Cerebras Systems

Cerebras Systems builds the Wafer-Scale Engine (WSE) — the largest computer chip ever made — and the CS-3 systems built around it, delivering AI training and inference at speeds far beyond conventional GPUs. Cerebras Inference is the company's cloud API: an OpenAI-compatible REST interface at api.cerebras.ai that serves open-weight frontier models (OpenAI GPT-OSS, Gemma 4, Z.ai GLM 4.7) at industry-leading tokens-per-second. Developers authenticate with a bearer API key and call chat/completions, completions, and models endpoints, with streaming, tool calling, structured outputs, vision, prompt caching, and batch inference. Custom model weights can be deployed on dedicated endpoints. Official Python and Node.js SDKs, a Cloud Console with a playground, and coding-tool integrations (VS Code, Cline, Kilo Code, OpenCode) round out the developer surface.

Cerebras Systems publishes 5 APIs on the APIs.io network, including Chat API, Completions API, Models API, and 2 more. Tagged areas include Company, AI Infrastructure, Artificial Intelligence, Machine-Learning, and Inference.

Cerebras Systems’ developer surface includes status page, documentation, API reference, getting-started guide, support, engineering blog, pricing, and 38 more developer resources.

🌐 Visit website 📡 Source on GitHub

61.1/100 strong ▬ flat Agent 29/100 agent ready saas Full breakdown ↓
scored 2026-09-06 · rubric v0.19.0

AccessFreemiumSelf serveFree trial⚡ Free to try

2 APIs

Company AI Infrastructure Artificial Intelligence Machine-Learning Inference Large Language Models Developer Tools Cloud Computing Semiconductors

Kin Score

Kin Score How this is scored →
scored 2026-09-06 · rubric v0.19.0

Composite quality — 61.1/100 · strong

Contract Quality 13.3 / 25

Developer Ergonomics 14.4 / 20

Access Clarity 18.4 / 20

Operational Transparency 6.8 / 13

Contract Governance 0.5 / 12

Discoverability 7.6 / 10

Agent readiness — 29/100 · agent ready

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 8 / 8

Request/Response Examples 7 / 7

Rate-Limit Signaling 7 / 7

Typed Event Surface 0 / 6

Agent Skills 5 / 5

Well-Known Catalog 0 / 4

Consent & Bot Identity 0 / 3

A2A Agent Card 0 / 8

Dry-Run / Simulate Mode 0 / 4

Delegated User Identity 0 / 6

Protected Resource Metadata 0 / 5

Registration Without a Human 0 / 6

Agentic Commerce Well-Known Document 0 / 5

Improve this rating by publishing the missing artifacts — every area above can be raised, and the full rubric is at apis.io/rating/. Every facet and dimension name above is a link: it opens that measurement's own page — what it means, the exact checks that feed it, how the whole catalog distributes on it, and the providers at the top of it. This rating is computed from github.com/api-evangelist/cerebras-systems: open an issue to ask a question, or submit a pull request to add artifacts. Submit an artifact on GitHub — free → Manage your own listing — the Influence plan, $499/mo →

APIs 5

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

Rate Limits 1

Documented rate limits and quota policies.

Get Started 4

Portal, sign-up, and the first successful call

DeveloperPortal

DeveloperPortal

GettingStarted

GettingStarted

SignUp

SignUp

Login

Documentation 2

Reference material describing how the API behaves

Documentation

Documentation

APIReference

APIReference

Agent Surfaces 5

MCP servers, agent skills, and machine-readable catalogs

LlmsText

LlmsText

LLMsTxt

LLMsTxt

X-MCPServerCandidate

X-MCPServerCandidate

AgenticAccess

AgenticAccess

AgentSkill

AgentSkill

Design & Contract 5

Pagination, idempotency, versioning, errors, and events

Conventions

ErrorCatalog

Conformance

Lifecycle

DataModel

Build 6

SDKs, sample code, and the tooling you integrate with

PostmanWorkspace

PostmanWorkspace

GitHubOrganization

Packages

SDKs

Python SDK

Node.js SDK

Access & Security 6

Authentication, authorization, and security posture

TrustCenter

TrustCenter

Compliance

Security

Authentication

DomainSecurity

Operate 7

Status, limits, changes, and where to get help

Status

Support

StatusPage

ChangeLog

Deprecation

RateLimits

ChangeLog

Scroll for all 7

Commercial 4

Pricing, plans, and the legal terms of use

Pricing

TermsOfService

PrivacyPolicy

Plans

Company 4

The organization behind the API

LinkedIn

Twitter

Twitter

Website

Website

Blog

Blog

Other 2

Properties that don't map to a standard resource type

ModelZoo

ModelZoo

Overlay

Overlay

Source (apis.yml)

