CrewAI (gateway)

Route CrewAI’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-crewai crewai

Set environment variables

$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

No separate OpenAI provider key is needed. The code below points CrewAI’s OpenAI-compatible traffic to the Respan gateway.

Point CrewAI to the Respan gateway

1 import os
2 
3 from respan import Respan
4 from respan_instrumentation_crewai import CrewAIInstrumentor
5 
6 respan_api_key = os.environ["RESPAN_API_KEY"]
7 respan_base_url = os.getenv("RESPAN_BASE_URL", "https://api.respan.ai/api")
8 
9 os.environ["OPENAI_API_KEY"] = respan_api_key
10 os.environ["OPENAI_BASE_URL"] = respan_base_url
11 
12 respan = Respan(
13     api_key=respan_api_key,
14     base_url=respan_base_url,
15     instrumentations=[CrewAIInstrumentor()],
16 )
17 
18 from crewai import Agent, Crew, LLM, Task
19 
20 llm = LLM(
21     model="gpt-4.1-nano",
22     api_key=respan_api_key,
23     base_url=respan_base_url,
24 )
25 
26 researcher = Agent(
27     role="Researcher",
28     goal="Research the latest AI trends",
29     backstory="Senior AI researcher.",
30     llm=llm,
31 )
32 
33 task = Task(
34     description="Research the latest trends in AI agent frameworks.",
35     expected_output="A summary of key trends.",
36     agent=researcher,
37 )
38 
39 crew = Crew(agents=[researcher], tasks=[task])
40 print(crew.kickoff())
41 respan.flush()

Switch models

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

1 llm = LLM(
2     model="claude-sonnet-4-5-20250929",
3     api_key=respan_api_key,
4     base_url=respan_base_url,
5 )

See the full model list.

1	import os
2
3	from respan import Respan
4	from respan_instrumentation_crewai import CrewAIInstrumentor
5
6	respan_api_key = os.environ["RESPAN_API_KEY"]
7	respan_base_url = os.getenv("RESPAN_BASE_URL", "https://api.respan.ai/api")
8
9	os.environ["OPENAI_API_KEY"] = respan_api_key
10	os.environ["OPENAI_BASE_URL"] = respan_base_url
11
12	respan = Respan(
13	api_key=respan_api_key,
14	base_url=respan_base_url,
15	instrumentations=[CrewAIInstrumentor()],
16	)
17
18	from crewai import Agent, Crew, LLM, Task
19
20	llm = LLM(
21	model="gpt-4.1-nano",
22	api_key=respan_api_key,
23	base_url=respan_base_url,
24	)
25
26	researcher = Agent(
27	role="Researcher",
28	goal="Research the latest AI trends",
29	backstory="Senior AI researcher.",
30	llm=llm,
31	)
32
33	task = Task(
34	description="Research the latest trends in AI agent frameworks.",
35	expected_output="A summary of key trends.",
36	agent=researcher,
37	)
38
39	crew = Crew(agents=[researcher], tasks=[task])
40	print(crew.kickoff())
41	respan.flush()

1	llm = LLM(
2	model="claude-sonnet-4-5-20250929",
3	api_key=respan_api_key,
4	base_url=respan_base_url,
5	)