docs(image): document gpt-image-2 / gpt-image-2-edit quality parameter#263
Open
Dervlex wants to merge 3 commits into
Open
docs(image): document gpt-image-2 / gpt-image-2-edit quality parameter#263Dervlex wants to merge 3 commits into
quality parameter#263Dervlex wants to merge 3 commits into
Conversation
The `quality` parameter (`low | medium | high`, default `high`) is now honored end-to-end for `gpt-image-2` and `gpt-image-2-edit` by web, public API, and SDK clients — no opt-in header required. Mobile clients remain on the legacy fixed price schedule until they ship their own quality UI. Adds: - Quality-tier explanation + example to /image/generate, /image/edit, and /image/multi-edit endpoint docs. - `model_spec.pricing.quality` matrix example to /models endpoint doc. - Quality-tier pricing tables (1K/2K/4K × low/medium/high) to the pricing overview, with prices computed from the live FAL base rates plus the standard 1.15× markup. - Note in the image-models landing page pointing to the matrix. - `quality` property on `GenerateImageRequest`, `EditImageRequest`, `MultiEditImageRequest`, and `MultiEditImageMultipartRequest` in swagger.yaml. (The OpenAI-compat `/v1/image/generations` schema keeps its passthrough-only `quality` description — that endpoint still ignores the field for parity with OpenAI.) Replaces the earlier draft branch (`docs/gpt-image-2-dynamic-pricing`) which described an unimplemented token-based pricing model. This branch matches what production actually exposes.
Contributor
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Workflows to automatically generate PRs for you. |
…2K" footnote API docs are about what the API does, not which clients call it. The mobile reference also carried a quantitatively wrong claim — legacy fixed pricing is ~$0.01 above dynamic-`high` for `gpt-image-2` at *all three* resolutions (not just 1K/2K) and *identical* for `gpt-image-2-edit` at every resolution. Re-frames the four Info blocks (generate, edit, multi-edit, pricing overview) and the prose in the Models endpoint as API-and-SDK-centric, with no false claim about a specific client's bill.
Resolves swagger.yaml conflict by accepting main's version. The outerface auto-generated swagger (commit 05eb744 "Update swagger.yaml from outerface deployment") already adds the `quality` parameter to the three request schemas that need it (GenerateImageRequest, EditImageRequest, MultiEditImageRequest) and additionally adds: - `model_spec.pricing.quality` per-(resolution, quality) pricing matrix - `model.quality.default` and `model.quality.options` per-model fields My hand-written swagger additions in 60756d5 covered only the three request schemas and would have been overwritten by the next outerface deployment anyway (swagger.yaml is auto-generated upstream). Dropping them in favour of the bot-generated version is the right call. The .mdx documentation changes (the actual value of this PR) are unaffected.
sabrinaaquino
approved these changes
May 22, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
The
qualityparameter (low | medium | high, defaulthigh) is now honored end-to-end forgpt-image-2andgpt-image-2-editby web, public API, and SDK clients — no opt-in header required. Mobile clients remain on the legacy fixed price schedule until they ship their own quality UI.Adds:
model_spec.pricing.qualitymatrix example to /models endpoint doc.qualityproperty onGenerateImageRequest,EditImageRequest,MultiEditImageRequest, andMultiEditImageMultipartRequestin swagger.yaml. (The OpenAI-compat/v1/image/generationsschema keeps its passthrough-onlyqualitydescription — that endpoint still ignores the field for parity with OpenAI.)Replaces the earlier draft branch (
docs/gpt-image-2-dynamic-pricing) which described an unimplemented token-based pricing model. This branch matches what production actually exposes.