Every model, one API.
Open models running in the Netherlands. Same endpoint, same key, pick by name.
ModelGood atPrice
qwen3.8-27bGeneral chat and tool use. The default. Our own mixed quant, not FP8 or INT4.€ 0.10 in · € 1.20 out€ 0.05 cached in · per million tokensTry →qwen3-embeddingsVectors for search and retrieval.€ 0.10 inper million tokensTry →clef-flashA decision model. Fast and cheap.€ 0.04 inper million tokensGet notified →Connect
Change one line.
Any OpenAI-compatible library works. Point it at our endpoint and use your ETHUX key.
client = OpenAI(
base_url="https://api.ethux.net/v1",
api_key=os.environ["ETHUX_KEY"],
)