Last refreshed 2026-04-27. Next refresh: weekly.
Why use GPT-4 Vision Preview on Azure OpenAI?
Azure OpenAI offers GPT-4 Vision 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.
Input / 1M
$10.00
Output / 1M
$40.00
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-vision-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-vision-preview", # your deployment name
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- gpt-4-vision-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.
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $10.00 |
| Output tokens | $40.00 |
Capabilities
VisionMultimodalCode Execution
FAQ
What does GPT-4 Vision Preview cost on Azure OpenAI?
On Azure OpenAI, GPT-4 Vision Preview costs $10 per 1M input tokens and $40.00 per 1M output tokens.
What is the context window for GPT-4 Vision Preview on Azure OpenAI?
GPT-4 Vision Preview supports a 128,000 token context window on Azure OpenAI.
Who created GPT-4 Vision Preview?
GPT-4 Vision Preview was created by OpenAI as part of the GPT-4 model family.
Is GPT-4 Vision Preview open source?
GPT-4 Vision Preview's open source status is unknown in the seed data.
Get Started
Model Specs
Released2023-11-06
Parameters1.76T (8x222B MoE)*
Context128K
ArchitectureMixture of Experts
Knowledge cutoff2023-04