inference / compute endpoints) are billed by the type and duration of GPU hardware used, on a per-minute basis (commonly expressed as a per-GPU-hour rate). Enterprise plans with custom commitments are available by contacting CentML. Specific per-model token rates and per-GPU-hour rates are not reconciled in this artifact and should be confirmed on the CentML pricing page.

Centml Plans Pricing is the machine-readable pricing-plan profile for CentML on the APIs.io network, conforming to the API Commons Plans specification.

It defines 3 plans, covering usage and enterprise tiers, with named plans including Serverless Endpoints, Dedicated Deployments, Enterprise.

Tagged areas include AI, LLM, Inference, Serverless, and GPU.

3 Plans API Commons Plans
View Source
AILLMInferenceServerlessGPUPlans

Plans

Serverless Endpoints usage

OpenAI-compatible serverless inference billed by tokens processed. No infrastructure to manage; per-token rates vary by model.

Serverless Input Tokens (tokens · month) per-1M-token rate varies by model (see CentML pricing page) USD
Serverless Output Tokens (tokens · month) per-1M-token rate varies by model (see CentML pricing page) USD
Dedicated Deployments usage

Dedicated, autoscaling inference / compute endpoints billed by GPU hardware type and duration on a per-minute basis (per-GPU-hour equivalent).

Dedicated GPU Hours (gpu_hours · month) per-GPU-hour rate varies by hardware instance (A100, H100, L4, etc.) USD
Enterprise enterprise

Custom plans for larger-scale or specialized deployments, including volume commitments and dedicated support. Contact CentML sales.

Enterprise Agreement (contract · year) contact sales USD

Sources