egaki 0.2.0 → 0.3.0

package/CHANGELOG.md

@@ -2,6 +2,38 @@
 
 All notable changes to this project will be documented in this file.
 
+## 0.3.0
+
+1. **Google Vertex AI provider** — use Google Cloud billing instead of AI Studio by
+   prefixing model IDs with `vertex/`:
+
+   ```bash
+   egaki login --provider vertex --key AIza...
+   egaki image "product shot on marble" -m vertex/imagen-4.0-generate-001 -o product.png
+   egaki image "editorial portrait" -m vertex/gemini-3.1-flash-image-preview --aspect-ratio 4:5
+   egaki video "storm over mountains" -m vertex/veo-3.1-fast-generate-001 --duration 6 -o storm.mp4
+   ```
+
+   Bare model IDs (e.g. `imagen-4.0-generate-001`) continue to route through Google AI
+   Studio as before. `vertex/` prefix routes through `@ai-sdk/google-vertex` using your
+   `GOOGLE_VERTEX_API_KEY`. The two providers are fully independent — having one key does
+   not affect the other.
+
+   Supported Vertex models:
+   - `vertex/imagen-4.0-generate-001`, `vertex/imagen-4.0-ultra-generate-001`, `vertex/imagen-4.0-fast-generate-001`
+   - `vertex/gemini-2.5-flash-image`, `vertex/gemini-3-pro-image-preview`, `vertex/gemini-3.1-flash-image-preview`
+   - `vertex/veo-3.1-generate-001`, `vertex/veo-3.1-fast-generate-001`
+
+2. **`egaki models --provider vertex`** — list only Vertex models:
+
+   ```bash
+   egaki models --provider vertex
+   ```
+
+3. **Fixed confusing error for Vertex without a key** — if you attempt a `vertex/` model
+   without a `GOOGLE_VERTEX_API_KEY` configured, you now get a clear error pointing you
+   to set one up instead of a cryptic upstream failure.
+
 ## 0.2.0
 
 1. **New `egaki video` command** — generate videos from text prompts or still images.

package/README.md

@@ -55,6 +55,14 @@ egaki image "cyberpunk alley at night" --aspect-ratio 16:9
 egaki image "polaroid-style travel photo" --aspect-ratio 4:5
 ```
 
+### Use Google Cloud billing via Vertex AI
+
+```bash
+egaki login --provider vertex --key AIza...
+egaki image "editorial sneaker photo on white seamless" -m vertex/imagen-4.0-generate-001 -o sneaker.png
+egaki video "storm over mountains" -m vertex/veo-3.1-fast-generate-001 --duration 6 -o storm.mp4
+```
+
 ### Pipe image output to other tools
 
 ```bash
@@ -67,7 +75,7 @@ egaki image "flat icon of a fox" --stdout | magick - -resize 512x512 fox-icon.pn
 
 ```bash
 egaki video "a paper boat drifting on a calm lake at sunrise" -o boat.mp4
-egaki video "timelapse of a stormy sea, cinematic" -m google/veo-3.1-generate-001 --duration 8 -o storm.mp4
+egaki video "timelapse of a stormy sea, cinematic" -m veo-3.1-generate-001 --duration 8 -o storm.mp4
 ```
 
