Orion-zhen/transAPI

OpenAI compatible API purely based on Transformers

30
/ 100
Emerging

This project helps developers test large language models (LLMs) that aren't supported by common inference engines like vLLM or HuggingFace TGI. It takes any model compatible with HuggingFace Transformers and makes it accessible through an OpenAI-compatible API. This allows developers to quickly integrate and experiment with a wider range of models for their applications.

No commits in the last 6 months.

Use this if you are a developer experimenting with less common or newly released large language models that are supported by HuggingFace Transformers but not by other popular inference backends, and you need an OpenAI-compatible interface for testing.

Not ideal if you need a production-ready solution with advanced features like continuous batching, paged attention, or OpenAI-style tool calling, or if the model you are using is already supported by vLLM or TGI.

LLM development API integration model prototyping HuggingFace Transformers AI experimentation
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 8 / 25

How are scores calculated?

Stars

9

Forks

1

Language

Python

License

AGPL-3.0

Last pushed

Aug 09, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/Orion-zhen/transAPI"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.