Quickstart

Call Boardwalk from your app with the OpenAI or Anthropic SDK.

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. In the examples, replace your-api-key with the key from your app’s server-side configuration.

2. Make a request

Choose an API and a language below. Use a model ID from the catalog or the name of your deployed model. Check the model's supported_endpoints for available APIs.

POST/v1/chat/completions

from openai import OpenAI

client = OpenAI(
    base_url="https://api.boardwalk.cloud/v1",
    api_key="your-api-key",
)

response = client.chat.completions.create(
    model="Qwen/Qwen3-0.6B",
    messages=[{"role": "user", "content": "Say hello in five words."}],
    max_completion_tokens=1024,
)
print(response.choices[0].message.content)
print(response.usage)

SDK setup: pip install openai · npm install openai. cURL needs no SDK.

Each example prints the answer and token usage. The selected API determines the request fields and response shape; your Boardwalk API key works with all three.

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.

Run a batchProcess a dataset asynchronously and download the results.

Choose a modelFind model IDs, capabilities, and exact revisions.

Deploy your modelUse the same API with your own weights.

Structured output and toolsGet JSON that matches a schema and call tools from your app.