Nscale website screenshot

Nscale

Nscale is an AI/GPU cloud that pairs serverless, OpenAI-compatible inference with on-demand GPU compute. The Serverless Inference API serves open models (Llama, Qwen, DeepSeek, GPT OSS, Mistral, Flux) at https://inference.api.nscale.com/v1 with pay-per-token billing, while the platform API provisions GPU clusters, compute instances, networks, and storage.

Nscale publishes 5 APIs on the APIs.io network, including Chat API, Completions API, Embeddings API, and 2 more. Tagged areas include Artificial Intelligence, GPU, Inference, Serverless, and Cloud Compute.

The Nscale catalog on APIs.io includes 1 event-driven AsyncAPI specification and 1 Spectral governance ruleset.

Nscale’s developer surface includes authentication, engineering blog, documentation, and 7 more developer resources.

🌐 Visit website 📡 Source on GitHub
42.1/100 developing ▬ flat Agent 30/100 agent aware Full breakdown ↓
scored 2026-08-20 · rubric v0.12.0
AccessPaidSelf serve
5 APIs
Artificial IntelligenceGPUInferenceServerlessCloud Compute

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-08-20 · rubric v0.12.0
Composite quality — 42.1/100 · developing
Contract Quality 16.6 / 25
Developer Ergonomics 4.8 / 20
Access Clarity 7.9 / 20
Operational Transparency 4.1 / 13
Contract Governance 1.4 / 12
Discoverability 7.4 / 10
Agent readiness — 30/100 · agent aware
Machine-Readable Contract 18 / 18
Agentic Access Contract 10 / 10
Documented Reversibility 0 / 6
MCP Server 0 / 12
Machine-Readable Auth 10 / 10
Idempotency 0 / 9
Stable Error Semantics 0 / 8
Request/Response Examples 0 / 7
Rate-Limit Signaling 7 / 7
Typed Event Surface 6 / 6
Agent Skills 0 / 5
Well-Known Catalog 0 / 4
Consent & Bot Identity 0 / 3
A2A Agent Card 0 / 8
Dry-Run / Simulate Mode 0 / 4
Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. This rating is computed from github.com/api-evangelist/nscale: open an issue to ask a question, or submit a pull request to add artifacts. Want it done for you? Prioritized profiling — $2,500 →

APIs 5

Individual APIs this provider publishes, each with its own machine-readable definition.

Nscale Chat API

OpenAI-compatible chat completions.

Nscale Completions API

OpenAI-compatible legacy text completions.

Nscale Embeddings API

Vector embeddings of text input.

Nscale Images API

Text-to-image generation.

Nscale Models API

Model catalog discovery.

Open Collections 7

Open, tool-agnostic API collections (OpenAPI-derived and Bruno).

API Collection

OPEN COLLECTION

Nscale Serverless Inference Chat API

OPEN COLLECTION

Nscale Serverless Inference Chat Completions API

OPEN COLLECTION

Nscale Serverless Inference Chat Embeddings API

OPEN COLLECTION

Nscale Serverless Inference Chat Images API

OPEN COLLECTION

Nscale Serverless Inference Chat Models API

OPEN COLLECTION

Nscale Serverless Inference API

OPEN COLLECTION

Scroll for all 7

Pricing Plans 1

Published pricing tiers and plan structures.

Nscale Plans Pricing

3 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Nscale Rate Limits

4 limits

RATE LIMITS

FinOps 1

Cost, billing, and metering signals for API financial operations.

Nscale Finops

FINOPS

Event Specifications 1

AsyncAPI definitions for this provider's event-driven and streaming APIs.

Nscale Chat Completions Streaming (HTTP + SSE)

AsyncAPI 2.6 description of Nscale's **chat completion streaming** surface. Nscale does not publish a WebSocket API. The only asynchronous / event-style transport documented for...

ASYNCAPI

Spectral Rules 1

Spectral governance rulesets for linting and validating these APIs.

Nscale API Rules

5 rules · 1 errors 4 warnings

SPECTRAL

Security Posture 2

Authentication, domain security, vulnerability disclosure, and trust-center signals.

Nscale Authentication

http · 1 scheme

SECURITY

Nscale Domain Security

TLSv1.3 · HSTS · DNSSEC · DMARC

SECURITY

Agentic Access 1

Recommended x-agentic-access execution contracts for AI agents.

Nscale Agentic Access

6 operations · 4 acting

6 operations · 4 acting

AGENTIC

Resources

Documentation 1

Reference material describing how the API behaves

Documentation
Documentation

Agent Surfaces 1

MCP servers, agent skills, and machine-readable catalogs

AgenticAccess
AgenticAccess

Access & Security 2

Authentication, authorization, and security posture

DomainSecurity
DomainSecurity
 Authentication
Authentication

Operate 1

Status, limits, changes, and where to get help

RateLimits
RateLimits

Commercial 2

Pricing, plans, and the legal terms of use

Plans
Plans
 FinOps
FinOps

Company 3

The organization behind the API

Blog
Blog
 LinkedIn
LinkedIn
 Website
Website

Source (apis.yml)

