Basic text generation

Your first ai_sdk call – generate a greeting with one function.

This is the hello-world of ai_sdk. You only need two imports: the provider factory and the generate_text helper.

1. Install dependencies

   pip install ai-sdk openai
   

   Make sure the environment variable OPENAI_API_KEY is set.
2. Create a model instance & generate text

   hello.py

   from ai_sdk import openai, generate_text
   
   # 1. Re-use the model across calls
   
   model = openai("gpt-4.1-mini")
   
   # 2. Generate a friendly greeting
   
   res = generate_text(model=model, prompt="Say hi to the world in one sentence")
   print(res.text)
   
   

   Expected output (your wording may vary):

   Hello, world – great to see you!
   

What just happened?

1. openai() returns a LanguageModel wrapper that talks to the OpenAI Chat Completions API.
2. generate_text() sends the prompt, waits for the response, and returns a typed GenerateTextResult.

print(res.finish_reason)  # "stop"
print(res.usage)         # TokenUsage(prompt_tokens=7, completion_tokens=9, ...)

That’s it – no async boilerplate, no JSON parsing, no provider-locked SDK calls.