100+ Models ยท 50+ Providers ยท Free

The Free AI Proxy API

Access GPT-4o, Claude, Gemini, DeepSeek, Llama & more โ€”

0 Models
0 Providers
0 APIs Saved
0 Uptime

Conversations

0.7
4000
1
0
0
๐Ÿค–

Welcome to RetroSpec Chat

Ask anything! GPT-4o, Claude, Gemini, DeepSeek, and 100+ other models are at your fingertips.

Explore Models

Choose from 100+ AI models across all major providers

Model Comparison

VS

API Documentation

OpenAI-compatible API โ€” drop-in replacement for your apps

cURL
curl -X POST https://api.retrospec.dev/v1/chat/completions \\
  -H 'Content-Type: application/json' \\
  -H 'Authorization: Bearer sk-retrospec-free' \\
  -d '{
    \"model\": \"gpt-4o-mini\",
    \"messages\": [
      {\"role\": \"user\", \"content\": \"Hello!\"}
    ],
    \"stream\": false
  }'
Python
from openai import OpenAI

client = OpenAI(
    api_key='sk-retrospec-free',
    base_url='https://api.retrospec.dev/v1'
)

response = client.chat.completions.create(
    model='gpt-4o-mini',
    messages=[{'role': 'user', 'content': 'Hello!'}],
    stream=False
)

print(response.choices[0].message.content)
JavaScript
const response = await fetch('https://api.retrospec.dev/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer sk-retrospec-free'
  },
  body: JSON.stringify({
    model: 'gpt-4o-mini',
    messages: [{ role: 'user', content: 'Hello!' }],
    stream: false
  })
});

const data = await response.json();
console.log(data.choices[0].message.content);
๐Ÿ”„

Automatic Fallback

If one provider fails, we automatically route to the next available model

โšก

Streaming Support

Full SSE streaming support for real-time responses

๐Ÿ”’

Privacy First

No logging, no tracking, no data retention

๐ŸŒ

Global CDN

300+ edge locations for lowest latency worldwide

Provider Status

Real-time health of all AI providers

OpenAI
Healthy
Latency 142ms
Uptime 99.9%
Anthropic
Healthy
Latency 189ms
Uptime 99.7%
Google
Healthy
Latency 98ms
Uptime 99.8%
DeepSeek
Healthy
Latency 156ms
Uptime 99.5%
Requests/min 0

Settings

Enable animations
Particle effects
Sound effects
Respect prefers-reduced-motion

Add your own API keys for higher rate limits

Save frequently used prompts for quick access

Code Reviewer Review this code for bugs and improvements...
Summarizer Summarize the following text concisely...

v1.0.0

A free AI proxy API running on Cloudflare Workers

Quick Presets

Keyboard Shortcuts

Ctrl+Enter Send message
Shift+Enter New line
Ctrl+K Search models
Ctrl+L Clear chat
Ctrl+/ Show shortcuts
Esc Close modals