Skip to main content

Open WebUI and other clients

Any client that accepts an OpenAI-compatible base URL and an API key works with these values:

SettingValue
Base URLhttps://api.openhippo.io/v1
API keyyour key (hk_live_...), sent as Authorization: Bearer
Modelan ID or alias from the model list

Open WebUI​

In Open WebUI, add an OpenAI API connection under Admin settings → Connections:

  • URL: https://api.openhippo.io/v1
  • Key: your API key

Open WebUI loads the model list via GET /v1/models. For teams that do not want to run a chat of their own, there is Hippo Chat.

OpenAI SDKs​

The official OpenAI SDKs work unchanged with base_url/baseURL and the key, see Quickstart. Or via environment variables the SDKs read automatically:

export OPENAI_BASE_URL="https://api.openhippo.io/v1"
export OPENAI_API_KEY="$OPENHIPPO_API_KEY"

LangChain​

pip install langchain-openai
import os
from langchain_openai import ChatOpenAI, OpenAIEmbeddings

llm = ChatOpenAI(
    base_url="https://api.openhippo.io/v1",
    api_key=os.environ["OPENHIPPO_API_KEY"],
    model="openhippo/gpt-oss-120b",
)
print(llm.invoke("Name three sights in Augsburg.").content)

embeddings = OpenAIEmbeddings(
    base_url="https://api.openhippo.io/v1",
    api_key=os.environ["OPENHIPPO_API_KEY"],
    model="openhippo/Qwen3-Embedding-0.6B",
    check_embedding_ctx_length=False,
)
print(len(embeddings.embed_query("Augsburg")))

check_embedding_ctx_length=False makes LangChain send text instead of OpenAI-specific token IDs.