hiway2llm 0.1.0

HiWay2LLM SDK (Python) — OpenAI-compatible client for the HiWay router. BYOK, 40-60% savings, 0% markup on inference.

hiway2llm

Official Python SDK for HiWay2LLM — BYOK smart LLM routing with 40-60 % savings and zero markup on inference.

Install

pip install hiway2llm

Or with uv:

uv add hiway2llm

Works on Python 3.9+. Pulls in httpx (the only runtime dep).

Quickstart

import os
from hiway2llm import Hiway

h = Hiway(api_key=os.environ["HIWAY_API_KEY"])

res = h.chat.completions.create(
    model="auto",                                     # smart routing
    messages=[{"role": "user", "content": "Say hi"}],
)

print(res["choices"][0]["message"]["content"])
print(res["_hiway"]["routed_model"])                  # which model was picked

Already using the OpenAI SDK? You can keep it — just change base_url:

from openai import OpenAI
client = OpenAI(
    api_key=os.environ["HIWAY_API_KEY"],              # hw_live_...
    base_url="https://app.hiway2llm.com/v1",
)

Both approaches hit the same OpenAI-compatible endpoint.

API surface

Method	Description
h.chat.completions.create(model=..., messages=..., **opts)	OpenAI-compatible chat completion.
h.models.list()	Models your workspace can route to (BYOK-filtered).
h.me()	Current user + plan.

Errors

All 4xx / 5xx responses raise HiwayError with .status + .body:

from hiway2llm import Hiway, HiwayError

h = Hiway()
try:
    h.chat.completions.create(model="auto", messages=[{"role": "user", "content": "hi"}])
except HiwayError as e:
    if e.status == 402:
        # quota exhausted — prompt to upgrade
        ...

Links

• Homepage
• Docs
• CLI
• GitHub

License

MIT — © Mytm-Group SAS