Guides
Developer guides for OpenAI-compatible LLM APIs
Working code for the same chat-completions API that hosted providers and local servers expose. Each guide states exactly what the code was tested against.
Quickstarts
From an empty folder to a working request, with credentials kept out of the code.
2 min · checked 14 November 2026
Call an uncensored LLM API from Node.js
Call an uncensored or open-weight LLM from Node.js with the OpenAI SDK: environment variables, a first request, streaming with cancellation, errors and retries.
3 min · checked 14 November 2026
Call an uncensored LLM API from Python
Call an uncensored or open-weight LLM from Python with the OpenAI SDK: environment variables, first request, streaming, error handling, retries and provider switching.
API features
Streaming, tool calling and the details that change between providers.
3 min · checked 14 November 2026
OpenAI-compatible LLM APIs, and where they differ
What OpenAI-compatible means for uncensored LLM APIs: base URLs, ignored parameters, reasoning fields, usage in streams, tool calls, plus a script to probe any endpoint.
3 min · checked 14 November 2026
Streaming LLM responses with server-sent events
How LLM API streaming works: the server-sent events format, parsing chunks, the final usage chunk, cancelling a stream, timeouts and errors that arrive mid-stream.
2 min · checked 14 November 2026
Tool calling with an OpenAI-compatible LLM API
Tool calling with open-weight and uncensored LLMs: defining tools, the request and response loop, validating arguments, limits on rounds, and provider differences.