K-AI API

Feel free to AI

Leading AI models reverse engineered to a simple api call.

Chat Completion

Send a message and get a response from the best available AI.

POST /v1/chat/completions
Parameters
message Your prompt(required)

Example Request
curl https://kiwa001-kai-api-gateway.hf.space/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer YOUR_API_KEY" \ -d '{"model": "gemini-3-flash", "messages": [{"role": "user", "content": "Hello!"}]}'

Note: Replace YOUR_API_KEY with your actual API key from the dashboard above.

Try It Live

List Models

Get all currently available AI models.

GET /models

Returns a JSON list of all models supported by the API, ranked by quality.


Example Request
curl https://kiwa001-kai-api-gateway.hf.space/models \ -H "Authorization: Bearer YOUR_API_KEY"
Try It Live

Web Search & Research

Reverse-engineered web search and deep content gathering. Requires API key (free, no token deduction).

POST /search
Endpoints
  • /search: Standard web search (Links)
  • /deep_research: Deep content gathering (Scraper)
Parameters
query Search topic(required)

Example Request
curl -X POST https://kiwa001-kai-api-gateway.hf.space/search \ -H "Content-Type: application/json" \ -H "Authorization: Bearer YOUR_API_KEY" \ -d '{"query": "Machine Learning", "limit": 5}'

Note: Web searches require an API key but are free (no token deduction).

Try It Live

🏆 Live Model Ranking (Time-Weighted)

Real-time performance tracked by the engine (Speed & Reliability).

LIVE UPDATES
# Model ID Score Avg Time Success Fail
Loading live stats...

Network Analytics

Live Latency vs. Reliability & Provider Distribution.

SPEED vs RELIABILITY

PROVIDER DISTRIBUTION

Check Your API Usage

Enter your API key to see your current token usage and remaining quota.