LangChain (gateway)

Route LangChain’s underlying LLM calls through the Respan gateway to use 250+ models from different providers. Only your Respan API key is needed — no separate provider keys required.

Setup

Install packages

$ pip install langchain langchain-openai python-dotenv

Set environment variables

$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

No OPENAI_API_KEY needed — the Respan gateway handles provider authentication.

Point LangChain to the Respan gateway

1 import os
2 from langchain_openai import ChatOpenAI
3 
4 llm = ChatOpenAI(
5     api_key=os.environ["RESPAN_API_KEY"],
6     base_url=os.getenv("RESPAN_BASE_URL", "https://api.respan.ai/api"),
7     model="gpt-5.5",
8 )
9 
10 response = llm.invoke("Say hello through the Respan gateway.")
11 print(response.content)

Switch models

Change the model parameter on ChatOpenAI to use another OpenAI model through the same gateway-backed endpoint.

1 llm = ChatOpenAI(api_key=..., base_url="https://api.respan.ai/api", model="gpt-5.5")
2 llm = ChatOpenAI(api_key=..., base_url="https://api.respan.ai/api", model="gpt-5-mini")

ChatOpenAI is LangChain’s OpenAI-compatible chat adapter. This page avoids showing Claude or Gemini inside that OpenAI-named adapter; use the Respan API or OpenAI SDK gateway pages for provider-neutral Claude and Gemini examples.

See the full model list.

Respan parameters

Pass additional Respan parameters via extra_body for gateway features.

1 llm = ChatOpenAI(
2     base_url="https://api.respan.ai/api/",
3     api_key=os.environ["RESPAN_API_KEY"],
4     model="gpt-5.5",
5     extra_body={
6         "customer_identifier": "user_123",
7         "fallback_models": ["gpt-5-mini"],
8         "metadata": {"session_id": "abc123"},
9         "thread_identifier": "conversation_456",
10     },
11 )

See Respan params & metadata for the full list.