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
x-docs-platform: mintlify
x-docs-platform-confidence: medium
x-docs-platform-checked: 2026-09-21
x-docs-hosting: vercel
tags:
- Company
- AI Infrastructure
- Artificial Intelligence
- Machine Learning
- Inference
- LLM
- Developer Tools
- Cloud Computing
- Semiconductors
tags_raw:
- Company
- Ai Infrastructure
- Artificial Intelligence
- Machine Learning
- Inference
- Large Language Models
- Developer Tools
- Cloud Computing
- Semiconductors
- Machine-Learning
apis:
- 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
- aid: cerebras-systems:cerebras-systems-chat-completions-api
  name: Cerebras Systems Chat Completions API
  description: The Chat Completions API from Cerebras Systems — 1 operation(s) for chat completions.
  humanURL: https://inference-docs.cerebras.ai
  baseURL: https://api.cerebras.ai
  tags:
  - Chat Completions
  properties:
  - type: OpenAPI
    url: openapi/cerebras-systems-chat-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
maintainers:
- FN: Kin Lane
  email: kin@apievangelist.com
- FN: APIs.json
  email: info@apis.io
common:
- type: CapabilityMap
  url: capabilities/cerebras-systems-capability-edges.yml
  name: Cerebras Systems Business Capability Map
- 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