Lamini Plans Pricing
Lamini offers a self-service, pay-as-you-go tier (Lamini On-Demand) for running inference and tuning jobs on its hosted GPU cluster, plus a custom Enterprise tier for dedicated, reserved, or on-premises deployments. On-Demand bills a flat per-token inference rate and a per-tuning-step rate; new accounts receive free credits to start. Enterprise pricing is negotiated with sales.
Lamini Plans Pricing is the machine-readable pricing-plan profile for Lamini on the APIs.io network, conforming to the API Commons Plans specification.
It defines 2 plans, covering usage and enterprise tiers, with named plans including Lamini On-Demand, Enterprise.
Tagged areas include AI, LLM, Fine-Tuning, Memory Tuning, and Inference.
Plans
Self-service, pay-as-you-go inference and tuning on Lamini's hosted GPU cluster, metered per token and per tuning step, with free starting credit.
- Inference Completions
- Memory Tuning
- Fine-Tuning
- Classify
- Embeddings
Dedicated, reserved-capacity, VPC, or on-premises deployments with volume commitments, security and compliance controls, and dedicated support. Contact Lamini sales.
- Reserved / Dedicated GPU Capacity
- On-Premises Deployment
- Volume Pricing
- Dedicated Support