Python SDK + CLI for Alpie Core are live (sync, async, streaming)
Hey Builders 👋
We have just released the official Python SDK and CLI for Alpie Core, our 32B reasoning model trained and served entirely at native 4-bit precision.
The goal was simple: make it genuinely easy to build, test, and ship with a reasoning model in real-world systems, not just demos.
What’s included in the first release:
Clean Python SDK with sync, async, and streaming support
A lightweight CLI for quick experiments and scripting
OpenAI-compatible API surface for drop-in integration
Built-in retries, timeouts, and typed error handling
Designed for long-context and multi-step reasoning workflows
The SDK is production-ready and already integrated with our hosted API, so you can transition from pip install to real workloads quickly. To make experimentation frictionless, the first API key comes with 5 million free tokens to test, benchmark, and build without limits. Get started on our website.
We’d love feedback from builders using it in:
Agentic flows and tool-calling setups
Long-context reasoning or planning tasks
High-throughput async workloads
Anything that breaks in production before it breaks in a benchmark
Docs + source are live, and we’re actively iterating.
Github Link: https://github.com/169Pi/Pi169-SDK
If you encounter sharp edges, missing primitives, or design gaps, please let us know. This SDK will evolve directly based on how people actually use Alpie Core.

Replies
This is interesting. I’ve worked with a few AI SDKs recently, and having both sync/async support plus streaming from day one is a big win. In practice, that flexibility really matters once you move from demos to real user-facing tools. Curious to see how devs integrate this in production workflows.