SDKs
Official client libraries for the Segmind platform. Submit inference, poll for results, chat with LLMs, and upload files — without hand-rolling HTTP and polling loops.
The official client libraries for building on Segmind. They handle authentication, the async submit-and-poll loop, error mapping, and file uploads for you, so calling a model is a single function call.
Available SDKs
Python
pip install segmind — async-by-default run(), sync run_sync(), submit/poll handles, and LLM chat().
JavaScript / TypeScript
npm install segmind — run(), runSync(), submit/wait jobs, chat(), file uploads, history, webhooks and PixelFlow for Node.js 22+.
What the SDKs cover today
Model inference on the AI Gateway — running any model, LLM chat, and file uploads — is fully wrapped in Python.
The JavaScript SDK (0.2) covers the same REST surface: running models, LLM chat, file uploads for model inputs, request history, webhooks and PixelFlow workflows. Realtime sessions follow in 0.3.
Published PixelFlow workflows run from both
SDKs: segmind.pixelflows.run() in JavaScript, and in Python from 1.2.0
(every polling method raised AttributeError in 1.1.0, a defect on our side).
See the Workflow API Reference for the HTTP
contract underneath.
Prefer raw HTTP?
The SDKs are a convenience layer — every model is reachable over plain HTTP. See the API Reference for the v1 sync and v2 async endpoints.