{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreiaox56qrd3aowbp6ehvhmlc7vspds4k6qeg4houszueuyn7gu3hu4",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mp463yxbpyc2"
  },
  "path": "/t/openai-must-document-the-input-image-pricing-of-gpt-image-2-so-i-did/1382940#post_6",
  "publishedAt": "2026-06-25T08:40:20.000Z",
  "site": "https://community.openai.com",
  "textContent": "# Prior model prompt overbilling on “edits”\n\nOn prior models, OpenAI seems to be over-billing for input text on the edits endpoint\n\n  * On `v1/images/generations`, all models have the same 6 token overhead - your sent prompt as measured by tiktoken with o200k_base, plus `6` tokens (that is not documented, but at least uniform).\n\n  * On `/v1/images/edits`, however, that figure grows. There is a significant leak of the input image size into the input text tokens.\n\n\n\n\n## gpt-image-1.5 1024x1024 inputs\n\n  * Send 13 tokens of prompt with one 1024x1024 input, size:1024x1024: get billed for 28 tokens. Over by 22. Over expectation by 16.\n\n  * Send 13 tokens of prompt with one 1024x1024 input, size:1024x1536: get billed for 35 tokens. Over expectation by 16.\n\n  * Send 13 tokens of prompt with _two_ 1024x1024 input, size:1024x1024: get billed for 50 tokens. Over expectation by 30.\n\n\n\n\n## gpt-image-1.5 1:3 ratio inputs\n\n  * Send 12 tokens of prompt with one 480x1408 input, size:1024x1536: get billed for 57 tokens.\n  * Send 13 tokens of prompt with two 480x1408 input, size:1024x1536: get billed for **94 tokens**. Text token bill significantly exceeding actual prompt.\n\n\n\n### Nowhere is this explained and nowhere is it reasonable to send input images and get extra billing for text, differing by the size.\n\n* * *\n\nImage inputs to gpt-image-1.5 still use the “tiles” formula and pricing of gpt-image-1, (undocumented also), with the addition of its billed `output.text_tokens` for reasoning.",
  "title": "OpenAI *must* document the input image pricing of gpt-image-2 (so I did)"
}