aid: cerebras-systems
name: Cerebras Systems
description: 'Cerebras Systems builds the Wafer-Scale Engine (WSE) — the largest computer chip ever made — and the CS-3 systems
  built around it, delivering AI training and inference at speeds far beyond conventional GPUs. Cerebras Inference is the
  company''s cloud API: an OpenAI-compatible REST interface at api.cerebras.ai that serves open-weight frontier models (OpenAI
  GPT-OSS, Gemma 4, Z.ai GLM 4.7) at industry-leading tokens-per-second. Developers authenticate with a bearer API key and
  call chat/completions, completions, and models endpoints, with streaming, tool calling, structured outputs, vision, prompt
  caching, and batch inference. Custom model weights can be deployed on dedicated endpoints. Official Python and Node.js SDKs,
  a Cloud Console with a playground, and coding-tool integrations (VS Code, Cline, Kilo Code, OpenCode) round out the developer
  surface.'
url: https://raw.githubusercontent.com/api-evangelist/cerebras-systems/refs/heads/main/apis.yml
x-type: company
x-source: vc-portfolio
x-backed-by:
- coatue
x-tier: stub
x-tier-reason: portfolio-lead
deliveryModel:
  model: saas
  open_source: false
  commercial: true
  callable_host: true
  label: Hosted service · you call their endpoint
  confidence: high
  source:
  - openapi
  - pricing
  generated: '2026-08-28'
  method: derived
accessModel:
  pricing: freemium
  onboarding: self-serve
  trial: true
  try_now: true
  public: false
  label: Freemium (free trial) · Self-serve signup
  confidence: high
  source:
  - plans
  - authentication
  - rate-limits
  - security
  generated: '2026-09-03'
  method: derived
specificationVersion: '0.23'
created: '2026-07-17'
modified: '2026-07-18'
image: https://github.com/Cerebras.png
tags:
- Company
- AI Infrastructure
- Artificial Intelligence
- Machine-Learning
- Inference
- Large Language Models
- Developer Tools
- Cloud Computing
- Semiconductors
tags_raw:
- Company
- Ai Infrastructure
- Artificial Intelligence
- Machine Learning
- Inference
- Large Language Models
- Developer Tools
- Cloud Computing
- Semiconductors
apis:
- aid: cerebras-systems:cerebras-systems-chat-api
  name: Cerebras Systems Chat API
  description: The Chat API from Cerebras Systems — 1 operation(s) for chat.
  humanURL: https://inference-docs.cerebras.ai
  baseURL: https://api.cerebras.ai
  tags:
  - Chat
  properties:
  - type: OpenAPI
    url: openapi/cerebras-systems-chat-api-openapi.yml
  - type: APIReference
    url: https://inference-docs.cerebras.ai/api-reference/chat-completions
  - type: Documentation
    url: https://inference-docs.cerebras.ai
  - type: ErrorCatalog
    url: errors/cerebras-systems-problem-types.yml
  - type: Authentication
    url: authentication/cerebras-systems-authentication.yml
  - type: Conventions
    url: conventions/cerebras-systems-conventions.yml
  - type: DataModel
    url: data-model/cerebras-systems-data-model.yml
- aid: cerebras-systems:cerebras-systems-completions-api
  name: Cerebras Systems Completions API
  description: The Completions API from Cerebras Systems — 1 operation(s) for completions.
  humanURL: https://inference-docs.cerebras.ai
  baseURL: https://api.cerebras.ai
  tags:
  - Completions
  properties:
  - type: OpenAPI
    url: openapi/cerebras-systems-completions-api-openapi.yml
  - type: APIReference
    url: https://inference-docs.cerebras.ai/api-reference/chat-completions
  - type: Documentation
    url: https://inference-docs.cerebras.ai
  - type: ErrorCatalog
    url: errors/cerebras-systems-problem-types.yml
  - type: Authentication
    url: authentication/cerebras-systems-authentication.yml
  - type: Conventions
    url: conventions/cerebras-systems-conventions.yml
  - type: DataModel
