Quick Start

This guide takes you from a new account to a successful API response.

1. Create an API key

Sign in to the TokenPass Console, open API key management, and create a key. Store it in an environment variable instead of placing it directly in source code.

export TOKENPASS_API_KEY="your-tokenpass-api-key"

PowerShell:

$env:TOKENPASS_API_KEY = "your-tokenpass-api-key"

2. Send your first request

curl

curl https://tokenpass.cloud/v1/chat/completions \
  -H "Authorization: Bearer $TOKENPASS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5-mini",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["TOKENPASS_API_KEY"],
    base_url="https://tokenpass.cloud/v1",
)

response = client.chat.completions.create(
    model="gpt-5-mini",
    messages=[{"role": "user", "content": "Hello!"}],
)

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

JavaScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.TOKENPASS_API_KEY,
  baseURL: "https://tokenpass.cloud/v1",
});

const response = await client.chat.completions.create({
  model: "gpt-5-mini",
  messages: [{ role: "user", content: "Hello!" }],
});

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

3. Discover model IDs

curl https://tokenpass.cloud/v1/models \
  -H "Authorization: Bearer $TOKENPASS_API_KEY"

Use the returned id value in API requests. The documentation describes model capabilities, while this endpoint is the canonical source for callable IDs.

Next steps

• Read the API Reference for Responses, Messages, streaming, tools, and errors.
• Browse Models and Pricing.
• Configure Claude Code or OpenClaw.