Quick Start

MindProxy is an AI API gateway: you call OpenAI, Claude, Gemini and more through one API key and compatible endpoints, while the platform handles auth, billing, usage records and troubleshooting.

The 5 steps below take you from zero to your first successful call.

Base URL

Examples in this site use the gateway address https://gateway.mindproxy.ai.

Open the console home page, register with your email and sign in. The left nav has Overview, API Keys, Recharge, Usage and more.

2. Create an API key

Go to API Keys and click Create API Key.

The plaintext key is shown only once — copy and store it somewhere safe right away; you cannot view it again after leaving the page.
You can scope each key to specific models and set a monthly spend limit.

See Get an API Key.

3. Recharge (USDT)

Go to Recharge, create an order, and the system returns a unique amount and a payment entry. Only Infini-hosted on-chain USDT recharge is supported for now. Once confirmed on-chain, your balance is credited automatically.

See Recharge & Billing.

4. Make your first call

Send your API key with every request:

Authorization: Bearer <your API key>

The easiest path is the OpenAI-compatible endpoint. First put the key in an environment variable:

bash

export TT_API_KEY="sk-your-key"

cURL

bash

curl https://gateway.mindproxy.ai/v1/chat/completions \
  -H "Authorization: Bearer $TT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello, who are you?"}]
  }'

OpenAI SDK (Python)

Just point base_url at the platform; the rest of your code is unchanged:

python

from openai import OpenAI

client = OpenAI(api_key="sk-your-key", base_url="https://gateway.mindproxy.ai/v1")

resp = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

What goes in model? Use a model ID listed on Models & plans or the console "Model Prices" page. You can also call GET /v1/models to list every model your key can use.

5. Check usage, billing and request logs

Console page	Purpose
Usage	Token usage and charges by time / model, exportable as CSV
Recharge	Balance, recharge orders and ledger records
Requests	Look up a single call's billing and error detail by request id

Every response carries an X-TT-Request-ID header — give it to support to locate the call.

Next steps

Don't want to write code? See Client Integration.
Integrating into your app? See SDK examples.
Want Claude / Gemini native formats, images or async tasks? See the API Reference.
Hitting errors? See Errors & rate limits.

Quick Start ​

1. Register and sign in ​

2. Create an API key ​

3. Recharge (USDT) ​

4. Make your first call ​

cURL ​

OpenAI SDK (Python) ​

5. Check usage, billing and request logs ​

Next steps ​