Cerebras website screenshot

Cerebras

Cerebras Systems designs the wafer-scale WSE-3 chip and the CS-2/CS-3 AI systems built around it, and operates Cerebras Inference, a high-throughput cloud platform for running open-source large language models including Llama, Qwen, and DeepSeek families. Cerebras Inference is positioned as one of the fastest token-generation services in the market, with OpenAI-compatible REST endpoints, first-party Python and Node.js SDKs, and dedicated and on-prem deployment options for enterprise customers. The company partners with OpenAI, AWS, GSK, Mayo Clinic, and Notion, and maintains an active open source presence including its model garden and inference cookbook on GitHub.

1 APIs 0 Features
AI InferenceLarge Language ModelsWafer ScaleHardwareCloudOpenAI CompatibleLLMSDKAcceleratorHigh Performance Computing

APIs

Cerebras Inference API

The Cerebras Inference API exposes ultra-low-latency inference for open-weight large language models including Llama 3.1, Llama 4, Qwen, and other frontier open models. The API ...

Collections

Pricing Plans

Cerebras Plans Pricing

1 plans

PLANS

Rate Limits

Cerebras Rate Limits

2 limits

RATE LIMITS

FinOps

Resources

🔗
Website
Website
🔗
Documentation
Documentation
🌐
DeveloperPortal
DeveloperPortal
💰
Pricing
Pricing
👥
GitHubOrganization
GitHubOrganization
🔗
ModelZoo
ModelZoo
📰
Blog
Blog
🔗
LinkedIn
LinkedIn
🔗
Twitter
Twitter
🟢
Status
Status
🔗
LlmsText
LlmsText

Sources

Raw ↑
opencollection: 1.0.0
info:
  name: Cerebras Inference API
  version: 1.0.0
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Chat
    type: folder
  items:
  - info:
      name: Create a chat completion
      type: http
    http:
      method: POST
      url: https://api.cerebras.ai/v1/chat/completions
      body:
        type: json
        data: '{}'
    docs: 'Generates a model response for the given chat conversation. Supports

      streaming via server-sent events and tool/function calling. Drop-in

      compatible with the OpenAI client libraries.

      '
- info:
    name: Completions
    type: folder
  items:
  - info:
      name: Create a text completion
      type: http
    http:
      method: POST
      url: https://api.cerebras.ai/v1/completions
      body:
        type: json
        data: '{}'
    docs: Generates a text completion for the given prompt.
- info:
    name: Models
    type: folder
  items:
  - info:
      name: List available models
      type: http
    http:
      method: GET
      url: https://api.cerebras.ai/v1/models
    docs: Returns an array of models hosted on Cerebras Inference.
bundled: true