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 teams can compare model cost, quality, and provider fit before changing application code more deeply.
curl https://api.nextmodel.app/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $NEXTMODEL_API_KEY" \
-d '{"model":"qwen/qwen3.7-max","messages":[{"role":"user","content":"Reply with OK."}]}'# pip install openai
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["NEXTMODEL_API_KEY"],
base_url="https://api.nextmodel.app/v1",
)
resp = client.chat.completions.create(
model="qwen/qwen3.7-max",
messages=[{"role": "user", "content":"Reply with OK."}],
)
print(resp.choices[0].message.content)// npm install openai
import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.NEXTMODEL_API_KEY,
baseURL: "https://api.nextmodel.app/v1",
});
const resp = await client.chat.completions.create({
model: "qwen/qwen3.7-max",
messages: [{ role: "user", "content":"Reply with OK." }],
});
console.log(resp.choices[0].message.content);Docs index
Every core integration page in one place.
Quickstart
Switch any OpenAI SDK to NextModel with three edits, run your first call, and change models by editing one field.
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
Every gateway error code, the JSON envelope, billing semantics, and retry guidance.
Billing
Estimate model cost and reconcile usage across projects and keys.
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.
Chat
The OpenAI-compatible chat surface: same SDK, same shapes, streaming and tools included.
Video
Submit a video job, poll it, and pass reference images as URLs or inline data URIs.
Audio
Audio SKUs today, and why this page ships no audio snippet yet.
Models
The catalog is the reference: every model page carries copy-paste snippets built from live metadata.
Claude Code
Claude Code talks the Anthropic protocol natively — point it at the gateway host, no path suffix.
Cursor
Add NextModel as an OpenAI-compatible provider in Cursor.
Any client
The three-edit migration, restated for agents and plain HTTP clients.
Codex CLI
Register NextModel as a custom OpenAI-compatible model provider in Codex CLI.
OpenCode
Add NextModel as an OpenAI-compatible provider in opencode.json.
Crush
Point the Charm Crush agent at NextModel via crush.json.
Cherry Studio
Add NextModel as an OpenAI-compatible provider in Cherry Studio.
Cline
Use NextModel as the OpenAI-compatible provider in the Cline VS Code extension.
Model IDs
How catalog ids are shaped, why they contain slashes, and which id to send where.
Usage
Query balance and usage over the API, and read the per-request billing headers.
FAQ
Migration, billing boundaries, limits, and the questions support answers most.
API Reference
Every live gateway endpoint, grouped by protocol, with auth conventions and rate-limit headers.
Verify Responses
From per-request billing headers to cryptographic receipts anchored on Base — how to prove what happened, not take it on faith.