Quickstart

For Claude, ChatGPT or Codex, use the MCP quickstart.

Get your API key

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

Install an SDK

npm install @ninjachat/sdk

pip install ninjachat

Put the key in your environment

export NINJACHAT_API_KEY='nj_sk_your-api-key-here'

Make your first request

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

import { NinjaChat } from "@ninjachat/sdk";

const client = new NinjaChat({
  apiKey: process.env.NINJACHAT_API_KEY!,
});

const response = await client.responses.create({
  model: "ninja/auto",
  input: "What is the capital of France?",
});

console.log(response.output_text);

import os
from ninjachat import NinjaChat

client = NinjaChat(api_key=os.environ["NINJACHAT_API_KEY"])
response = client.responses.create(
    model="ninja/auto",
    input="What is the capital of France?",
)
print(response["output_text"])

curl https://www.ninjachat.ai/api/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $NINJACHAT_API_KEY" \
  -d '{
    "model": "ninja/auto",
    "input": "What is the capital of France?"
  }'

Read the response

Read the answer from output_text. Check model, cost_usd and request_id for the model used, cost and request trace.

Example response and routing details

{
  "id": "resp_...",
  "object": "response",
  "status": "completed",
  "model": "gemini-3-flash",
  "output_text": "The capital of France is Paris.",
  "cost_usd": 0.00003,
  "provider": "google",
  "request_id": "req_...",
  "routing": {
    "strategy": "balanced",
    "requested_models": ["ninja/auto"],
    "resolved_model": "gemini-3-flash",
    "provider": "google",
    "fallbacks_allowed": true,
    "data_policy": "default",
    "router": {
      "id": "ninja/auto",
      "task": "factual",
      "classified_by": "regex",
      "candidates": ["gemini-3-flash", "..."]
    }
  }
}

model is the concrete model the router chose — the same value as routing.resolved_model — while routing.requested_models keeps the ninja/auto you asked for. routing.router explains the pick: the detected task, how it was classified (regex, llm, or llm-cached), and the ranked candidate chain. The sample is trimmed; see Smart routing for the full block.

Need streaming, images, video, usage, or request traces? Continue to the SDK guide. Already using the OpenAI SDK? Change two lines.

Next steps

SDKs

TypeScript and Python clients

Smart Routing

ninja/auto plus cost, latency, and quality routing

Choose a model

Frontier chat, image, and video models

Observability

Request traces, usage, balance, health, and webhooks

Go live

Reliability, spend controls, and launch checks

Pricing

Live token and media rates

Get Started

Chat

Orchestration

Production

Media & search

Reference

Next steps

SDKs

Smart Routing

Choose a model

Observability

Go live

Pricing

​Next steps

SDKs

Smart Routing

Choose a model

Observability

Go live

Pricing

Next steps