Skip to main content

​
Python

LangChain’s ChatOpenAI class accepts a custom base_url, making integration seamless. 
pip install langchain-openai

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="https://www.opencompress.ai/api/v1",
    api_key="sk-occ-your-key-here",
    model="gpt-4o",
)

response = llm.invoke("Explain the benefits of prompt compression.")
print(response.content)

​
With chains

from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="https://www.opencompress.ai/api/v1",
    api_key="sk-occ-your-key-here",
    model="gpt-4o",
)

prompt = ChatPromptTemplate.from_messages([
    ("system", "You are a technical writer. Be concise and clear."),
    ("user", "Write documentation for: {topic}"),
])

chain = prompt | llm
response = chain.invoke({"topic": "REST API authentication"})
print(response.content)

​
With agents

from langchain_openai import ChatOpenAI
from langchain.agents import create_tool_calling_agent, AgentExecutor
from langchain_core.prompts import ChatPromptTemplate

llm = ChatOpenAI(
    base_url="https://www.opencompress.ai/api/v1",
    api_key="sk-occ-your-key-here",
    model="gpt-4o",
)

# Your tools and agent setup work exactly the same
# OpenCompress compresses the input before each LLM call

​
TypeScript

import { ChatOpenAI } from "@langchain/openai";

const llm = new ChatOpenAI({
  configuration: {
    baseURL: "https://www.opencompress.ai/api/v1",
  },
  apiKey: "sk-occ-your-key-here",
  model: "gpt-4o",
});

const response = await llm.invoke("Explain prompt compression.");
console.log(response.content);
Agent workflows benefit the most from compression. System prompts, tool schemas, and conversation history all contain significant token waste that OpenCompress removes.