GPT-4o-mini high vision cost

[SomebodySysop]

@bobartig

This doesn’t seem right, despite what OpenAI’s head of stuff said.

Agreed.

@bobartig

Anthropic’s Claude 3 models have consistent token usage across models for image processing, meaning for consumers, it is an order of magnitude better to be using Claude 3 Haiku over gpt-4o mini right now for low-cost vision applications.

Or, Gemini Flash/Pro:

Super-high token usage with gpt-4o-mini and image

But, this is the first call: For doing nothing more than extracting the text from this image: [image] 14,000 tokens charged for 600 characters of text? This is the request in the Playground: https://platform.openai.com/playground/chat?models=gpt-4o-mini&preset=preset-vjZ8QKzF1RaISBGbWkExyRNk And, just to compare Apples to Apples: [high token usage - gemini comparison] Gemini Pro charges 601 tokens for the same exact prompt and image. I suspect Gemini Flash is even cheaper.