 ### Generate with a cheap model
@@ -88,7 +96,7 @@ egaki video "slowly animate the clouds" --input photo.jpg -m klingai/kling-v2.6-
 
 ```bash
 egaki video "aerial drone shot over a city grid" \
-  -m google/veo-3.1-fast-generate-001 \
+  -m veo-3.1-fast-generate-001 \
   --aspect-ratio 16:9 \
   --resolution 1080p \
   --duration 6 \
@@ -175,8 +183,9 @@ egaki image "mascot variations, flat vector look" \
 
 | Model ID | Best for | Example command |
 | --- | --- | --- |
-| `google/veo-3.1-generate-001` | Highest quality video with audio, up to 4K | `egaki video "rainy Tokyo street at night" -m google/veo-3.1-generate-001 --duration 8 -o tokyo.mp4` |
-| `google/veo-3.1-fast-generate-001` | Fast Veo with 720p–4K, good for iteration | `egaki video "abstract paint patterns" -m google/veo-3.1-fast-generate-001 --duration 5 -o paint.mp4` |
+| `veo-3.1-generate-001` | Highest quality video with audio, up to 4K | `egaki video "rainy Tokyo street at night" -m veo-3.1-generate-001 --duration 8 -o tokyo.mp4` |
+| `veo-3.1-fast-generate-001` | Fast Veo with 720p–4K, good for iteration | `egaki video "abstract paint patterns" -m veo-3.1-fast-generate-001 --duration 5 -o paint.mp4` |
+| `vertex/veo-3.1-generate-001` | Same as above, routed through Vertex AI | `egaki video "rainy Tokyo street" -m vertex/veo-3.1-generate-001 --duration 8 -o tokyo.mp4` |
 | `klingai/kling-v2.5-turbo-t2v` | Cheap, fast Kling text-to-video | `egaki video "a paper boat on a pond" -m klingai/kling-v2.5-turbo-t2v --duration 5 -o boat.mp4` |
 | `bytedance/seedance-v1.5-pro` | Bytedance, audio support, three resolutions | `egaki video "timelapse of clouds above mountains" -m bytedance/seedance-v1.5-pro -o clouds.mp4` |
 | `xai/grok-imagine-video` | xAI video generation, cheap for short clips | `egaki video "a dog catching a frisbee" -m xai/grok-imagine-video --duration 3 -o dog.mp4` |
@@ -189,6 +198,7 @@ egaki image "mascot variations, flat vector look" \
 - **BFL image models (`flux-*`)**: Kontext/Pro variants via AI Gateway subscription
 - **Recraft models (`recraft-*`)**: v2/v3/v4 families available via AI Gateway subscription
 - **xAI image models (`grok-imagine-*`)**: Grok image generation via AI Gateway subscription
+- **Vertex models (`vertex/*`)**: same models as Google AI Studio, routed through Vertex AI / Google Cloud billing
 - **Google Veo video models**: up to 4K, audio optional, duration 4–8s
 - **Kling video models**: mode (std/pro), audio on v2.6+, image-to-video support
 - **Bytedance Seedance**: 480p–1080p, audio support on v1.5-pro
@@ -200,6 +210,7 @@ egaki supports **both** authentication modes:
 
 - **BYOK (bring your own keys):** add provider keys with `egaki login` per provider.
 - **Egaki subscription:** use one `egaki_...` key to access all supported models without managing keys for each provider.
+- **Google vs Vertex:** bare model IDs (e.g. `imagen-4.0-generate-001`) use Google AI Studio. Prefix with `vertex/` (e.g. `vertex/imagen-4.0-generate-001`) to route through Vertex AI / Google Cloud billing.
 
 ```bash
 # Subscribe and get a checkout URL
@@ -211,8 +222,9 @@ egaki subscribe --plan pro
 # Save your Egaki key after checkout
 egaki login --provider egaki --key egaki_...
 
-# BYOK example (direct provider key)
+# BYOK examples (direct provider keys)
 egaki login --provider google --key AIza...
+egaki login --provider vertex --key AIza...
 
