Last refreshed 2026-05-19. Next refresh: weekly.
Why use GPT-4 Turbo Preview on Azure OpenAI?
Azure OpenAI offers GPT-4 Turbo Preview with pay-as-you-go pricing at $10.00/1M input tokens. Azure OpenAI Service hosts OpenAI's GPT-4o, GPT-4, GPT-3.5, and embedding models on Microsoft Azure with enterprise SLAs.
Compare GPT-4 Turbo Preview across 3 providers to find the best fit for your use caseInput / 1M
$10.00
Output / 1M
$30.00
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install openaiAuth
export AZURE_OPENAI_API_KEY=...Call
import os
from openai import AzureOpenAI
client = AzureOpenAI(
azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"], # e.g. https://{resource}.openai.azure.comModel ID
gpt-4-turbo-previewRequest 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="gpt-4-turbo-preview", # your deployment name
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- gpt-4-turbo-preview 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.
Compare GPT-4 Turbo Preview Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| OpenAI API | $10.00 | $30.00 |
| Azure OpenAI | $10.00 | $30.00 |
| OpenRouter | $10.00 | $30.00 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $10.00 |
| Output tokens | $30.00 |
Capabilities
VisionStructured OutputsCode Execution
About GPT-4 Turbo Preview
GPT-4 Turbo Preview is OpenAI's GPT-4 model. It is deprecated (originally released 2023-11-06); use it only for reproducing earlier results or evaluating drift over time.
Get Started
Model Specs
Released2023-11-06
Parameters1.76T (8x222B MoE)*
Context128k
ArchitectureMixture of Experts
Knowledge cutoff2023-12