feat(ai-openai): add gpt-image-2 to image model meta by AlemTuzlak · Pull Request #625 · TanStack/ai

AlemTuzlak · 2026-05-22T10:06:01Z

Summary

Adds gpt-image-2 to OPENAI_IMAGE_MODELS so it can be selected through the openaiImage adapter (generate({ adapter: openaiImage(...), model: 'gpt-image-2', ... }))
Reuses the gpt-image-1 provider-options shape (quality, background, output_format, output_compression, moderation, partial_images) and size set (1024x1024, 1536x1024, 1024x1536, auto); the OpenAI docs for gpt-image-2 expose the same v1/images/generations + v1/images/edits endpoints with the same request parameters
Extends validateImageSize, validateBackground, and validatePrompt (32 000-char limit) to recognize the new model
Refreshes packages/typescript/ai/skills/ai-core/media-generation/SKILL.md and docs/media/image-generation.md to list gpt-image-2
Includes a minor changeset for @tanstack/ai-openai

Pricing source: OpenAI gpt-image-2 model page. Token-based pricing recorded in ModelMeta is text-input $5 / cached $1.25 / image-output $30 per 1M tokens; the schema does not have a separate field for the $8 image-input-token rate (same limitation as the existing gpt-image-1 entry).

Test plan

pnpm --filter @tanstack/ai-openai test:types
pnpm --filter @tanstack/ai-openai test:eslint (no new warnings/errors)
E2E coverage uses the existing image-generation spec running on gpt-image-1; the adapter call path is unchanged for gpt-image-2, so no new fixture was added. Add one if reviewers want gpt-image-2 exercised in CI.

Summary by CodeRabbit

New Features
- Added support for OpenAI's gpt-image-2 model for image generation, available via the existing image adapter with the same options and sizes as current OpenAI image models.
Documentation
- Updated docs to include gpt-image-2 in model options, sizes, availability, and adapter listings.
Bug Fixes
- Restored web fetch capability for OpenRouter chat models so web-fetching tools remain available.

coderabbitai · 2026-05-22T10:06:16Z

📝 Walkthrough

Walkthrough

Adds OpenAI gpt-image-2 model support: model metadata and export, provider option types and validation updates to accept gpt-image-2, documentation and changeset entries, and a separate fix restoring web_fetch capability in OpenRouter chat model typings.

Changes

GPT-Image-2 Model Support

Layer / File(s)	Summary
Model metadata and type export `packages/typescript/ai-openai/src/model-meta.ts`	Introduces `GPT_IMAGE_2` constant (name `gpt-image-2`, knowledge cutoff, pricing, supported endpoints) and adds it to `OPENAI_IMAGE_MODELS` so `OpenAIImageModel` includes `gpt-image-2`.
Validation rules and type mappings `packages/typescript/ai-openai/src/image/image-provider-options.ts`	Adds `gpt-image-2` to `OpenAIImageModelProviderOptionsByName` and `OpenAIImageModelSizeByName`; updates `validateImageSize`, `validateBackground`, and `validatePrompt` to recognize `gpt-image-2` (same sizes and 32,000-char prompt limit as other GPT image models).
User-facing and internal documentation `packages/typescript/ai-openai/src/adapters/image.ts`, `docs/media/image-generation.md`, `packages/typescript/ai/skills/ai-core/media-generation/SKILL.md`, `.changeset/openai-gpt-image-2.md`	Updates adapter JSDoc to list `gpt-image-2`, adds `gpt-image-2` to supported sizes and availability (`1-10` images/request) in public docs, updates example to `openaiImage('gpt-image-2')`, and adds a changeset documenting usage and shared provider options.
OpenRouter tool capability typing fix `.changeset/openrouter-web-fetch-tool-capability.md`, `packages/typescript/ai-openrouter/src/model-meta.ts`	Restores `web_fetch` in `OpenRouterChatModelToolCapabilitiesByName` so chat models declare both `web_search` and `web_fetch`.

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~20 minutes

Possibly related PRs

TanStack/ai#582: Related OpenRouter tool-capability typing work restoring web_fetch.

Suggested reviewers

KevinVandy

Poem

🐰 A soft-hop cheer for images now new,
gpt-image-2 joins the creative view.
Sizes and prompts checked, metadata in line,
Docs and changelogs sing—everything's fine.
Hooray from a rabbit, with carrots and code too!

