GPT-4 Turbo Vision Preview
gpt-4-turbo-vision-previewPricing
List prices at Azure OpenAI, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $11.00 | $33.00 |
What it costs a month
At Azure OpenAI list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$5,775
- RAG over documents2,000 requests a day, 8K in / 0.6K out$6,468
- Coding agent1,000 requests a day, 40K in / 2K out$15,180
- Overnight batch20,000 requests a day, 4K in / 0.4K out$34,320
Where to run it
1 host serve GPT-4 Turbo Vision Preview. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Azure OpenAICloud gpt-4-turbo-vision-preview | $11.00 / $33.00 | gpt-4-turbo-vision-preview |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- TextImages
- Produces
- Text
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
No host sells it for less than Azure OpenAI.
Smaller OpenAI models
- 3% less
- 71% less
- 76% less
Other frontier labs
- 3% less
- 76% less
- 82% less
- 52% less
Open-weight picks
- 73% less
- 76% less
- 86% less
- 88% less
Call it
Using Azure OpenAI's API.
from litellm import completion
response = completion(
model="azure/gpt-4-turbo-vision-preview",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does GPT-4 Turbo Vision Preview cost?
On Azure OpenAI, GPT-4 Turbo Vision Preview costs $11.00 per million input tokens and $33.00 per million output tokens.
Which APIs offer GPT-4 Turbo Vision Preview?
GPT-4 Turbo Vision Preview runs on 1 API: Azure OpenAI.
What is GPT-4 Turbo Vision Preview's context window?
128K tokens, with up to 4K tokens in one reply.
Is GPT-4 Turbo Vision Preview being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to GPT-4 Turbo Vision Preview?
Models that cost less and keep most of what it can do: GPT-6.2 Astra on OpenAI (3% less), Claude Fable 5.2 on Anthropic (3% less), Gemini 4 Carbon on Google AI Studio (76% less) and Command A Plus on AIHubMix (73% less). Savings are on a mix of 3 input tokens to 1 output token.
What is GPT-4 Turbo Vision Preview's API model id?
Use gpt-4-turbo-vision-preview with Azure OpenAI.
Sources
Raw catalog entry for gpt-4-turbo-vision-preview on Azure OpenAI
{
"input_cost_per_token": 0.000011,
"litellm_provider": "azure",
"max_input_tokens": 128000,
"max_output_tokens": 4096,
"mode": "chat",
"output_cost_per_token": 0.000033,
"source": "https://azure.microsoft.com/en-us/pricing/details/azure-openai/",
"supports_tool_choice": true,
"supports_vision": true
}