Pydantic AI (gateway)

Route OpenAI-compatible Pydantic AI model 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 pydantic-ai

Set environment variables

$ export RESPAN_API_KEY="YOUR_RESPAN_API_KEY"

No OPENAI_API_KEY needed — the Respan gateway handles provider authentication.

Point Pydantic AI to the Respan gateway

Python

1 import os
2 
3 respan_api_key = os.environ["RESPAN_API_KEY"]
4 respan_base_url = os.getenv("RESPAN_BASE_URL", "https://api.respan.ai/api")
5 
6 os.environ["OPENAI_API_KEY"] = respan_api_key
7 os.environ["OPENAI_BASE_URL"] = respan_base_url
8 
9 from pydantic_ai import Agent
10 
11 agent = Agent(
12     model="openai-chat:gpt-5.5",
13     system_prompt="You are a helpful assistant.",
14 )
15 
16 result = agent.run_sync("What is the capital of France?")
17 print(result.output)

Switch models

Change the model string to another OpenAI model ID through the same gateway-backed provider configuration.

1 agent = Agent(
2     model="openai-chat:gpt-5.5",
3     system_prompt="You are a helpful assistant.",
4 )

Pydantic AI’s openai-chat: prefix is a provider namespace that keeps this setup on Chat Completions. This page avoids showing Claude or Gemini behind that prefix; use the Respan API or OpenAI SDK gateway pages for provider-neutral Claude and Gemini examples.

See the full model list.