 # Check subscription usage / cancel
 egaki usage

package/dist/cli.js

@@ -55,6 +55,7 @@ cli
     .example('egaki login')
     .example('# Non-interactive login with flags')
     .example('egaki login --provider google --key AIza...')
+    .example('egaki login --provider vertex --key AIza...')
     .example('# Pipe key from stdin (useful in CI/scripts)')
     .example('echo "AIza..." | egaki login --provider google')
     .example('# Show configured providers')
@@ -170,6 +171,8 @@ cli
     .example('egaki image "fill with flowers" --input photo.jpg --mask mask.png')
     .example('# Generate with Gemini multimodal at 4K')
     .example('egaki image "dreamy landscape" -m gemini-2.5-flash-image --image-size 4K')
+    .example('# Route through Vertex AI (Google Cloud billing)')
+    .example('egaki image "product photo on marble" -m vertex/imagen-4.0-generate-001')
     .example('# Generate multiple images')
     .example('egaki image "abstract art" -n 4 -o art.png')
     .example('# Pipe to another tool')
@@ -250,6 +253,8 @@ cli
     .example('egaki video "A paper airplane gliding through clouds" -o airplane.mp4')
     .example('# Generate with Veo model + duration')
     .example('egaki video "cinematic rainy street at night" -m veo-3.1-fast-generate-001 --duration 6')
+    .example('# Route through Vertex AI (Google Cloud billing)')
+    .example('egaki video "storm over mountains" -m vertex/veo-3.1-fast-generate-001 --duration 6')
     .example('# Image-to-video (model support required)')
     .example('egaki video "animate subtle camera pan" --model luma-ray-2 --input frame.png -o animated.mp4')
     .example('# Generate multiple videos')
@@ -385,7 +390,10 @@ async function generateWithImageModel({ prompt, model, outputPath, count, aspect
     const imagePrompt = inputImages.length > 0
         ? { text: prompt, images: inputImages, ...(maskImage ? { mask: maskImage } : {}) }
         : prompt;
+    const config = getModelConfig(model);
     const imageModel = await createImageModel(model);
+    // Use the correct providerOptions key based on provider (google vs vertex)
+    const providerOptionsKey = config.provider === 'vertex' ? 'vertex' : 'google';
     if (!stdout) {
         console.error(pc.cyan('Generating...'));
     }
@@ -396,7 +404,7 @@ async function generateWithImageModel({ prompt, model, outputPath, count, aspect
         ...(aspectRatio ? { aspectRatio } : {}),
         ...(seed !== undefined ? { seed } : {}),
         providerOptions: {
-            google: {
+            [providerOptionsKey]: {
                 ...(allowPeople ? { personGeneration: 'allow_all' } : {}),
                 ...(aspectRatio ? { aspectRatio } : {}),
             },
@@ -421,7 +429,6 @@ async function generateWithImageModel({ prompt, model, outputPath, count, aspect
         console.error(pc.green(`Saved: ${filePath}`));
         savedFiles.push(filePath);
     }
-    const config = getModelConfig(model);
     const cost = calculateCost(config.cost, result.usage, result.images.length);
     if (cost != null) {
         console.error(pc.dim(`Cost: ${formatCost(cost)}`));
@@ -441,6 +448,8 @@ async function generateWithImageModel({ prompt, model, outputPath, count, aspect
 // Generate using generateText with responseModalities (Gemini multimodal models)
 async function generateWithTextModel({ prompt, model, outputPath, inputImages, imageSize, aspectRatio, json, stdout, }) {
     const textModel = await createTextModel(model);
+    const config = getModelConfig(model);
+    const providerOptionsKey = config.provider === 'vertex' ? 'vertex' : 'google';
     if (!stdout) {
         console.error(pc.cyan('Generating...'));
     }
@@ -463,7 +472,7 @@ async function generateWithTextModel({ prompt, model, outputPath, inputImages, i
         model: textModel,
         ...(messages ? { messages } : { prompt }),
         providerOptions: {
-            google: {
+            [providerOptionsKey]: {
                 responseModalities: ['TEXT', 'IMAGE'],
                 ...(imageSize || aspectRatio
                     ? {
@@ -501,7 +510,6 @@ async function generateWithTextModel({ prompt, model, outputPath, inputImages, i
         console.error(pc.green(`Saved: ${filePath}`));
         savedFiles.push(filePath);
     }
-    const config = getModelConfig(model);
     const cost = calculateCost(config.cost, result.usage, imageFiles.length);
     if (cost != null) {
         console.error(pc.dim(`Cost: ${formatCost(cost)}`));