    url: data-model/cerebras-systems-data-model.yml
- aid: cerebras-systems:cerebras-systems-models-api
  name: Cerebras Systems Models API
  description: The Models API from Cerebras Systems — 2 operation(s) for models.
  humanURL: https://inference-docs.cerebras.ai
  baseURL: https://api.cerebras.ai
  tags:
  - Models
  properties:
  - type: OpenAPI
    url: openapi/cerebras-systems-models-api-openapi.yml
  - type: APIReference
    url: https://inference-docs.cerebras.ai/api-reference/chat-completions
  - type: Documentation
    url: https://inference-docs.cerebras.ai
  - type: ErrorCatalog
    url: errors/cerebras-systems-problem-types.yml
  - type: Authentication
    url: authentication/cerebras-systems-authentication.yml
  - type: Conventions
    url: conventions/cerebras-systems-conventions.yml
  - type: DataModel
    url: data-model/cerebras-systems-data-model.yml
- aid: cerebras-systems:cerebras-systems-public-models-api
  name: Cerebras Systems Public Models API
  description: The Public Models API from Cerebras Systems — 2 operation(s) for public models.
  humanURL: https://inference-docs.cerebras.ai
  baseURL: https://api.cerebras.ai
  tags:
  - Public Models
  properties:
  - type: OpenAPI
    url: openapi/cerebras-systems-public-models-api-openapi.yml
  - type: APIReference
    url: https://inference-docs.cerebras.ai/api-reference/chat-completions
  - type: Documentation
    url: https://inference-docs.cerebras.ai
  - type: ErrorCatalog
    url: errors/cerebras-systems-problem-types.yml
  - type: Authentication
    url: authentication/cerebras-systems-authentication.yml
  - type: Conventions
    url: conventions/cerebras-systems-conventions.yml
  - type: DataModel
    url: data-model/cerebras-systems-data-model.yml
- aid: cerebras-systems:cerebras-systems-tcp-warming-api
  name: Cerebras Systems Tcp Warming API
  description: The Tcp Warming API from Cerebras Systems — 1 operation(s) for tcp warming.
  humanURL: https://inference-docs.cerebras.ai
  baseURL: https://api.cerebras.ai
  tags:
  - Tcp Warming
  properties:
  - type: OpenAPI
    url: openapi/cerebras-systems-tcp-warming-api-openapi.yml
  - type: APIReference
    url: https://inference-docs.cerebras.ai/api-reference/chat-completions
  - type: Documentation
    url: https://inference-docs.cerebras.ai
  - type: ErrorCatalog
    url: errors/cerebras-systems-problem-types.yml
  - type: Authentication
    url: authentication/cerebras-systems-authentication.yml
  - type: Conventions
    url: conventions/cerebras-systems-conventions.yml
  - type: DataModel
    url: data-model/cerebras-systems-data-model.yml
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: ModelZoo
  url: https://github.com/Cerebras/modelzoo
- type: LinkedIn
  url: https://www.linkedin.com/company/cerebras-systems
- type: Twitter
  url: https://twitter.com/CerebrasSystems
- type: Status
  url: https://status.cerebras.ai
- type: LlmsText
  url: https://inference-docs.cerebras.ai/llms.txt
- type: PostmanWorkspace
  url: https://www.postman.com/kinlaneapi/cerebras-systems/overview
- type: TrustCenter
  url: security/cerebras-systems-trust-center.yml
- type: Website
  url: https://www.cerebras.ai
- type: DeveloperPortal
  url: https://inference-docs.cerebras.ai
- type: Documentation
  url: https://inference-docs.cerebras.ai
- type: APIReference
  url: https://inference-docs.cerebras.ai/api-reference/chat-completions
- type: GettingStarted
  url: https://inference-docs.cerebras.ai/quickstart
- type: Support
  url: https://inference-docs.cerebras.ai/support/overview
- type: Blog
  url: https://www.cerebras.ai/blog
- type: GitHubOrganization
  url: https://github.com/Cerebras
- type: Pricing
  url: https://www.cerebras.ai/pricing
- type: SignUp
  url: https://cloud.cerebras.ai
