CheapTokens is beta/experimental software. Use at your own risk.

Getting Started

Go from zero to making API calls in a few steps. No account creation required.

1. Buy credits

Go to the Buy page and choose how many Venice.ai API credits you want. Payment is in USDC on the Base network via the x402 protocol. You can use a browser wallet (MetaMask, Coinbase Wallet, etc.) or an embedded wallet will be created for you.

Discount tip: Credits expire at midnight UTC. The later in the day you buy, the bigger the discount (up to ~75% off near the 23:00 UTC cutoff). Check the home page for the live discount.

2. Get your API key

After payment confirms, you receive a Venice.ai INFERENCE API key instantly. Copy it and store it securely — you will need it for all API calls. The key is valid until midnight UTC on the day of purchase.

3. Install the OpenAI SDK (optional)

Venice's API is OpenAI-compatible, so you can use the official OpenAI SDK in any language. Or just use curl directly.

Python
pip install openai

Node.js
npm install openai

4. Make your first API call

Point the SDK at https://api.venice.ai/api/v1 and use your Venice API key. You call Venice directly — CheapTokens is not a proxy.

Python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.venice.ai/api/v1",
    api_key="your_venice_key"
)

response = client.chat.completions.create(
    model="claude-sonnet-45",
    messages=[{"role": "user", "content": "Hello, world!"}],
    extra_body={"venice_parameters": {"disable_thinking": True}}
)

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

cURL
curl https://api.venice.ai/api/v1/chat/completions \
  -H "Authorization: Bearer your_venice_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-45",
    "messages": [{"role": "user", "content": "Hello, world!"}],
    "venice_parameters": {"disable_thinking": true}
  }'

5. Choose a model

Venice offers models across multiple tiers. Set the model parameter to any supported model ID. See the pricing page for a full list with per-token costs, or read the OpenAI compatibility guide for details on supported parameters.

Popular models: claude-sonnet-45, claude-opus-46, openai-gpt-52, deepseek-v32, grok-41-fast

← API Documentation Next: OpenAI Compatibility →