Free · No signup · Local dev

Mock LLM APIs
for your tests.

Tenant-scoped OpenAI and Anthropic-compatible endpoints, chaos injection, and MCP support. No API key. No rate limits. Just HTTP.

01

Pick a tenant

Each tenant has its own mock state and scenario library. Pass X-Tenant-ID in every request.

02

Send a message

Use /v1/chat/completions (OpenAI) or /v1/messages (Anthropic), or send MCP JSON-RPC to /mcp/message.

03

Get mock data

Responses stream token-by-token from a scenario matched by keyword. Inject chaos to simulate errors or latency.

Editor integration

Let your AI agent manage scenarios

Connect Claude Code, Cursor, or any MCP-compatible editor to your tenant. Your agent can create draft scenarios — you review and approve before they go live.

1

Get an API token from Playground → API Tokens.

2

Add the MCP server to your editor config.

3

Your agent calls create_scenario — drafts appear in the Scenarios tab for your review.

.claude/settings.json
{
  "mcpServers": {
    "llmplaceholder": {
      "type": "http",
      "url": "https://llmplaceholder.com/mcp/message",
      "headers": {
        "X-Tenant-ID": "my-tenant",
        "Authorization": "Bearer <api-token>"
      }
    }
  }
}
Docs

Routes & Guide

Full endpoint reference for LLM, MCP, admin, and chaos APIs — plus quick-start code samples.

View routes →
Tool

Playground

Interactive dashboard — manage tenants, scenarios, MCP tools, chaos profiles, and fire live requests.

Open playground →