A single API endpoint that gives you access to GPT-4, Claude, Gemini, Llama, Mistral, and 30+ other AI models through one unified interface.
No API keys to manage. No credit cards on random providers. One integration, all models.
- Every AI provider needs a separate API key
- Each has different SDKs, auth methods, and pricing
- Models change, deprecate, and get replaced
- Managing multiple bills is a nightmare
One API endpoint. One API key. All the models.
POST https://api.unified-ai.example.com/v1/chat
Authorization: Bearer YOUR_API_KEY
{
"model": "gpt-4",
"messages": [{"role": "user", "content": "Hello!"}]
}
| Category | Models |
|---|---|
| π Premium | GPT-4, GPT-4 Turbo, Claude 3 Opus, Claude 3.5 Sonnet |
| β‘ Fast | GPT-4o Mini, Claude 3 Haiku, Gemini 1.5 Flash |
| π Free Tiers | Llama 3.3 70B, Mistral, Mixtral, DeepSeek, Qwen |
| π¨ Image | DALL-E 3, Stable Diffusion XL, Flux |
| π Audio | Whisper (speech-to-text), TTS |
| π Search | Web search augmented generation |
| Plan | Price | Requests/month | Models |
|---|---|---|---|
| Starter | $10/mo | 1,000 | GPT-4o Mini, Llama, Mistral |
| Pro | $50/mo | 10,000 | All models including GPT-4, Claude |
| Enterprise | Custom | Unlimited | All models + dedicated infra |
Pay-as-you-go: $0.01 per request (no subscription needed)
- Join the waitlist: Open a GitHub issue with "API Access Request" as the title
- I'll send you your API key and documentation
- Start using it immediately
# cURL
curl -X POST https://api.unified-ai.example.com/v1/chat \
-H "Authorization: Bearer your_api_key" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o-mini",
"messages": [{"role": "user", "content": "Hello, world!"}]
}'
# Python
import requests
response = requests.post(
"https://api.unified-ai.example.com/v1/chat",
headers={"Authorization": "Bearer your_api_key"},
json={
"model": "claude-3-haiku",
"messages": [{"role": "user", "content": "Hello!"}]
}
)
print(response.json()["choices"][0]["message"]["content"])
# JavaScript
const response = await fetch("https://api.unified-ai.example.com/v1/chat", {
method: "POST",
headers: {
"Authorization": "Bearer your_api_key",
"Content-Type": "application/json"
},
body: JSON.stringify({
model: "gemini-1.5-flash",
messages: [{role: "user", content: "Hello!"}]
})
})
const data = await response.json()
console.log(data.choices[0].message.content)- All requests encrypted via TLS 1.3
- Rate limiting: 100 req/min (Starter), 1000 req/min (Pro)
- 99.9% uptime SLA for Pro and Enterprise
- Automatic failover between providers
- No data logged or stored
Open an issue, or email: doublecluccas@gmail.com
Built with g4f, Stealth Layer, and β€οΈ from Johannesburg
This project provides free access to a unified AI API. If you find it valuable:
- Sponsor on GitHub: https://github.com/sponsors/luccas12348486
- Self-host for your own use
- Contact for commercial licensing
Built by luccas12348486