BeeAI (gateway) | Respan Docs

Route BeeAI’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 beeai-framework

Set environment variables

$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

The code below passes RESPAN_API_KEY and the Respan base URL to BeeAI’s OpenAI-compatible LLM wrapper. No real OpenAI key is needed.

Initialize and run

1 import os
2 
3 from beeai_framework import LLM, UserMessage
4 
5 llm = LLM(
6     model="openai/gpt-5.5",
7     api_key=os.environ["RESPAN_API_KEY"],
8     base_url=os.getenv("RESPAN_BASE_URL", "https://api.respan.ai/api"),
9 )
10 
11 response = llm.generate(
12     [UserMessage("Tell me about recursion.")],
13     options={"max_tokens": 256},
14 )
15 print(response.output.response)

Switch models

Use another OpenAI model ID through the same gateway-backed LLM wrapper.

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

BeeAI uses LiteLLM under the hood. Avoid documenting Claude or Gemini behind an openai/ model prefix because that makes the transport provider look like the model provider. Use the Respan API or OpenAI SDK gateway pages for provider-neutral Claude and Gemini examples.

See the full model list.