Skip to main content

Get started in two steps

Spin up the OpenAI SDK against the LLM7.io endpoint and make your first requests.

Step 1: Set up

Configure the client

The OpenAI SDK requires an api_key value. Use a token from dash.llm7.io for higher limits, or use unused for anonymous access.

Step 2: Text generation

Chat completions (Python)

The output will be a short story generated by the model, for example:

Next steps

Function calling

Bind tool calls to your own functions reliably.

JSON mode

Get guaranteed JSON outputs for structured use-cases.

Streaming

Stream tokens for lower latency UIs.

Available models

Choose selectors and see model options.

Models API

Read live pricing, context windows, and model capabilities.
Need help? Check the API reference above or join the community.