Manage one API key to access OpenAI, Claude, Gemini, Llama, Mistral and more
Compare different AI models side-by-side with identical prompts
Monitor your API usage, costs, and set budget limits across all providers
Use the simplified endpoint to route to any AI model automatically:
curl -X POST "https://your-ai-buffet.com/ab/claude-3-opus" \
-H "Content-Type: application/json" \
-H "X-API-Key: your_ai_buffet_key" \
-d '{
"messages": [
{"role": "user", "content": "Write a short story about AI"}
],
"temperature": 0.7
}'import requests
# Access any model using provider-specific endpoints
response = requests.post(
"https://your-ai-buffet.com/api/anthropic/chat",
headers={"X-API-Key": "your_ai_buffet_key"},
json={
"model": "claude-3-opus",
"messages": [
{"role": "user", "content": "Explain quantum computing in simple terms"}
],
"temperature": 0.7
}
)
print(response.json())GPT-4o, GPT-4, GPT-3.5
Claude 3 Opus, Sonnet, Haiku
Gemini 1.5 Pro, Ultra
Llama 3 (8B, 70B, 405B)
Mistral Large, Medium, Small
Grok-1.5, Grok-1
Command, Command R+
OpenRouter, Requesty support
Automatic routing to available providers based on model name
Set budget and token limits per project or user
Secure storage of provider API keys
Compare responses from multiple models side-by-side
Save and reuse your most effective prompts
Track usage patterns and costs across all providers
Create an account and start using our API gateway in minutes.