apis.yml Raw ↑ 
aid: nscale
url: https://raw.githubusercontent.com/api-evangelist/nscale/refs/heads/main/apis.yml
name: Nscale
kind: company
description: Nscale is an AI/GPU cloud that pairs serverless, OpenAI-compatible inference with on-demand GPU compute. The
  Serverless Inference API serves open models (Llama, Qwen, DeepSeek, GPT OSS, Mistral, Flux) at https://inference.api.nscale.com/v1
  with pay-per-token billing, while the platform API provisions GPU clusters, compute instances, networks, and storage.
accessModel:
  pricing: paid
  onboarding: self-serve
  trial: false
  try_now: false
  public: false
  label: Paid · Self-serve signup
  confidence: high
  source:
  - plans
  - authentication
  generated: '2026-07-22'
  method: derived
image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/icons/nscale.png
tags:
- Artificial Intelligence
- GPU
- Inference
- Serverless
- Cloud Compute
tags_raw:
- AI
- GPU
- Inference
- Serverless
- Cloud Compute
created: '2026-06-21'
modified: '2026-06-21'
specificationVersion: '0.23'
apis:
- aid: nscale:nscale-chat-api
  name: Nscale Chat API
  description: OpenAI-compatible chat completions.
  humanURL: https://docs.nscale.com/docs/inference/serverless-models/overview
  baseURL: https://inference.api.nscale.com/v1
  tags:
  - Chat
  properties:
  - type: OpenAPI
    url: openapi/nscale-chat-api-openapi.yml
  - type: Documentation
    url: https://docs.nscale.com/docs/inference/serverless-models/overview
  - type: APIReference
    url: https://docs.nscale.com/api-reference
  - type: AsyncAPI
    url: asyncapi/nscale-asyncapi.yml
  - type: Postman
    url: collections/nscale.postman_collection.json
  - type: Documentation
    url: https://docs.nscale.com/docs/compute/overview
- aid: nscale:nscale-completions-api
  name: Nscale Completions API
  description: OpenAI-compatible legacy text completions.
  humanURL: https://docs.nscale.com/docs/inference/serverless-models/overview
  baseURL: https://inference.api.nscale.com/v1
  tags:
  - Completions
  properties:
  - type: OpenAPI
    url: openapi/nscale-completions-api-openapi.yml
  - type: Documentation
    url: https://docs.nscale.com/docs/inference/serverless-models/overview
  - type: APIReference
    url: https://docs.nscale.com/api-reference
  - type: AsyncAPI
    url: asyncapi/nscale-asyncapi.yml
  - type: Postman
    url: collections/nscale.postman_collection.json
  - type: Documentation
    url: https://docs.nscale.com/docs/compute/overview
- aid: nscale:nscale-embeddings-api
  name: Nscale Embeddings API
  description: Vector embeddings of text input.
  humanURL: https://docs.nscale.com/docs/inference/serverless-models/overview
  baseURL: https://inference.api.nscale.com/v1
  tags:
  - Embeddings
  properties:
  - type: OpenAPI
    url: openapi/nscale-embeddings-api-openapi.yml
  - type: Documentation
    url: https://docs.nscale.com/docs/inference/serverless-models/overview
  - type: APIReference
    url: https://docs.nscale.com/api-reference
  - type: AsyncAPI
    url: asyncapi/nscale-asyncapi.yml
  - type: Postman
    url: collections/nscale.postman_collection.json
  - type: Documentation
    url: https://docs.nscale.com/docs/compute/overview
- aid: nscale:nscale-images-api
  name: Nscale Images API
  description: Text-to-image generation.
  humanURL: https://docs.nscale.com/docs/inference/serverless-models/overview
  baseURL: https://inference.api.nscale.com/v1
  tags:
  - Image
  tags_raw:
  - Images
  properties:
  - type: OpenAPI
    url: openapi/nscale-images-api-openapi.yml
  - type: Documentation
    url: https://docs.nscale.com/docs/inference/serverless-models/overview
  - type: APIReference
    url: https://docs.nscale.com/api-reference
  - type: AsyncAPI
    url: asyncapi/nscale-asyncapi.yml
  - type: Postman
    url: collections/nscale.postman_collection.json
  - type: Documentation
    url: https://docs.nscale.com/docs/compute/overview
- aid: nscale:nscale-models-api
  name: Nscale Models API
  description: Model catalog discovery.
  humanURL: https://docs.nscale.com/docs/inference/serverless-models/overview
  baseURL: https://inference.api.nscale.com/v1
  tags:
  - Models
  properties:
  - type: OpenAPI
    url: openapi/nscale-models-api-openapi.yml
  - type: Documentation
    url: https://docs.nscale.com/docs/inference/serverless-models/overview
  - type: APIReference
    url: https://docs.nscale.com/api-reference
  - type: AsyncAPI
    url: asyncapi/nscale-asyncapi.yml
  - type: Postman
    url: collections/nscale.postman_collection.json
  - type: Documentation
    url: https://docs.nscale.com/docs/compute/overview
common:
- type: AgenticAccess
  url: agentic-access/nscale-agentic-access.yml
- type: DomainSecurity
  url: security/nscale-domain-security.yml
- type: Authentication
  url: authentication/nscale-authentication.yml
- url: https://www.nscale.com/blog
  type: Blog
- type: LinkedIn
  url: https://www.linkedin.com/company/nscale
- type: Website
  url: https://www.nscale.com
- type: Documentation
  url: https://docs.nscale.com
- type: Plans
  url: plans/nscale-plans-pricing.yml
- type: RateLimits
  url: rate-limits/nscale-rate-limits.yml
- type: FinOps
  url: finops/nscale-finops.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com