API Reference
RukkitAI API
Access open-source AI models via a simple REST API. Requires a Pro membership and an API key from your profile.
Authentication
Include your API key in every request as a Bearer token:
Authorization: Bearer rk_live_your_api_key_here
Generate keys in your profile (Pro only). Maximum 5 keys per account.
Base URL
https://rukkitai.org/api/v1
POST /chat
Send a message to an AI model and get a response.
Request body
{
"message": "string (required, max 4000 chars)",
"model": "string (optional, see models below)",
"system": "string (optional, system prompt, max 2000 chars)"
}Response
{
"content": "string",
"model": "string",
"usage": {
"total_tokens": number
}
}Rate limits
20 requests/minute per API key. No daily limit for Pro members.
Examples
curl
curl -X POST https://rukkitai.org/api/v1/chat \
-H "Authorization: Bearer rk_live_your_key" \
-H "Content-Type: application/json" \
-d '{
"message": "Explain what a transformer is in AI",
"model": "meta-llama/llama-3.3-70b-instruct:free"
}'Python
import requests
res = requests.post(
"https://rukkitai.org/api/v1/chat",
headers={"Authorization": "Bearer rk_live_your_key"},
json={
"message": "Explain what a transformer is in AI",
"model": "meta-llama/llama-3.3-70b-instruct:free",
}
)
data = res.json()
print(data["content"])JavaScript / TypeScript
const res = await fetch("https://rukkitai.org/api/v1/chat", {
method: "POST",
headers: {
"Authorization": "Bearer rk_live_your_key",
"Content-Type": "application/json",
},
body: JSON.stringify({
message: "Explain what a transformer is in AI",
model: "meta-llama/llama-3.3-70b-instruct:free",
}),
});
const { content, model, usage } = await res.json();
console.log(content);With system prompt
curl -X POST https://rukkitai.org/api/v1/chat \
-H "Authorization: Bearer rk_live_your_key" \
-H "Content-Type: application/json" \
-d '{
"message": "Review this code: console.log(x)",
"system": "You are a senior software engineer. Be concise.",
"model": "meta-llama/llama-3.1-8b-instruct:free"
}'Available Models
All models are open-source and free to use with a Pro membership. If no model is specified, Llama 3.3 70B is used.
| Model ID | Name | Notes |
|---|---|---|
| meta-llama/llama-3.1-8b-instruct:free | Llama 3.1 8B | Fast, general purpose |
| meta-llama/llama-3.3-70b-instruct:free | Llama 3.3 70B | High quality, slower |
| google/gemini-2.0-flash-exp:free | Gemini 2.0 Flash | Google, multimodal |
| deepseek/deepseek-r1:free | DeepSeek R1 | Strong reasoning |
| deepseek/deepseek-chat-v3-0324:free | DeepSeek V3 | Fast chat |
| mistralai/mistral-7b-instruct:free | Mistral 7B | Efficient, European |
| qwen/qwen3-8b:free | Qwen3 8B | Alibaba, multilingual |
| microsoft/phi-4-reasoning:free | Phi-4 Reasoning | Microsoft, reasoning |
Error codes
| Status | Meaning |
|---|---|
| 401 | Invalid or missing API key |
| 403 | Pro membership required |
| 400 | Invalid request body |
| 429 | Rate limit exceeded (20 req/min) |
| 503 | AI service temporarily unavailable |
Get API access
API access requires a Pro membership. Unlimited requests, 8 open-source models, 20 req/min rate limit.