Model Details
Where is GPT-4 1106 Vision Preview a perfect fit?
gpt-4-1106-vision-preview introduced image input capabilities to GPT-4, making it ideal for early multimodal use cases. Ideal for:
- Image analysis and caption generation
- Extracting structured data from screenshots, documents, or UI images
- Visual question answering and reasoning tasks
- Combining text and image inputs for richer interactions
- Prototyping multimodal applications before GPT-4o
- Early-stage computer vision + language integration workflows
- Image analysis and caption generation
- Extracting structured data from screenshots, documents, or UI images
- Visual question answering and reasoning tasks
- Combining text and image inputs for richer interactions
- Prototyping multimodal applications before GPT-4o
- Early-stage computer vision + language integration workflows
Quick Model Estimate
Your GPT-4 1106 Vision Preview Cost Estimate
💰 Total Cost
—
for 1000 input + 1000 output tokens
📥 Input (1000 × $10.000000)
—
📤 Output (1000 × $30.000000)
—
Cost Breakdown
📥 Input
📤 Output
At the last price OpenAI charged, before it stopped on 6th Dec 2024. No longer on offer.
Pricing
No provider we track currently offers GPT-4 1106 Vision Preview.
No longer offered by
The last prices each provider charged for GPT-4 1106 Vision Preview before it stopped offering it. These are no longer on offer. Each row links to that provider's price history.
Recent changes
When GPT-4 1106 Vision Preview was newly listed on a provider, moved to legacy or deprecated, or retired.
-
Retired
OpenAI retired GPT-4 1106 Vision Preview, with GPT-4o as the suggested replacement.
Other Models in the GPT-4 Family
FAQs about GPT-4 1106 Vision Preview
What is GPT-4 1106 Vision Preview's context window?
GPT-4 1106 Vision Preview has a context window of 128,000 tokens.
Is GPT-4 1106 Vision Preview still available?
GPT-4 1106 Vision Preview is deprecated and was retired on 6 December 2024. The replacement is GPT-4o.