Quickstart
Make your first request with the OpenAI SDK or a simple HTTP call.
1. Get an API key
Open the console, add credits, and create an API key with inference:write. Copy the key; it is shown only once. Keep it on your server.
Terminal
export BOARDWALK_API_KEY="bw_live_..."2. Make a request
Install the SDK with pip install openai or npm install openai. For cURL, no installation is needed. Use a model ID from the catalog or the name of your deployed model.
import os
from openai import OpenAI
client = OpenAI(
base_url="https://api.boardwalk.cloud/v1",
api_key=os.environ["BOARDWALK_API_KEY"],
)
response = client.chat.completions.create(
model="Qwen/Qwen3-0.6B",
messages=[{"role": "user", "content": "Say hello in five words."}],
max_tokens=1024,
)
print(response.choices[0].message.content)
print(response.usage)The answer is in choices[0].message.content. The usage object reports tokens used. A reasoning model can also return a separate reasoning field.
3. Check your usage
Open the request in the console to see its tokens, cost, and model revision. Each completed inference request has a receipt.