cerebras.ai

Cerebras provides cloud AI inference services and dedicated model endpoints on its wafer-scale compute platform. Its cloud console lets users create API keys, manage projects, and deploy or monitor inference workloads.

3 integrations · REST · CLI

Cerebras exposes a bearer-authenticated HTTP inference API at `https://api.cerebras.ai/v1`, a public unauthenticated models endpoint, and an npm-distributed `cerebras-mcp` CLI for its Code MCP integration; dedicated endpoint management uses a separate Management API key.

discovered 2mo ago

REST · OpenAPI2

Cerebras Inference APIdiscoveredrest
Cerebras Public Models endpointdiscoveredrest

CLI1

Cerebras Code MCP CLIdiscoveredcerebras-mcp

Credentials

Cerebras Management API keyapi_keyGet key ↗

Sign in to the Cerebras Cloud Console. For dedicated endpoints, find the separate key under Management API keys on the API keys page, as described in the Management API docs. Access is in private preview; the docs say to contact Cerebras or your account representative for access.

conventions · 0/7 published

integrations.json——
llms.txt✗/llms.txt
API catalog✗/.well-known/api-catalog
OpenAPI document✗/api/schema/, /openapi.json, /swagger.json, /api/openapi.json, or /v1/openapi.json
MCP server card✗/.well-known/mcp/server-card.json
OAuth protected resource✗/.well-known/oauth-protected-resource
Agent card✗/.well-known/agent-card.json
Agent skills✗/.well-known/agent-skills/index.json

Publish these signals → /publishing