/ docs / uk

Quickstart

Move from an existing OpenAI SDK to NextModel in three edits: base_url, API key, and model ID.

Code first

Python, Node, and curl examples use the same OpenAI-compatible endpoint.

What does the quickstart change?

A NextModel migration usually changes three values: the SDK base URL, the API key, and the model ID. The request shape stays OpenAI-compatible so UK teams can compare model cost, quality, and provider fit before changing application code more deeply.

Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.nextmodel.app/v1"
)

resp = client.chat.completions.create(
    model="doubao-seed-2-0-mini",
    messages=[{"role": "user", "content": "Hello from NextModel"}]
)

print(resp.choices[0].message.content)

Node

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.NEXTMODEL_API_KEY,
  baseURL: "https://api.nextmodel.app/v1",
});

const response = await client.chat.completions.create({
  model: "doubao-seed-2-0-mini",
  messages: [{ role: "user", content: "Hello from NextModel" }],
});

console.log(response.choices[0].message.content);

curl

curl https://api.nextmodel.app/v1/chat/completions \
  -H "Authorization: Bearer $NEXTMODEL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seed-2-0-mini",
    "messages": [{"role": "user", "content": "Hello from NextModel"}]
  }'

Docs index

Every core integration page in one place.

Quickstart

Connect an existing OpenAI SDK to NextModel in minutes, then compare providers and keep AI spend visible before UK production traffic grows.

Authentication

Use Bearer tokens, project-scoped keys, and budget-aware key management for AI API calls.

Chat completions

Call chat models through one OpenAI-compatible request shape.

Streaming

Understand streaming capability labels before using a model in production.

Models

Fetch model prices, capabilities, source labels, context length, and recommended use cases.

Errors

Common HTTP error categories for gateway and provider troubleshooting.

Billing

Estimate model cost and reconcile usage across projects and keys with UK-ready spend visibility.

OpenAI migration

Move an existing OpenAI SDK integration to NextModel with minimal application changes.

CacheSafety Bench

Understand how to benchmark safe LLM response reuse before enabling production caching.