package/dist/credentials.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"credentials.d.ts","sourceRoot":"","sources":["../src/credentials.ts"],"names":[],"mappings":"AAUA,eAAO,MAAM,SAAS,EAAE,MAAM,CAC5B,MAAM,EACN;IAAE,MAAM,EAAE,MAAM,CAAC;IAAC,KAAK,EAAE,MAAM,CAAC;IAAC,IAAI,EAAE,MAAM,CAAA;CAAE,CA2BhD,CAAA;AAED,eAAO,MAAM,iBAAiB,4BAA4B,CAAA;AAa1D,MAAM,MAAM,WAAW,GAAG,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;AAEhD,wBAAgB,eAAe,IAAI,WAAW,CAO7C;AAED,wBAAgB,gBAAgB,CAAC,KAAK,EAAE,WAAW,GAAG,IAAI,CAOzD;AAED,wBAAgB,eAAe,CAAC,QAAQ,EAAE,MAAM,EAAE,GAAG,EAAE,MAAM,GAAG,IAAI,CAInE;AAED,wBAAgB,iBAAiB,CAAC,QAAQ,EAAE,MAAM,GAAG,IAAI,CAIxD;AAED,wBAAgB,cAAc,CAAC,QAAQ,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS,CAGnE;AAKD,wBAAgB,sBAAsB,IAAI,IAAI,CAW7C;AAID,wBAAgB,YAAY,CAAC,QAAQ,EAAE,MAAM,GAAG;IAC9C,SAAS,EAAE,OAAO,CAAA;IAClB,MAAM,EAAE,KAAK,GAAG,QAAQ,GAAG,MAAM,CAAA;CAClC,CAaA"}
+{"version":3,"file":"credentials.d.ts","sourceRoot":"","sources":["../src/credentials.ts"],"names":[],"mappings":"AAUA,eAAO,MAAM,SAAS,EAAE,MAAM,CAC5B,MAAM,EACN;IAAE,MAAM,EAAE,MAAM,CAAC;IAAC,KAAK,EAAE,MAAM,CAAC;IAAC,IAAI,EAAE,MAAM,CAAA;CAAE,CAgChD,CAAA;AAED,eAAO,MAAM,iBAAiB,4BAA4B,CAAA;AAa1D,MAAM,MAAM,WAAW,GAAG,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAA;AAEhD,wBAAgB,eAAe,IAAI,WAAW,CAO7C;AAED,wBAAgB,gBAAgB,CAAC,KAAK,EAAE,WAAW,GAAG,IAAI,CAOzD;AAED,wBAAgB,eAAe,CAAC,QAAQ,EAAE,MAAM,EAAE,GAAG,EAAE,MAAM,GAAG,IAAI,CAInE;AAED,wBAAgB,iBAAiB,CAAC,QAAQ,EAAE,MAAM,GAAG,IAAI,CAIxD;AAED,wBAAgB,cAAc,CAAC,QAAQ,EAAE,MAAM,GAAG,MAAM,GAAG,SAAS,CAGnE;AAKD,wBAAgB,sBAAsB,IAAI,IAAI,CAW7C;AAID,wBAAgB,YAAY,CAAC,QAAQ,EAAE,MAAM,GAAG;IAC9C,SAAS,EAAE,OAAO,CAAA;IAClB,MAAM,EAAE,KAAK,GAAG,QAAQ,GAAG,MAAM,CAAA;CAClC,CAaA"}

package/dist/credentials.js

@@ -18,6 +18,11 @@ export const PROVIDERS = {
         label: 'Google AI (Gemini, Imagen)',
         hint: 'Get your key at https://aistudio.google.com/apikey',
     },
+    vertex: {
+        envVar: 'GOOGLE_VERTEX_API_KEY',
+        label: 'Google Vertex AI (Gemini, Imagen, Veo via Google Cloud)',
+        hint: 'Get an API key at https://console.cloud.google.com/apis/credentials',
+    },
     openai: {
         envVar: 'OPENAI_API_KEY',
         label: 'OpenAI (DALL-E)',

