Last refreshed 2026-09-29. Next refresh: weekly.
Why use davinci on Azure OpenAI?
Azure OpenAI offers davinci with pay-as-you-go pricing at $2.00/1M input tokens. Azure OpenAI Service hosts OpenAI's GPT-4o, GPT-4, GPT-3.5, and embedding models on Microsoft Azure with enterprise SLAs.
Setup recipe
Python + curlpip install openaiexport AZURE_OPENAI_API_KEY=...import os
from openai import AzureOpenAI
client = AzureOpenAI(
azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"], # e.g. https://{resource}.openai.azure.comdavinciRequest example
import os
from openai import AzureOpenAI
client = AzureOpenAI(
azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"], # e.g. https://{resource}.openai.azure.com
api_key=os.environ["AZURE_OPENAI_API_KEY"],
api_version="2024-02-01"
)
response = client.chat.completions.create(
model="davinci", # your deployment name
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- davinci is your Azure deployment name, not the underlying model name. Deployment names are set when you deploy a model in Azure AI Foundry / Azure OpenAI Studio.
- The examples expect AZURE_OPENAI_API_KEY; rename it only if your application config maps the new variable.
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $2.00 |
| Output tokens | $2.00 |
Capabilities
No model capability flags are currently sourced.
About davinci
Davinci, a sophisticated model within OpenAI's GPT-3 family, is renowned for its ability to handle complex tasks with exceptional proficiency 46. It excels in understanding nuanced language, solving logical puzzles, and generating creative content, making it highly effective for tasks like explaining character motives and performing detailed summarizations 47. While it is more costly and computationally intensive than models like Curie or Ada, its superior performance in interpreting complex language tasks justifies these demands 1.