Skip to main content
curl -X POST https://ninjachat.ai/api/v1/chat \
  -H "Authorization: Bearer nj_sk_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "auto", "messages": [{"role": "user", "content": "Hello!"}]}'
One API key. GPT-5, Claude, Gemini, and more. Set model to auto and NinjaChat picks the best model for each request — or choose one explicitly with model: "gpt-5".

30+ models, one key

Access GPT-5, Claude, Gemini, DeepSeek, Llama, and more. Switch models by changing a string.

Smart routing

Set model: "auto" and NinjaChat picks the best model based on your prompt.

Simple pricing

Flat per-request rates. No token math. Every response tells you what it cost.

​
Get started

1

Get an API key

Go to your Developers dashboard and create a key.
2

Make your first request

Copy the curl above, replace nj_sk_YOUR_API_KEY, and run it. Full quickstart
3

Explore features

Try smart routing to auto-select models, compare to benchmark them, or batch to run many prompts at once.
Want to try before coding? The API Playground lets you test all models and features in your browser.

​
Every response includes cost

{
  "choices": [{"message": {"role": "assistant", "content": "..."}}],
  "cost": {"this_request": "$0.006"},
  "balance": "$4.820"
}
No subscriptions. No per-token pricing. Flat per-request rates. Full pricing