What is the maximum number of images that a single request may contain with GPT4o accessed via openai.com's API?

Question

What is the maximum number of images that a single request may contain with GPT4o accessed via openai.com's API?

I don't see any limit about the number of images specified on the official documentation:

Answer 1

It appears that the limit is based on the number of tokens the image costs to process:

As mentioned in the OpenAI vision documentation How do rate limits for GPT-4 with Vision work?:

We process images at the token level, so each image we process counts towards your tokens per minute (TPM) limit. See the calculating costs section for details on the formula used to determine token count per image.

The vision documentation shows that the token cost of an image depends on its size and the level of detail desired in the analysis as mentioned here:

Image inputs are metered and charged in tokens, just as text inputs are. The token cost of a given image is determined by two factors: its size, and the detail option on each image_url block. All images with detail: low cost 85 tokens each. detail: high images are first scaled to fit within a 2048 x 2048 square, maintaining their aspect ratio. Then, they are scaled such that the shortest side of the image is 768px long. Finally, we count how many 512px squares the image consists of. Each of those squares costs 170 tokens. Another 85 tokens are always added to the final total.

Here are some examples demonstrating the above.

• A 1024 x 1024 square image in detail: high mode costs 765 tokens
  • 1024 is less than 2048, so there is no initial resize.
  • The shortest side is 1024, so we scale the image down to 768 x 768.
  • 4 512px square tiles are needed to represent the image, so the final token cost is 170 * 4 + 85 = 765.
• A 2048 x 4096 image in detail: high mode costs 1105 tokens
  • We scale down the image to 1024 x 2048 to fit within the 2048 square.
  • The shortest side is 1024, so we further scale down to 768 x 1536.
  • 6 512px tiles are needed, so the final token cost is 170 * 6 + 85 = 1105.
• A 4096 x 8192 image in detail: low most costs 85 tokens
  • Regardless of input size, low detail images are a fixed cost.

Answer 2

As of the latest information available, the maximum number of images that a single request may contain when accessing GPT-4o via OpenAI's API is 16 images. This limit ensures optimal performance and processing capabilities within the constraints of the model and API infrastructure.