Nscale · Pricing Plans

Nscale Plans Pricing

Nscale uses pay-as-you-go pricing. Serverless inference text models are billed per 1M tokens (input and output) and image models per megapixel based on resolution and diffusion steps. GPU compute (clusters, nodes, instances) is billed per GPU-hour, with reserved and enterprise commitments available via sales. New accounts receive a small free inference credit.

Nscale Plans Pricing is the machine-readable pricing-plan profile for Nscale 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 Inference (Pay-as-you-go), GPU Compute and Clusters, Enterprise.

Tagged areas include AI, GPU, Inference, Serverless, and Cloud Compute.

3 Plans API Commons Plans
View Source
AIGPUInferenceServerlessCloud ComputePlans

Plans

Serverless Inference (Pay-as-you-go) usage

Token- and megapixel-metered usage across the OpenAI-compatible serverless inference APIs with no monthly minimum.

Text Models (Chat / Completions) (tokens · month) from ~$0.01 input / ~$0.03 output per 1M (varies by model) USD
Large Text Models (e.g. 70B+ / DeepSeek) (tokens · month) up to ~$0.20 input / ~$0.60 output per 1M (varies by model) USD
Embeddings (tokens · month) per 1M tokens, see pricing page USD
Image Generation (Flux family) (megapixels · month) from ~$0.0013 per megapixel (@4 steps), scales with steps and size USD
GPU Compute and Clusters usage

On-demand GPU instances, nodes, and clusters billed per GPU-hour. Reserved capacity and longer commitments are available at reduced rates.

GPU Instance / Node (gpu_hours · month) per GPU-hour, varies by accelerator (H100 / B200 / MI300X); see quote USD
Enterprise enterprise

Reserved GPU capacity, dedicated clusters, private deployments, volume commitments, and negotiated terms. Contact Nscale sales.

Enterprise Agreement (contract · year) contact sales USD

Sources