package/dist/model-catalog.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"model-catalog.d.ts","sourceRoot":"","sources":["../src/model-catalog.ts"],"names":[],"mappings":"AAUA,MAAM,MAAM,YAAY,GAAG;IACzB,IAAI,EAAE,WAAW,CAAA;IACjB,kDAAkD;IAClD,QAAQ,EAAE,MAAM,CAAA;CACjB,CAAA;AAED,MAAM,MAAM,YAAY,GAAG;IACzB,IAAI,EAAE,WAAW,CAAA;IACjB,mCAAmC;IACnC,SAAS,EAAE,MAAM,CAAA;IACjB,oCAAoC;IACpC,UAAU,EAAE,MAAM,CAAA;CACnB,CAAA;AAED,MAAM,MAAM,SAAS,GAAG,YAAY,GAAG,YAAY,CAAA;AAEnD,MAAM,MAAM,aAAa,GAAG;IAC1B,wCAAwC;IACxC,OAAO,EAAE,OAAO,CAAA;IAChB,mCAAmC;IACnC,UAAU,EAAE,OAAO,CAAA;IACnB,8BAA8B;IAC9B,YAAY,EAAE,MAAM,EAAE,CAAA;IACtB,mDAAmD;IACnD,KAAK,CAAC,EAAE,MAAM,EAAE,CAAA;IAChB,kCAAkC;IAClC,IAAI,EAAE,OAAO,CAAA;IACb,uCAAuC;IACvC,cAAc,EAAE,OAAO,CAAA;CACxB,CAAA;AAED,MAAM,MAAM,UAAU,GAAG;IACvB,EAAE,EAAE,MAAM,CAAA;IACV,IAAI,EAAE,MAAM,CAAA;IACZ,iEAAiE;IACjE,WAAW,CAAC,EAAE,MAAM,CAAA;IACpB,QAAQ,EAAE,MAAM,CAAA;IAChB,QAAQ,EAAE,OAAO,GAAG,MAAM,CAAA;IAC1B,mDAAmD;IACnD,QAAQ,EAAE,MAAM,CAAA;IAChB,IAAI,EAAE,SAAS,CAAA;IACf,QAAQ,EAAE,aAAa,CAAA;CACxB,CAAA;AA+DD,eAAO,MAAM,OAAO,EAAE,UAAU,EA40B/B,CAAA;AAMD,wBAAgB,SAAS,CAAC,EAAE,EAAE,MAAM,GAAG,UAAU,GAAG,SAAS,CAE5D"}
+{"version":3,"file":"model-catalog.d.ts","sourceRoot":"","sources":["../src/model-catalog.ts"],"names":[],"mappings":"AAUA,MAAM,MAAM,YAAY,GAAG;IACzB,IAAI,EAAE,WAAW,CAAA;IACjB,kDAAkD;IAClD,QAAQ,EAAE,MAAM,CAAA;CACjB,CAAA;AAED,MAAM,MAAM,YAAY,GAAG;IACzB,IAAI,EAAE,WAAW,CAAA;IACjB,mCAAmC;IACnC,SAAS,EAAE,MAAM,CAAA;IACjB,oCAAoC;IACpC,UAAU,EAAE,MAAM,CAAA;CACnB,CAAA;AAED,MAAM,MAAM,SAAS,GAAG,YAAY,GAAG,YAAY,CAAA;AAEnD,MAAM,MAAM,aAAa,GAAG;IAC1B,wCAAwC;IACxC,OAAO,EAAE,OAAO,CAAA;IAChB,mCAAmC;IACnC,UAAU,EAAE,OAAO,CAAA;IACnB,8BAA8B;IAC9B,YAAY,EAAE,MAAM,EAAE,CAAA;IACtB,mDAAmD;IACnD,KAAK,CAAC,EAAE,MAAM,EAAE,CAAA;IAChB,kCAAkC;IAClC,IAAI,EAAE,OAAO,CAAA;IACb,uCAAuC;IACvC,cAAc,EAAE,OAAO,CAAA;CACxB,CAAA;AAED,MAAM,MAAM,UAAU,GAAG;IACvB,EAAE,EAAE,MAAM,CAAA;IACV,IAAI,EAAE,MAAM,CAAA;IACZ,iEAAiE;IACjE,WAAW,CAAC,EAAE,MAAM,CAAA;IACpB,QAAQ,EAAE,MAAM,CAAA;IAChB,QAAQ,EAAE,OAAO,GAAG,MAAM,CAAA;IAC1B,mDAAmD;IACnD,QAAQ,EAAE,MAAM,CAAA;IAChB,IAAI,EAAE,SAAS,CAAA;IACf,QAAQ,EAAE,aAAa,CAAA;CACxB,CAAA;AA+ED,eAAO,MAAM,OAAO,EAAE,UAAU,EAs4B/B,CAAA;AAMD,wBAAgB,SAAS,CAAC,EAAE,EAAE,MAAM,GAAG,UAAU,GAAG,SAAS,CAE5D"}

