specification: API Commons Plans
specificationVersion: '0.1'
schema: https://raw.githubusercontent.com/api-evangelist/interface-research/main/schema/api-commons.yml#/$defs/Plans
provider: Nscale
providerId: nscale
created: '2026-06-21'
modified: '2026-06-21'
reconciled: false
tags:
- AI
- GPU
- Inference
- Serverless
- Cloud Compute
- Plans
description: >-
  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.
notes: >-
  Representative serverless rates are published on the Nscale pricing and
  serverless product pages; per-model rates and per-GPU-hour figures change
  frequently and were not all individually confirmed (reconciled false). Verify
  against nscale.com/pricing and the console at reconciliation.
sources:
- https://www.nscale.com/pricing
- https://www.nscale.com/product/serverless
- https://www.nscale.com/product/gpu-nodes
- https://docs.nscale.com
plans:
- id: nscale-serverless-inference
  name: Serverless Inference (Pay-as-you-go)
  type: usage
  description: >-
    Token- and megapixel-metered usage across the OpenAI-compatible serverless
    inference APIs with no monthly minimum.
  entries:
  - label: Text Models (Chat / Completions)
    name: text_tokens
    type: usage
    metric: tokens
    limit: -1
    timeFrame: month
    geo: global
    unit: 1000000
    price: from ~$0.01 input / ~$0.03 output per 1M (varies by model)
    userMultiplied: false
  - label: Large Text Models (e.g. 70B+ / DeepSeek)
    name: large_text_tokens
    type: usage
    metric: tokens
    limit: -1
    timeFrame: month
    geo: global
    unit: 1000000
    price: up to ~$0.20 input / ~$0.60 output per 1M (varies by model)
    userMultiplied: false
  - label: Embeddings
    name: embeddings_tokens
    type: usage
    metric: tokens
    limit: -1
    timeFrame: month
    geo: global
    unit: 1000000
    price: per 1M tokens, see pricing page
    userMultiplied: false
  - label: Image Generation (Flux family)
    name: image_megapixels
    type: usage
    metric: megapixels
    limit: -1
    timeFrame: month
    geo: global
    unit: 1
    price: from ~$0.0013 per megapixel (@4 steps), scales with steps and size
    userMultiplied: false
  elements:
  - name: Chat Completions
  - name: Completions
  - name: Embeddings
  - name: Image Generation
  - name: Models
- id: nscale-gpu-compute
  name: GPU Compute and Clusters
  type: usage
  description: >-
    On-demand GPU instances, nodes, and clusters billed per GPU-hour. Reserved
    capacity and longer commitments are available at reduced rates.
  entries:
  - label: GPU Instance / Node
    name: gpu_hours
    type: usage
    metric: gpu_hours
    limit: -1
    timeFrame: month
    geo: global
    unit: 1
    price: per GPU-hour, varies by accelerator (H100 / B200 / MI300X); see quote
    userMultiplied: false
  elements:
  - name: Compute Instances
  - name: GPU Clusters
  - name: Object Storage
  - name: Networks
- id: nscale-enterprise
  name: Enterprise
  type: enterprise
  description: >-
    Reserved GPU capacity, dedicated clusters, private deployments, volume
    commitments, and negotiated terms. Contact Nscale sales.
  entries:
  - label: Enterprise Agreement
    name: enterprise
    type: flat
    metric: contract
    limit: -1
    timeFrame: year
    geo: global
    unit: 1
    price: contact sales
    userMultiplied: false
  elements:
  - name: Reserved GPU Capacity
  - name: Dedicated Clusters
  - name: Private Deployments
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com