LangGraph (gateway)

Route LangGraph’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 respan-tracing respan-instrumentation-langchain langgraph 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 LangGraph's LLM 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-4.1-nano",
8 )

Then build and run your graph as usual.

Switch models

Change the model parameter to use 250+ models from different providers through the same gateway.

1 llm = ChatOpenAI(api_key=..., base_url="https://api.respan.ai/api", model="claude-sonnet-4-5-20250929")
2 llm = ChatOpenAI(api_key=..., base_url="https://api.respan.ai/api", model="gemini-2.5-flash")

See the full model list.

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-4.1-nano",
8	)

1	llm = ChatOpenAI(api_key=..., base_url="https://api.respan.ai/api", model="claude-sonnet-4-5-20250929")
2	llm = ChatOpenAI(api_key=..., base_url="https://api.respan.ai/api", model="gemini-2.5-flash")