package/dist/model-catalog.js

@@ -53,6 +53,20 @@ const xaiImage = {
     provider: 'xai',
     strategy: 'image',
 };
+const vertexImagen = {
+    provider: 'vertex',
+    strategy: 'image',
+    features: {
+        ...googleImagen.features,
+    },
+};
+const vertexText = {
+    provider: 'vertex',
+    strategy: 'text',
+    features: {
+        ...googleText.features,
+    },
+};
 const fluxAspectRatios = ['1:1', '3:4', '4:3', '9:16', '16:9', '9:21', '21:9'];
 // ─── catalog ─────────────────────────────────────────────────────────────────
 export const CATALOG = [
@@ -134,6 +148,62 @@ export const CATALOG = [
         },
         cost: { type: 'per-token', inputPerM: 0.5, outputPerM: 3.0 },
     },
+    // ── Vertex: Imagen ──────────────────────────────────────────────────────
+    // Same models as Google AI Studio but routed through Vertex AI / Google Cloud billing.
+    // Use `egaki login --provider vertex --key <key>` to configure.
+    {
+        id: 'vertex/imagen-4.0-generate-001',
+        name: 'Imagen 4 (Vertex)',
+        released: '2025-08-15',
+        ...vertexImagen,
+        cost: { type: 'per-image', perImage: 0.04 },
+    },
+    {
+        id: 'vertex/imagen-4.0-ultra-generate-001',
+        name: 'Imagen 4 Ultra (Vertex)',
+        released: '2025-08-15',
+        ...vertexImagen,
+        cost: { type: 'per-image', perImage: 0.06 },
+    },
+    {
+        id: 'vertex/imagen-4.0-fast-generate-001',
+        name: 'Imagen 4 Fast (Vertex)',
+        released: '2025-08-15',
+        ...vertexImagen,
+        cost: { type: 'per-image', perImage: 0.02 },
+    },
+    // ── Vertex: Gemini text+image ─────────────────────────────────────────
+    {
+        id: 'vertex/gemini-2.5-flash-image',
+        name: 'Gemini 2.5 Flash Image (Vertex)',
+        released: '2025-08-26',
+        ...vertexText,
+        cost: { type: 'per-token', inputPerM: 0.3, outputPerM: 30 },
+    },
+    {
+        id: 'vertex/gemini-3-pro-image-preview',
+        name: 'Gemini 3 Pro Image (Vertex)',
+        released: '2025-11-20',
+        ...vertexText,
+        cost: { type: 'per-token', inputPerM: 1.25, outputPerM: 10 },
+    },
+    {
+        id: 'vertex/gemini-3.1-flash-image-preview',
+        name: 'Gemini 3.1 Flash Image (Vertex)',
+        released: '2026-02-26',
+        ...vertexText,
+        features: {
+            ...vertexText.features,
+            aspectRatios: [
+                ...vertexText.features.aspectRatios,
+                '4:1',
+                '1:4',
+                '8:1',
+                '1:8',
+            ],
+        },
+        cost: { type: 'per-token', inputPerM: 0.5, outputPerM: 3.0 },
+    },
     // ── BFL (AI Gateway) ───────────────────────────────────────────────────
     {
         id: 'flux-kontext-max',

