https://developers.openai.com/api/docs/guides/image-generation
https://developers.openai.com/api/docs/pricing#image-generation
Calculating costs:
System Card:
ChatGPT Images 2.0 System Card - OpenAI Deployment Safety Hub
Well that gives me hope for all the time I spent coding for that style of imageā¦
thatās a lot of words right, right there
API notes
Quality:low = less expensive; Quality: medium, high = more expensive
2.0 provides much more arbitrary image sizing, as long as specified at 16px intervals.
A maximum of 3:1 ratio. Noteworthy for sharers is making an image for the maximum 1:1 native Discourse forum size 690x500 (1.38 ratio) is too small and not quantized correctly; youād need 53% more area to meet the minimum. 1376x992 or 1376x1008 for a doubling; or 1024x752.
That demonstrates that you might want to think about tooling to offer end users or to AI, that you provide alternately, adaptively, one dimension and a ratio or a ādesiredā->āoutputā resolution that can then be āsteppedā and clipped.
No direct formula is provided for the passes and upscaling and dimensional expansion billing. For example, if we consider images as 16px tiles or patches, 1024x1024 would be 64x64 = 4096, yet that bill is 7024 tokens at high quality. Time to dig into the doc siteās Javascript and retrieve what should have been delivered in documentation.
https://developers.openai.com/api/docs/guides/image-generation#size-and-quality-options
Weirdness with the billing calculator that must be explained formulaically:
1024x1024 = 7024 tokens
1536x1024 = 5488 tokens
1792x1024 = 5063 tokens (also DALL-E 3ās wide size)
Does quality suffer at a larger image and yet lower billing? Or is there error to be discovered (as with almost every prior image product so farā¦)?
Double that 1792 for 4x the area?
3584x2048 = 12329 tokens