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 inconclusive)

Check name	Status	Explanation	Resolution
Description check	❓ Inconclusive	The PR description is comprehensive and well-structured, covering changes, testing, and release impact. However, the provided description does not follow the template structure with 🎯 Changes, ✅ Checklist, and 🚀 Release Impact sections.	Reformat the description to follow the repository template with proper section headings (## 🎯 Changes, ## ✅ Checklist, ## 🚀 Release Impact) for consistency and clarity.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main change: adding gpt-image-2 to the image model metadata for the ai-openai package, which is the primary objective of this PR.
Docstring Coverage	✅ Passed	Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

📝 Generate docstrings

Create stacked PR
Commit on current branch

🧪 Generate unit tests (beta)

Create PR with unit tests
Commit unit tests in branch feat/openai-gpt-image-2

Warning

There were issues while running some tools. Please review the errors and either fix the tool's configuration or disable the tool if it's a critical failure.

🔧 ESLint

If the error stems from missing dependencies, add them to the package.json file. For unrecoverable errors (e.g., due to private dependencies), disable the tool in the CodeRabbit configuration.

ESLint install failed: lockfile failed supply-chain policy check. Run pnpm install locally to update the lockfile.

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

github-actions · 2026-05-22T10:06:42Z

🚀 Changeset Version Preview

2 package(s) bumped directly, 0 bumped as dependents.

🟨 Minor bumps

Package	Version	Reason
`@tanstack/ai-openai`	0.9.6 → 0.10.0	Changeset

🟩 Patch bumps

Package	Version	Reason
`@tanstack/ai-openrouter`	0.9.6 → 0.9.7	Changeset

nx-cloud · 2026-05-22T10:07:00Z

View your CI Pipeline Execution ↗ for commit c32b43d

Command	Status	Duration	Result
`nx run-many --targets=build --exclude=examples/...`	✅ Succeeded	2s	View ↗

☁️ Nx Cloud last updated this comment at 2026-05-22 10:30:48 UTC

nx-cloud · 2026-05-22T10:07:00Z

View your CI Pipeline Execution ↗ for commit c32b43d

Command	Status	Duration	Result
`nx run-many --targets=build --exclude=examples/...`	✅ Succeeded	8s	View ↗

