Always access the OpenAI platform when using the DeepSeek model with LitellmModel

[qianxiaoming]

When using the DeepSeek model with LitellmModel, it always requires accessing the OpenAI platform:

import asyncio
import os
from agents import Agent, Runner
from agents.extensions.models.litellm_model import LitellmModel

os.environ["DEEPSEEK_API_KEY"] = "sk-74a*****************f131"

async def main():
    model = LitellmModel(model="deepseek/deepseek-chat", api_key=os.environ["DEEPSEEK_API_KEY"])

    agent = Agent(
        name="Assistant",
        instructions="You only respond in haikus.",
        model=model,
    )

    result = await Runner.run(agent, "Tell me about recursion in programming.")
    print(result.final_output)

if __name__ == "__main__":
    asyncio.run(main())

This script output these:

[non-fatal] Tracing client error 401: {
  "error": {
    "message": "Incorrect API key provided: sk-74a47***********************f131. You can find your API key at https://platform.openai.com/account/api-keys.",
    "type": "invalid_request_error",
    "param": null,
    "code": "invalid_api_key"
  }
}
Recursion calls self,  
Like a loop but with functions,  
Base case ends the chain.
[non-fatal] Tracing client error 401: {
  "error": {
    "message": "Incorrect API key provided: sk-74a47***********************f131. You can find your API key at https://platform.openai.com/account/api-keys.",
    "type": "invalid_request_error",
    "param": null,
    "code": "invalid_api_key"
  }
}

Debug information

• Agents SDK version: (v0.0.16)
• Python version (3.11)