package/dist/models.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"models.d.ts","sourceRoot":"","sources":["../src/models.ts"],"names":[],"mappings":"AAiBA,OAAO,KAAK,EAAE,UAAU,EAAE,aAAa,EAAE,MAAM,IAAI,CAAA;AAInD,OAAO,KAAK,EAAE,UAAU,EAAE,MAAM,oBAAoB,CAAA;AAEpD,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,0BAA0B,CAAA;AAE/D,MAAM,MAAM,aAAa,GAAG,UAAU,GAAG,eAAe,CAAA;AACxD,YAAY,EAAE,UAAU,EAAE,eAAe,EAAE,CAAA;AAE3C,eAAO,MAAM,YAAY,EAA+B,CAAC,MAAM,EAAE,GAAG,MAAM,EAAE,CAAC,CAAA;AAC7E,eAAO,MAAM,YAAY,EAAqC,CAAC,MAAM,EAAE,GAAG,MAAM,EAAE,CAAC,CAAA;AAEnF,eAAO,MAAM,aAAa,4BAA4B,CAAA;AACtD,eAAO,MAAM,mBAAmB,8BAA8B,CAAA;AAE9D,wBAAgB,cAAc,CAAC,OAAO,EAAE,MAAM,GAAG,aAAa,CAO7D;AAuBD,wBAAgB,iBAAiB,CAAC,YAAY,EAAE,MAAM,GAAG,IAAI,CAmC5D;AAgDD,wBAAsB,gBAAgB,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,CAAC,UAAU,CAAC,CAkC3E;AAED,wBAAsB,eAAe,CACnC,OAAO,EAAE,MAAM,GACd,OAAO,CAAC,aAAa,CAAC,CAiCxB;AAED,wBAAsB,gBAAgB,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,CAAC,GAAG,CAAC,CAqCpE"}
+{"version":3,"file":"models.d.ts","sourceRoot":"","sources":["../src/models.ts"],"names":[],"mappings":"AAiBA,OAAO,KAAK,EAAE,UAAU,EAAE,aAAa,EAAE,MAAM,IAAI,CAAA;AAInD,OAAO,KAAK,EAAE,UAAU,EAAE,MAAM,oBAAoB,CAAA;AAEpD,OAAO,KAAK,EAAE,eAAe,EAAE,MAAM,0BAA0B,CAAA;AAE/D,MAAM,MAAM,aAAa,GAAG,UAAU,GAAG,eAAe,CAAA;AACxD,YAAY,EAAE,UAAU,EAAE,eAAe,EAAE,CAAA;AAE3C,eAAO,MAAM,YAAY,EAA+B,CAAC,MAAM,EAAE,GAAG,MAAM,EAAE,CAAC,CAAA;AAC7E,eAAO,MAAM,YAAY,EAAqC,CAAC,MAAM,EAAE,GAAG,MAAM,EAAE,CAAC,CAAA;AAYnF,eAAO,MAAM,aAAa,4BAA4B,CAAA;AACtD,eAAO,MAAM,mBAAmB,8BAA8B,CAAA;AAE9D,wBAAgB,cAAc,CAAC,OAAO,EAAE,MAAM,GAAG,aAAa,CAO7D;AAuBD,wBAAgB,iBAAiB,CAAC,YAAY,EAAE,MAAM,GAAG,IAAI,CAiD5D;AAqDD,wBAAsB,gBAAgB,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,CAAC,UAAU,CAAC,CAsC3E;AAED,wBAAsB,eAAe,CACnC,OAAO,EAAE,MAAM,GACd,OAAO,CAAC,aAAa,CAAC,CAqCxB;AAED,wBAAsB,gBAAgB,CAAC,OAAO,EAAE,MAAM,GAAG,OAAO,CAAC,GAAG,CAAC,CAyCpE"}

