Gpt-image-1 vs GPT Image 1

[_j]

Yes, all the costs should be collected together in documentation for the image models. Per-model, even.

• prompt text you send
• reference images you send (edits endpoint)
• price increase for higher input quality
• image outputs you receive, by size and output quality
• with exact token consumption at the pricing instead of rounded off pricing

I attempt to collect prices you will pay step-by-step in this post.

Gpt-image-1 collected pricing information - and why Responses is undocumented

The pricing of gpt-image-1 in documentation is minimized from what actually is billed. Documentation has information all scattered around. Plus there is incomplete and undocumented information in the manner in which Responses consumes chat context and fills the image model with tokens and multiple images after a tool call. Here is a collected pricing to step through an examination of your ultimate costs of using gpt-image-1, vs dall-e-3 which is simply $0.04 per image. gpt-image-1 Pricing …

That forum topic has not been updated for the reduced output price of the newer gpt-image-1-mini model (just like API documentation itself hasn’t been updated for the model by OpenAI). Any attempt at producing helpful developer info here is futile in the forum format - it quickly scrolls from being found due to all the bugs.