Cerebrium

Cerebrium is a serverless GPU infrastructure platform for real-time AI and ML workloads. Developers package code with the Cortex framework and Cerebrium CLI, then deploy each function as an authenticated REST endpoint on autoscaling GPU/CPU compute billed per second, with streaming, WebSocket, async, and OpenAI-compatible invocation patterns.

Cerebrium publishes 2 APIs on the APIs.io network: Inference API and OpenAI Compatible API. Tagged areas include AI, GPU, Serverless, Inference, and ML Infrastructure.

Cerebrium’s developer surface includes authentication, documentation, and 8 more developer resources.

🌐 Visit website 📡 Source on GitHub
39.1/100 thin ▬ flat Agent 31/100 agent aware Full breakdown ↓
scored 2026-07-28 · rubric v0.6
AccessFreemiumSelf serve⚡ Free to try
3 APIs
AIGPUServerlessInferenceML Infrastructure

Kin Score

Kin Score Kin Score How this is scored →
scored 2026-07-28 · rubric v0.6
Composite quality — 39.1/100 · thin
Contract Quality 15.1 / 25
Developer Ergonomics 3.9 / 20
Commercial Clarity 7.9 / 20
Operational Transparency 4.8 / 13
Governance 0.0 / 12
Discoverability 7.4 / 10
Agent readiness — 31/100 · agent aware
Machine-Readable Contract 18 / 18
Agentic Access Contract 10 / 10
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 0 / 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/cerebrium: 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 3

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

Cerebrium Logs / Status API

Surfaces app logs, metrics, and platform status through the CLI (cerebrium logs, cerebrium status), the app dashboard, and the public status page.

Cerebrium Inference API

The Inference API from Cerebrium — 1 operation(s) for inference.

Cerebrium OpenAI Compatible API

The OpenAI Compatible API from Cerebrium — 2 operation(s) for openai compatible.

Open Collections 1

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

Cerebrium Cortex Inference API

OPEN COLLECTION

Pricing Plans 1

Published pricing tiers and plan structures.

Cerebrium Plans Pricing

4 plans

PLANS

Rate Limits 1

Documented rate limits and quota policies.

Cerebrium Rate Limits

4 limits

RATE LIMITS

FinOps 1

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

Cerebrium Finops

FINOPS

Security Posture 2

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

Cerebrium Authentication

http · 1 scheme

SECURITY

Cerebrium Domain Security

TLSv1.3 · HSTS · DMARC

SECURITY

Agentic Access 1

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

Cerebrium Agentic Access

3 operations · 3 acting

3 operations · 3 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

Build 1

SDKs, sample code, and the tooling you integrate with

GitHubOrganization
GitHubOrganization

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 2

The organization behind the API

LinkedIn
LinkedIn
 Website
Website

Source (apis.yml)

apis.yml Raw ↑ 
aid: cerebrium
url: https://raw.githubusercontent.com/api-evangelist/cerebrium/refs/heads/main/apis.yml
name: Cerebrium
kind: company
description: Cerebrium is a serverless GPU infrastructure platform for real-time AI and ML workloads. Developers package code
  with the Cortex framework and Cerebrium CLI, then deploy each function as an authenticated REST endpoint on autoscaling
  GPU/CPU compute billed per second, with streaming, WebSocket, async, and OpenAI-compatible invocation patterns.
accessModel:
  pricing: freemium
  onboarding: self-serve
  trial: false
  try_now: true
  public: false
  label: Freemium · 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/cerebrium.png
tags:
- AI
- GPU
- Serverless
- Inference
- ML Infrastructure
created: '2026-06-20'
modified: '2026-06-20'
specificationVersion: '0.19'
apis:
- aid: cerebrium:cerebrium-logs-status-api
  name: Cerebrium Logs / Status API
  tags:
  - Logs
  - Status
  - Observability
  image: https://kinlane-images.s3.amazonaws.com/shared/apis-json/apis-json-logo.jpg
  humanURL: https://status.cerebrium.ai/
  baseURL: https://api.aws.us-east-1.cerebrium.ai/v4
  properties:
  - url: https://www.cerebrium.ai/docs/cerebrium/getting-started/introduction
    type: Documentation
  - url: https://status.cerebrium.ai/
    type: StatusPage
  description: Surfaces app logs, metrics, and platform status through the CLI (cerebrium logs, cerebrium status), the app
    dashboard, and the public status page.
- aid: cerebrium:cerebrium-inference-api
  name: Cerebrium Inference API
  description: The Inference API from Cerebrium — 1 operation(s) for inference.
  humanURL: https://www.cerebrium.ai/docs/cerebrium/endpoints/inference-api
  baseURL: https://api.aws.us-east-1.cerebrium.ai/v4
  tags:
  - Inference
  properties:
  - type: OpenAPI
    url: openapi/cerebrium-inference-api-openapi.yml
  - type: Documentation
    url: https://www.cerebrium.ai/docs/cerebrium/endpoints/inference-api
  - type: APIReference
    url: https://www.cerebrium.ai/docs/cerebrium/endpoints/inference-api
  - type: PostmanCollection
    url: collections/cerebrium.postman_collection.json
  - type: Documentation
    url: https://www.cerebrium.ai/docs/cerebrium/endpoints/streaming
  - type: Documentation
    url: https://www.cerebrium.ai/docs/cerebrium/endpoints/async
  - type: Documentation
    url: https://www.cerebrium.ai/docs/cerebrium/getting-started/introduction
- aid: cerebrium:cerebrium-openai-compatible-api
  name: Cerebrium OpenAI Compatible API
  description: The OpenAI Compatible API from Cerebrium — 2 operation(s) for openai compatible.
  humanURL: https://www.cerebrium.ai/docs/cerebrium/endpoints/inference-api
  baseURL: https://api.aws.us-east-1.cerebrium.ai/v4
  tags:
  - OpenAI Compatible
  properties:
  - type: OpenAPI
    url: openapi/cerebrium-openai-compatible-api-openapi.yml
  - type: Documentation
    url: https://www.cerebrium.ai/docs/cerebrium/endpoints/inference-api
  - type: APIReference
    url: https://www.cerebrium.ai/docs/cerebrium/endpoints/inference-api
  - type: PostmanCollection
    url: collections/cerebrium.postman_collection.json
  - type: Documentation
    url: https://www.cerebrium.ai/docs/cerebrium/endpoints/streaming
  - type: Documentation
    url: https://www.cerebrium.ai/docs/cerebrium/endpoints/async
  - type: Documentation
    url: https://www.cerebrium.ai/docs/cerebrium/getting-started/introduction
common:
- type: AgenticAccess
  url: agentic-access/cerebrium-agentic-access.yml
- type: DomainSecurity
  url: security/cerebrium-domain-security.yml
- type: Authentication
  url: authentication/cerebrium-authentication.yml
- type: GitHubOrganization
  url: https://github.com/CerebriumAI
- type: LinkedIn
  url: https://www.linkedin.com/company/cerebrium
- type: Website
  url: https://www.cerebrium.ai
- type: Documentation
  url: https://www.cerebrium.ai/docs
- type: Plans
  url: plans/cerebrium-plans-pricing.yml
- type: RateLimits
  url: rate-limits/cerebrium-rate-limits.yml
- type: FinOps
  url: finops/cerebrium-finops.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com