Quickstart - Lowertoken

Setup

1

Create a gateway key

Open the console, create an API token, and add a small prepaid balance before production use.

2

Point your client at Lowertoken

Use https://api.lowertoken.com/v1 as the base URL and keep the same chat completions format.

curl

curl https://api.lowertoken.com/v1/chat/completions \
  -H "Authorization: Bearer $LOWERTOKEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash-202605",
    "messages": [
      {"role": "user", "content": "Write a concise product launch checklist."}
    ]
  }'

Python

from openai import OpenAI

client = OpenAI(
    api_key="LOWERTOKEN_API_KEY",
    base_url="https://api.lowertoken.com/v1",
)

response = client.chat.completions.create(
    model="kimi-k2.7-code",
    messages=[{"role": "user", "content": "Summarize this customer interview."}],
)

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

Node

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.LOWERTOKEN_API_KEY,
  baseURL: "https://api.lowertoken.com/v1",
});

const response = await client.chat.completions.create({
  model: "minimax-m3",
  messages: [{ role: "user", content: "Draft a short support reply." }],
});

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

Developer Tools

Any tool that accepts an OpenAI-compatible API base URL can usually route through Lowertoken.

Tool	Base URL	Model example	Note
Claude Code compatible proxies	`https://api.lowertoken.com/v1`	`kimi-k2.7-code`	Use for low-cost coding experiments.
Cline	`https://api.lowertoken.com/v1`	`deepseek-v4-flash-202605`	Set custom provider and model name.
Cherry Studio	`https://api.lowertoken.com/v1`	`minimax-m3`	Good for quick route comparison.

Before production

Confirm the live route price in the console, review the Data Flow page, and set per-key usage limits before moving customer traffic.