星海词元星海词元
Ready to build?Get an API key — all models at 50% of the official price →
Home › Integrations › LangChain

LangChain

ChatOpenAI(base_url=...)

LangChain's OpenAI-compatible chat classes take base_url and api_key directly, so chains, agents and tools keep working unchanged.

Code

from langchain_openai import ChatOpenAI
llm = ChatOpenAI(base_url="https://starseaapi.com/v1", api_key="sk-your-key",
                 model="deepseek-v4.1-flash")

Quickstart

01

Create an API key

Sign up, then create a token in the console. A key works across the whole catalogue; scope and quota can be restricted per key.

02

Point your client at the endpoint

Set base_url to https://starseaapi.com/v1 and use the key. Any OpenAI-compatible SDK, IDE or desktop client works.

03

Pick a model

Start with a low-cost tier for prototyping. Every id in the catalogue can be swapped without touching code.

04

Watch cost, not just quality

Output tokens are usually priced at a multiple of input, and reasoning models emit thinking tokens. Keep stable prompt prefixes first so caching applies.

Integrations