☁️ Nx Cloud last updated this comment at 2026-05-22 10:06:59 UTC

pkg-pr-new · 2026-05-22T10:07:36Z

Open in StackBlitz

@tanstack/ai

npm i https://pkg.pr.new/@tanstack/ai@625

@tanstack/ai-anthropic

npm i https://pkg.pr.new/@tanstack/ai-anthropic@625

@tanstack/ai-client

npm i https://pkg.pr.new/@tanstack/ai-client@625

@tanstack/ai-code-mode

npm i https://pkg.pr.new/@tanstack/ai-code-mode@625

@tanstack/ai-code-mode-skills

npm i https://pkg.pr.new/@tanstack/ai-code-mode-skills@625

@tanstack/ai-devtools-core

npm i https://pkg.pr.new/@tanstack/ai-devtools-core@625

@tanstack/ai-elevenlabs

npm i https://pkg.pr.new/@tanstack/ai-elevenlabs@625

@tanstack/ai-event-client

npm i https://pkg.pr.new/@tanstack/ai-event-client@625

@tanstack/ai-fal

npm i https://pkg.pr.new/@tanstack/ai-fal@625

@tanstack/ai-gemini

npm i https://pkg.pr.new/@tanstack/ai-gemini@625

@tanstack/ai-grok

npm i https://pkg.pr.new/@tanstack/ai-grok@625

@tanstack/ai-groq

npm i https://pkg.pr.new/@tanstack/ai-groq@625

@tanstack/ai-isolate-cloudflare

npm i https://pkg.pr.new/@tanstack/ai-isolate-cloudflare@625

@tanstack/ai-isolate-node

npm i https://pkg.pr.new/@tanstack/ai-isolate-node@625

@tanstack/ai-isolate-quickjs

npm i https://pkg.pr.new/@tanstack/ai-isolate-quickjs@625

@tanstack/ai-ollama

npm i https://pkg.pr.new/@tanstack/ai-ollama@625

@tanstack/ai-openai

npm i https://pkg.pr.new/@tanstack/ai-openai@625

@tanstack/ai-openrouter

npm i https://pkg.pr.new/@tanstack/ai-openrouter@625

@tanstack/ai-preact

npm i https://pkg.pr.new/@tanstack/ai-preact@625

@tanstack/ai-react

npm i https://pkg.pr.new/@tanstack/ai-react@625

@tanstack/ai-react-ui

npm i https://pkg.pr.new/@tanstack/ai-react-ui@625

@tanstack/ai-solid

npm i https://pkg.pr.new/@tanstack/ai-solid@625

@tanstack/ai-solid-ui

npm i https://pkg.pr.new/@tanstack/ai-solid-ui@625

@tanstack/ai-svelte

npm i https://pkg.pr.new/@tanstack/ai-svelte@625

@tanstack/ai-utils

npm i https://pkg.pr.new/@tanstack/ai-utils@625

@tanstack/ai-vue

npm i https://pkg.pr.new/@tanstack/ai-vue@625

@tanstack/ai-vue-ui

npm i https://pkg.pr.new/@tanstack/ai-vue-ui@625

@tanstack/openai-base

npm i https://pkg.pr.new/@tanstack/openai-base@625

@tanstack/preact-ai-devtools

npm i https://pkg.pr.new/@tanstack/preact-ai-devtools@625

@tanstack/react-ai-devtools

npm i https://pkg.pr.new/@tanstack/react-ai-devtools@625

@tanstack/solid-ai-devtools

npm i https://pkg.pr.new/@tanstack/solid-ai-devtools@625

commit: 65784fa

coderabbitai

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@docs/media/image-generation.md`:
- Line 93: The documentation's OpenAI model overview bullet list is missing
`gpt-image-2` causing inconsistency with the tables; update the overview bullet
list in image-generation.md to include `gpt-image-2` (matching the table row
that lists `gpt-image-2` and its sizes `1024x1024`, `1536x1024`, `1024x1536`,
`auto`) so the intro bullets and the detailed table are consistent.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

Push a commit to this branch (recommended)
Create a new PR with the fixes

ℹ️ Review info

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: 13a5ffb1-ba94-451b-8c3b-1f5b2567f5df

📥 Commits

Reviewing files that changed from the base of the PR and between 27d30c9 and c32b43d.

📒 Files selected for processing (6)

.changeset/openai-gpt-image-2.md
docs/media/image-generation.md
packages/typescript/ai-openai/src/adapters/image.ts
packages/typescript/ai-openai/src/image/image-provider-options.ts
packages/typescript/ai-openai/src/model-meta.ts
packages/typescript/ai/skills/ai-core/media-generation/SKILL.md

Adds `gpt-image-2` to OPENAI_IMAGE_MODELS so it can be used through openaiImage adapters. Reuses the gpt-image-1 provider-options/size shape (quality, background, output_format, output_compression, moderation, partial_images; sizes 1024x1024 / 1536x1024 / 1024x1536 / auto) and extends size + prompt-length validators. Also updates the media-generation skill and image-generation doc page to list the new model.

The model-metadata sync in #623 regenerated `OpenRouterChatModelToolCapabilitiesByName` with `['web_search']` only, which made `webFetchTool()` (added in #611) unassignable to any OpenRouter text adapter and broke the per-model type-safety test. Add `'web_fetch'` back so the existing tests compile.

coderabbitai

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (1)

packages/typescript/ai-openai/src/image/image-provider-options.ts (1)
184-195: 🛠️ Refactor suggestion | 🟠 Major | 🏗️ Heavy lift

Use Zod schemas as the single source of truth for image-model constraints.

packages/typescript/ai-openai/src/image/image-provider-options.ts hard-codes runtime rules in validateImageSize (e.g., validSizes), validateBackground (supportedModels), and validatePrompt (model-specific prompt limits), while OpenAIImageModelSizeByName separately defines/derives model/size constraints—yet this file contains no Zod schemas/imports. Move these model/size/background/prompt rules into Zod and infer the exported types/maps from that schema (to keep runtime and type-level constraints in sync).
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@packages/typescript/ai-openai/src/image/image-provider-options.ts` around
lines 184 - 195, The file currently duplicates model/size/background/prompt
rules across runtime validators and a separate OpenAIImageModelSizeByName type;
replace those hard-coded runtime lists by defining Zod schemas (e.g.,
ImageModelSchema, ImageModelConfigSchema) that declare each model's supported
sizes, backgrounds, and prompt constraints, import z from Zod, infer TypeScript
types via z.infer and derive the OpenAIImageModelSizeByName map from the schema,
then update validateImageSize, validateBackground, and validatePrompt to read
constraints from the Zod-backed config (or validate against the Zod schemas
directly) instead of using hard-coded validSizes/supportedModels/prompt limits
so runtime and type-level rules stay in sync.