- type: Login
  url: https://cloud.cerebras.ai
- type: TermsOfService
  url: https://www.cerebras.ai/terms-of-service
- type: PrivacyPolicy
  url: https://www.cerebras.ai/privacy-policy
- type: StatusPage
  url: https://status.cerebras.ai
- type: TrustCenter
  url: https://trust.cerebras.ai
- type: Compliance
  url: https://trust.cerebras.ai
- type: Security
  url: https://trust.cerebras.ai
- type: ChangeLog
  url: https://inference-docs.cerebras.ai/support/change-log
- type: Deprecation
  url: https://inference-docs.cerebras.ai/support/deprecation
- type: Packages
  url: packages/cerebras-systems-packages.yml
- type: SDKs
  url: packages/cerebras-systems-packages.yml
- type: Python SDK
  url: https://github.com/Cerebras/cerebras-cloud-sdk-python
- type: Node.js SDK
  url: https://github.com/Cerebras/cerebras-cloud-sdk-node
- type: LLMsTxt
  url: llms/cerebras-systems-llms.txt
- type: X-MCPServerCandidate
  url: mcp/cerebras-systems-mcp.yml
  note: 'Renamed from MCPServer 2026-09-03 (roadmap#247): the manifest self-describes as status: candidate — a tool list derived
    from the published API contracts, not an existing server. The scorer already read the manifest and reported mcp_server
    correctly; the MCPServer type was crediting the artifact-type surfaces with a server that does not exist.'
- type: Authentication
  url: authentication/cerebras-systems-authentication.yml
- type: Conventions
  url: conventions/cerebras-systems-conventions.yml
- type: ErrorCatalog
  url: errors/cerebras-systems-problem-types.yml
- type: Conformance
  url: conformance/cerebras-systems-conformance.yml
- type: Lifecycle
  url: lifecycle/cerebras-systems-lifecycle.yml
- type: RateLimits
  url: rate-limits/cerebras-systems-rate-limits.yml
- type: Plans
  url: plans/cerebras-systems-plans.yml
- type: Overlay
  url: overlays/cerebras-systems-inference-overlay.yaml
- type: DataModel
  url: data-model/cerebras-systems-data-model.yml
- type: DomainSecurity
  url: security/cerebras-systems-domain-security.yml
- type: AgenticAccess
  url: agentic-access/cerebras-systems-agentic-access.yml
- type: AgentSkill
  url: skills/_index.yml
- type: ChangeLog
  url: changelog/cerebras-systems-changelog.yml
x-enrichment:
  date: '2026-07-19'
  status: backfilled
  pass: local-v1
  note: backfilled from .gitignore signal + verified work evidence

Work with this as data

Every provider here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for providers

9 MCP tools reach this

find_providersBrowse and filter every provider in the catalog.
get_provider_artifactsEvery artifact this provider publishes, grouped by type.
get_provider_operationsEvery operation across all of their OpenAPIs — one call instead of parsing every spec.
get_provider_toolsEvery MCP tool they ship, with the operation each wraps.
get_provider_evidenceHow each part of their score was established. Free — the basis for a claim should not sit behind it.
get_provider_ratingPRO — composite, band, trend and facet scores.
apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
resolveTurn a domain, URL or GitHub org into the provider it belongs to.
find_cohortsEvery scored population of providers in the catalog.

All 92 tools →

Call it yourself

curl for this page

This provider

curl "https://apis.io/api/v1/providers/cerebras-systems"

All providers

curl "https://apis.io/api/v1/providers?limit=25"

Every operation they expose

curl "https://apis.io/api/v1/providers/cerebras-systems/operations?limit=25"

How their score was established

curl "https://apis.io/api/v1/providers/cerebras-systems/evidence"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no email required.

GitHub Google LinkedIn

A second provider on the same verified email joins the account you already have.