Pipecat (gateway)

Route Pipecat’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-ai respan-instrumentation-pipecat

Set environment variables

$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"
$ export RESPAN_BASE_URL="https://api.respan.ai/api"
$ export RESPAN_MODEL="gpt-4.1-nano"

No OPENAI_API_KEY needed — the Respan gateway handles provider authentication.

Point Pipecat to the Respan gateway

1 import os
2 
3 from pipecat.services.openai.llm import OpenAILLMService
4 
5 llm = OpenAILLMService(
6     api_key=os.environ["RESPAN_API_KEY"],
7     base_url=os.getenv("RESPAN_BASE_URL", "https://api.respan.ai/api"),
8     settings=OpenAILLMService.Settings(model=os.getenv("RESPAN_MODEL", "gpt-4.1-nano")),
9 )

Then build and run your pipeline as usual.

Switch models

Change the model setting on OpenAILLMService to use 250+ models from different providers through the same gateway.

1 OpenAILLMService(
2     api_key=os.environ["RESPAN_API_KEY"],
3     base_url="https://api.respan.ai/api",
4     settings=OpenAILLMService.Settings(model="claude-sonnet-4-5-20250929"),
5 )
6 
7 OpenAILLMService(
8     api_key=os.environ["RESPAN_API_KEY"],
9     base_url="https://api.respan.ai/api",
10     settings=OpenAILLMService.Settings(model="gemini-2.5-flash"),
11 )

See the full model list.

$	export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"
$	export RESPAN_BASE_URL="https://api.respan.ai/api"
$	export RESPAN_MODEL="gpt-4.1-nano"

1	import os
2
3	from pipecat.services.openai.llm import OpenAILLMService
4
5	llm = OpenAILLMService(
6	api_key=os.environ["RESPAN_API_KEY"],
7	base_url=os.getenv("RESPAN_BASE_URL", "https://api.respan.ai/api"),
8	settings=OpenAILLMService.Settings(model=os.getenv("RESPAN_MODEL", "gpt-4.1-nano")),
9	)

1	OpenAILLMService(
2	api_key=os.environ["RESPAN_API_KEY"],
3	base_url="https://api.respan.ai/api",
4	settings=OpenAILLMService.Settings(model="claude-sonnet-4-5-20250929"),
5	)
6
7	OpenAILLMService(
8	api_key=os.environ["RESPAN_API_KEY"],
9	base_url="https://api.respan.ai/api",
10	settings=OpenAILLMService.Settings(model="gemini-2.5-flash"),
11	)