MockLLM API Documentation

rocket_launchIntroduction

MockLLM provides a drop-in replacement for OpenAI's API that returns deterministic, predictable responses for testing and development. No more burning through API credits while running tests or waiting seconds for responses during local development.

flash_onQuick Start

Get your first mock response in under 2 minutes:

from openai import OpenAI

client = OpenAI(
    base_url="https://api.mockllm.io/v1",
    api_key="your-api-key"
)

response = client.chat.completions.create(
    model: 'claude-opus-4.6',
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

keyAuthentication

All API requests require authentication via Bearer token in the Authorization header.

Header Format

Authorization: Bearer YOUR_API_KEY

Getting an API Key

1. Sign up for a free account at mockllm.io
2. Navigate to your Dashboard
3. Go to Settings → API Keys
4. Click "Generate New Key"
5. Copy and store your key securely (it won't be shown again)

workspace_premiumPricing Tiers

chatChat Completions

OpenAI-compatible endpoint for generating chat completions. Returns deterministic mock responses based on your fixtures or default mocks.

{
  "model": "claude-opus-4.6",
  "messages": [
    {"role": "system", "content": "You are a helpful assistant."},
    {"role": "user", "content": "Hello!"}
  ],
  "temperature": 0.7,
  "max_tokens": 100
}

{
  "id": "chatcmpl-mock-123456",
  "object": "chat.completion",
  "created": 1704067200,
  "model": "claude-opus-4.6",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 9,
    "completion_tokens": 12,
    "total_tokens": 21
  }
}

buildFixtures

Fixtures allow you to define custom response patterns for specific models or inputs. Manage fixtures through the dashboard for the best experience.

{
  "fixtures": [
    {
      "id": "fixture_001",
      "pattern": {"model": "claude-opus-4.6"},
      "response": {
        "id": "chatcmpl-mock-gpt4",
        "object": "chat.completion",
        "choices": [{
          "message": {
            "role": "assistant",
            "content": "Custom GPT-5.3 response!"
          }
        }]
      }
    }
  ],
  "count": 1,
  "user_id": "user_abc...",
  "usage": 42,
  "limit": 1000
}

analyticsAnalytics

Track your API usage with detailed analytics endpoints.

{
  "data": [
    {
      "date": "2024-01-15",
      "count": 42,
      "endpoint_breakdown": {
        "/v1/chat/completions": 35,
        "/fixtures": 7
      }
    },
    {
      "date": "2024-01-16",
      "count": 38,
      "endpoint_breakdown": {
        "/v1/chat/completions": 30,
        "/analytics/summary": 8
      }
    }
  ],
  "granularity": "day",
  "total_records": 80
}

{
  "total_calls_this_month": 156,
  "total_calls_today": 12,
  "avg_response_time_ms": 45.5,
  "most_used_model": "claude-opus-4.6",
  "calls_by_endpoint": {
    "/v1/chat/completions": 140,
    "/fixtures": 16
  }
}

health_and_safetyHealth Check

{
  "status": "healthy",
  "pocketbase": "connected",
  "default_fixtures": 3,
  "version": "1.0.0"
}

codePython SDK

Use the official OpenAI Python library with a custom base URL. No additional dependencies needed.

Installation

pip install openai

Basic Usage

from openai import OpenAI

client = OpenAI(
    base_url="https://api.mockllm.io/v1",
    api_key="your-api-key"
)

response = client.chat.completions.create(
    model: 'claude-opus-4.6',
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

With Async Support

import asyncio
from openai import AsyncOpenAI

client = AsyncOpenAI(
    base_url="https://api.mockllm.io/v1",
    api_key="your-api-key"
)

async def main():
    response = await client.chat.completions.create(
        model: 'claude-opus-4.6',
        messages=[{"role": "user", "content": "Hello!"}]
    )
    print(response.choices[0].message.content)

asyncio.run(main())

javascriptJavaScript SDK

Use the OpenAI Node.js library or native fetch API.

Using OpenAI SDK

import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.mockllm.io/v1',
  apiKey: 'your-api-key',
});

const response = await client.chat.completions.create({
  model: 'claude-opus-4.6',
  messages: [{ role: 'user', content: 'Hello!' }],
});

console.log(response.choices[0].message.content);

Using Native Fetch

const response = await fetch('https://api.mockllm.io/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Authorization': 'Bearer YOUR_API_KEY',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    model: 'claude-opus-4.6',
    messages: [{role: 'user', content: 'Hello!'}]
  })
});

const data = await response.json();
console.log(data.choices[0].message.content);

terminalcURL Examples

Quick testing with cURL from the command line.

Chat Completions

curl -X POST https://api.mockllm.io/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-4.6",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

List Fixtures

curl https://api.mockllm.io/fixtures \
  -H "Authorization: Bearer YOUR_API_KEY"

Health Check

curl https://api.mockllm.io/health

webhookWebhooks

MockLLM uses webhooks for subscription and billing events via Stripe. Pro users can configure webhook endpoints to receive real-time notifications.

Contact support@mockllm.io to configure your webhook endpoint.

errorError Handling

MockLLM uses conventional HTTP response codes to indicate success or failure.

Error Response Format

{
  "detail": {
    "error": "rate_limit_exceeded",
    "message": "Monthly limit of 1000 requests exceeded. Upgrade at https://mockllm.io/pricing",
    "usage": 1000,
    "limit": 1000
  }
}

speedRate Limits

Rate Limit Headers

All API responses include headers to help you track your usage:

X-RateLimit-Limit: 1000
X-RateLimit-Remaining: 958
X-RateLimit-Reset: 1706745600

Handling Rate Limits

When you exceed your rate limit, the API returns a 429 status code. Implement exponential backoff or upgrade to Pro for unlimited access.

historyChangelog

Follow us on Twitter for the latest updates and feature announcements.