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Outside diff comments:
In `@packages/typescript/ai-openai/src/image/image-provider-options.ts`:
- Around line 184-195: The file currently duplicates
model/size/background/prompt rules across runtime validators and a separate
OpenAIImageModelSizeByName type; replace those hard-coded runtime lists by
defining Zod schemas (e.g., ImageModelSchema, ImageModelConfigSchema) that
declare each model's supported sizes, backgrounds, and prompt constraints,
import z from Zod, infer TypeScript types via z.infer and derive the
OpenAIImageModelSizeByName map from the schema, then update validateImageSize,
validateBackground, and validatePrompt to read constraints from the Zod-backed
config (or validate against the Zod schemas directly) instead of using
hard-coded validSizes/supportedModels/prompt limits so runtime and type-level
rules stay in sync.

ℹ️ Review info

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro

Run ID: f365fb03-3b0a-40a2-a6ba-bcddaca7fc49

📥 Commits

Reviewing files that changed from the base of the PR and between c32b43d and 65784fa.

📒 Files selected for processing (8)

.changeset/openai-gpt-image-2.md
.changeset/openrouter-web-fetch-tool-capability.md
docs/media/image-generation.md
packages/typescript/ai-openai/src/adapters/image.ts
packages/typescript/ai-openai/src/image/image-provider-options.ts
packages/typescript/ai-openai/src/model-meta.ts
packages/typescript/ai-openrouter/src/model-meta.ts
packages/typescript/ai/skills/ai-core/media-generation/SKILL.md

✅ Files skipped from review due to trivial changes (5)

packages/typescript/ai-openai/src/adapters/image.ts
.changeset/openrouter-web-fetch-tool-capability.md
packages/typescript/ai/skills/ai-core/media-generation/SKILL.md
docs/media/image-generation.md
.changeset/openai-gpt-image-2.md

coderabbitai Bot reviewed May 22, 2026

View reviewed changes

Comment thread docs/media/image-generation.md

AlemTuzlak added 2 commits May 22, 2026 12:24

AlemTuzlak force-pushed the feat/openai-gpt-image-2 branch from c32b43d to 65784fa Compare May 22, 2026 10:29

coderabbitai Bot reviewed May 22, 2026

View reviewed changes

AlemTuzlak merged commit ebdad7f into main May 22, 2026
10 checks passed

AlemTuzlak deleted the feat/openai-gpt-image-2 branch May 22, 2026 10:43

github-actions Bot mentioned this pull request May 22, 2026

ci: Version Packages #627

Merged

coderabbitai Bot mentioned this pull request May 22, 2026

docs: refresh README and package metadata #626

Merged

4 tasks

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

feat(ai-openai): add gpt-image-2 to image model meta#625

feat(ai-openai): add gpt-image-2 to image model meta#625
AlemTuzlak merged 2 commits into
mainfrom
feat/openai-gpt-image-2

AlemTuzlak commented May 22, 2026 •

edited by coderabbitai Bot

Loading

Uh oh!

coderabbitai Bot commented May 22, 2026 •

edited

Loading

Walkthrough

Changes

Estimated code review effort

Possibly related PRs

Suggested reviewers

Poem

❌ Failed checks (1 inconclusive)

Uh oh!

github-actions Bot commented May 22, 2026 •

edited

Loading

Uh oh!

nx-cloud Bot commented May 22, 2026 •

edited

Loading

Uh oh!

nx-cloud Bot commented May 22, 2026

Uh oh!

pkg-pr-new Bot commented May 22, 2026 •

edited

Loading

Uh oh!

coderabbitai Bot left a comment

Uh oh!

Uh oh!

coderabbitai Bot left a comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

AlemTuzlak commented May 22, 2026 • edited by coderabbitai Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Test plan

Summary by CodeRabbit

Uh oh!

coderabbitai Bot commented May 22, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

Possibly related PRs

Suggested reviewers

Poem

❌ Failed checks (1 inconclusive)

Uh oh!

github-actions Bot commented May 22, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

🚀 Changeset Version Preview

🟨 Minor bumps

🟩 Patch bumps

Uh oh!

nx-cloud Bot commented May 22, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

nx-cloud Bot commented May 22, 2026

Uh oh!

pkg-pr-new Bot commented May 22, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

coderabbitai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

coderabbitai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

AlemTuzlak commented May 22, 2026 •

edited by coderabbitai Bot

Loading

coderabbitai Bot commented May 22, 2026 •

edited

Loading

github-actions Bot commented May 22, 2026 •

edited

Loading

nx-cloud Bot commented May 22, 2026 •

edited

Loading

pkg-pr-new Bot commented May 22, 2026 •

edited

Loading