Source from repo

Image Generation (AI SDK)

Generate images via OpenAI, Google, OpenRouter, DashScope, Jimeng, Seedream, and Replicate APIs with batch support.

jimliuGitHub jimliuSource repo Original GitHub link Publisher page

Files

Skill

n/a

Size

353.2 KB

Entrypoint

SKILL.md

Format

git-repo

Open file

references/providers/openrouter.md

Syntax-highlighted preview of this file as included in the skill package.

Rendered Source

markdown20 linesFree

references/providers/openrouter.md

1# OpenRouter
2 
3Read when the user picks `--provider openrouter`. Default model is `google/gemini-3.1-flash-image`.
4 
5## Common Models
6 
7Use full OpenRouter model IDs:
8 
9- `google/gemini-3.1-flash-image` (recommended — supports image output and reference-image workflows)
10- `google/gemini-2.5-flash-image-preview`
11- `black-forest-labs/flux.2-pro`
12- Any other OpenRouter image-capable model ID
13 
14## Behavior Notes
15 
16- OpenRouter image generation uses `/chat/completions`, not the OpenAI `/images` endpoints
17- `--ref` requires a multimodal model that supports both image input and image output
18- `--imageSize` maps to `imageGenerationOptions.size`
19- `--size <WxH>` is converted to the nearest supported OpenRouter size, and the aspect ratio is inferred when possible
20

Image Generation (AI SDK)

references/providers/openrouter.md

Preparing the source view

Image Generation (AI SDK)

references/providers/openrouter.md