Skip to main content
1

Get your API key

Create a key at Developers → Connections → Apps. Keys look like nj_sk_... and are shown once — copy immediately.
2

Put it in your environment

3

Make your first request

Set model to auto and NinjaChat picks the best model for you.
4

Read the response

Every response tells you which model ran, what it cost, and your remaining balance:
auto routed this to gemini-3-flash — the fastest option for a short factual question.
Already using the OpenAI SDK? Point it at NinjaChat — two lines change.

Next steps

Smart Routing

auto explained — and its fast/cheap/quality variants

Images

14 models from $0.03

Video

Veo, Kling, Seedance from $3

Compare

Race models, get ranked results

Sessions

Server-side conversation memory

Pricing

Flat rates, no token math