LangChain + Evrona
To LangChain the gateway is a plain OpenAI provider: only base_url changes.
What to prepare
No key yet? Create an account — keys are created in the dashboard under “API keys”, and the full value is shown only once. Copy the Model ID from the catalog in full, including the prefix before “/”.
Connection steps
Install the langchain-openai package.
Build a ChatOpenAI with our address, your key and a Model ID.
After that everything is as usual — chains, tools, agents: function calling works.
# pip install langchain-openai
from langchain_openai import ChatOpenAI
llm = ChatOpenAI(
model="google/gemini-3.7-flash",
base_url="https://evrona.ru/v1",
api_key="ev-YOUR_KEY",
)
print(llm.invoke("Hello").content)In the JavaScript version the address lives in the configuration.baseURL field, the rest is no different.
Function calling is supported, so agentic modes work. Strict JSON mode (response_format) and the retired functions format are turned down with an unsupported_parameter error — no parameter is lost in silence. Image input is taken by models marked "Understands images" in the catalog: a content part of type image_url with a data:image/png;base64,… URL (PNG, JPEG or WebP, up to 5 MB each, up to 50 per request). Remote URLs are not fetched, and a model without that mark returns unsupported_capability — both errors name the reason outright.