Budget Routing

Pass budget_cents to automatically select the highest-quality model that fits within your cost limit. This overrides the model parameter.

Request

{
  "budget_cents": 0.5,
  "messages": [{"role": "user", "content": "Translate to Spanish: Hello world"}],
  "include_routing": true
}

Response

{
  "model": "deepseek-v3",
  "routing": {
    "budget_routing": {
      "requested_budget_cents": 0.5,
      "resolved": "deepseek-v3",
      "reason": "Best model within 0.5¢: DeepSeek V3 (0.3¢/req)"
    }
  },
  "cost": {"this_request": "$0.003"}
}

Parameters

Parameter	Type	Description
`budget_cents`	number	Maximum cost in cents for this request. Overrides `model`.
`include_routing`	boolean	Include the routing decision in the response.

Code examples

import requests, os

r = requests.post("https://www.ninjachat.ai/api/v1/chat",
    headers={"Authorization": f"Bearer {os.environ['NINJACHAT_API_KEY']}"},
    json={
        "budget_cents": 1.0,
        "messages": [{"role": "user", "content": "Explain gradient descent"}],
        "include_routing": True,
    }
)
data = r.json()
print(f"Model: {data['model']}, Cost: {data['cost']['this_request']}")

curl -X POST https://www.ninjachat.ai/api/v1/chat \
  -H "Authorization: Bearer nj_sk_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "budget_cents": 0.5,
    "messages": [{"role": "user", "content": "What is 2+2?"}],
    "include_routing": true
  }'

Budget routing works alongside smart routing — if you pass both model: "auto" and budget_cents, the budget ceiling takes priority.

Get Started

Chat Completions

Smart Features

Images, Video & Search

Reference

Request

Response

Parameters

Code examples

​Request

​Response

​Parameters

​Code examples

Request

Response

Parameters

Code examples