Introducing Structured Outputs in the API

Re:Introducing Structured Outputs in the API by simonw on Tuesday August 06, 2024 @02:40PM (#41173839)

The price decrease is particularly notable because it represents a 50% cut in the price to handle image inputs, across any OpenAI model.

Previously image inputs on GPT-4o-mini were priced the SAME as GPT-4o, so using mini wouldn't actually save you any money on image analysis.

This new gpt-4o-2024-08-06 model is 50% cheaper than both GPT-4o AND GPT-4o-mini for image inputs, as far as I can tell.

UPDATE: I may be wrong about this. The pricing calculator for image inputs on https://openai.com/api/pricing/ doesn't indicate any change in price for the new model.

[ Parent | on HN ]

Re:Introducing Structured Outputs in the API by minimaxir on Tuesday August 06, 2024 @02:43PM (#41173876)

The calculator doesn't account for the fact that there are now two different prices in a given price matrix.

[ Parent | on HN ]

Re:Introducing Structured Outputs in the API by jeffharris on Tuesday August 06, 2024 @04:24PM (#41174929)

yep image input on the new model is also 50% cheaper

and apologies for the outdated pricing calculator ... we'll be updating it later today

[ Parent | on HN ]

Re:Introducing Structured Outputs in the API by brianjking on Tuesday August 06, 2024 @09:20PM (#41177298)

So we can send an image + text to the new structured output model and use the chain of thought schema?

I'm getting an error.

openai.BadRequestError: Error code: 400 - {'error': {'message': 'Invalid content type. image_url is only supported by certain models.', 'type': 'invalid_request_error', 'param': 'messages.[1].content.[1].type', 'code': None}}

[ Parent | on HN ]