package/dist/models.js

@@ -4,6 +4,16 @@ import { CATALOG, findModel } from './model-catalog.js';
 import { VIDEO_CATALOG, findVideoModel } from './video-model-catalog.js';
 export const IMAGE_MODELS = CATALOG.map((m) => m.id);
 export const VIDEO_MODELS = VIDEO_CATALOG.map((m) => m.id);
+/**
+ * Strip provider prefix from a model ID (e.g. "vertex/imagen-4.0-generate-001" → "imagen-4.0-generate-001").
+ * Provider SDKs expect bare model IDs, but the catalog uses prefixed IDs for routing.
+ */
+function stripProviderPrefix(modelId) {
+    const slash = modelId.indexOf('/');
+    if (slash === -1)
+        return modelId;
+    return modelId.slice(slash + 1);
+}
 export const DEFAULT_MODEL = 'nano-banana-pro-preview';
 export const DEFAULT_VIDEO_MODEL = 'veo-3.1-fast-generate-001';
 export function getModelConfig(modelId) {
@@ -39,6 +49,19 @@ export function ensureProviderKey(providerName) {
     // If direct provider key exists, we're good
     if (hasDirectProviderKey(providerName))
         return;
+    // Vertex models require a direct key — the upstream Vercel AI Gateway
+    // does not support vertex/ routing, so egaki gateway can't proxy them.
+    if (providerName === 'vertex') {
+        console.error('');
+        console.error(pc.red(pc.bold('Vertex models require a direct Google Cloud API key')));
+        console.error('');
+        console.error(`  ${pc.cyan('egaki login --provider vertex --key <key>')}`);
+        console.error('');
+        console.error(pc.dim('Get a key at https://console.cloud.google.com/apis/credentials'));
+        console.error(pc.dim('Egaki subscription does not cover Vertex routing yet.'));
+        console.error('');
+        process.exit(1);
+    }
     // If egaki key exists, we'll route through the gateway
     if (hasEgakiKey())
         return;
@@ -72,8 +95,11 @@ async function createGatewayImageModel(modelId, provider) {
         apiKey: process.env['EGAKI_API_KEY'],
         baseURL: EGAKI_GATEWAY_URL,
     });
-    // Gateway expects provider/model format for routing
-    const gatewayModelId = `${provider}/${modelId}`;
+    // Gateway expects provider/model format for routing.
+    // For models that already have a prefix (e.g. vertex/imagen-4.0), strip it
+    // and use the catalog provider. For bare IDs, prepend the provider.
+    const bareId = stripProviderPrefix(modelId);
+    const gatewayModelId = `${provider}/${bareId}`;
     return gateway.image(gatewayModelId);
 }
 /**
@@ -85,7 +111,8 @@ async function createGatewayTextModel(modelId, provider) {
         apiKey: process.env['EGAKI_API_KEY'],
         baseURL: EGAKI_GATEWAY_URL,
     });
-    const gatewayModelId = `${provider}/${modelId}`;
+    const bareId = stripProviderPrefix(modelId);
+    const gatewayModelId = `${provider}/${bareId}`;
     return gateway(gatewayModelId);
 }
 /**
@@ -97,7 +124,8 @@ async function createGatewayVideoModel(modelId, provider) {
         apiKey: process.env['EGAKI_API_KEY'],
         baseURL: EGAKI_GATEWAY_URL,
     });
-    const gatewayModelId = `${provider}/${modelId}`;
+    const bareId = stripProviderPrefix(modelId);
+    const gatewayModelId = `${provider}/${bareId}`;
     return gateway.video(gatewayModelId);
 }
 // Lazily import the provider and create the right model instance.
@@ -115,6 +143,10 @@ export async function createImageModel(modelId) {
                 const { google } = await import('@ai-sdk/google');
                 return google.image(modelId);
             }
+            case 'vertex': {
+                const { vertex } = await import('@ai-sdk/google-vertex');
+                return vertex.image(stripProviderPrefix(modelId));
+            }
             case 'openai': {
                 const { openai } = await import('@ai-sdk/openai');
                 return openai.image(modelId);
@@ -151,9 +183,13 @@ export async function createTextModel(modelId) {
                 const { google } = await import('@ai-sdk/google');
                 return google(modelId);
             }
+            case 'vertex': {
+                const { vertex } = await import('@ai-sdk/google-vertex');
+                return vertex(stripProviderPrefix(modelId));
+            }
             default:
-                // Only Google supports generateText with responseModalities for images
-                console.error(pc.red(`Text+image generation is only supported for Google models, got provider: ${config.provider}`));
+                // Only Google/Vertex support generateText with responseModalities for images
+                console.error(pc.red(`Text+image generation is only supported for Google/Vertex models, got provider: ${config.provider}`));
                 process.exit(1);
         }
     }
@@ -178,12 +214,16 @@ export async function createVideoModel(modelId) {
                 const { google } = await import('@ai-sdk/google');
                 return google.video(modelId);
             }
+            case 'vertex': {
+                const { vertex } = await import('@ai-sdk/google-vertex');
+                return vertex.video(stripProviderPrefix(modelId));
+            }
             case 'fal': {
                 const { fal } = await import('@ai-sdk/fal');
                 return fal.video(modelId);
             }
             default:
-                console.error(pc.red(`Direct video generation is only supported for Google and Fal keys, got provider: ${config.provider}`));
+                console.error(pc.red(`Direct video generation is only supported for Google, Vertex, and Fal keys, got provider: ${config.provider}`));
                 process.exit(1);
         }
     }

package/dist/video-model-catalog.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"video-model-catalog.d.ts","sourceRoot":"","sources":["../src/video-model-catalog.ts"],"names":[],"mappings":"AAIA,MAAM,MAAM,wBAAwB,GAAG;IACrC,sCAAsC;IACtC,aAAa,EAAE,MAAM,CAAA;IACrB,+DAA+D;IAC/D,UAAU,CAAC,EAAE,MAAM,CAAA;IACnB,kDAAkD;IAClD,IAAI,CAAC,EAAE,MAAM,CAAA;IACb,mCAAmC;IACnC,KAAK,CAAC,EAAE,OAAO,CAAA;CAChB,CAAA;AAED,MAAM,MAAM,kBAAkB,GAAG;IAC/B,IAAI,EAAE,kBAAkB,CAAA;IACxB,oEAAoE;IACpE,kBAAkB,EAAE,MAAM,CAAA;IAC1B,KAAK,EAAE,wBAAwB,EAAE,CAAA;CAClC,CAAA;AAED,MAAM,MAAM,gBAAgB,GAAG;IAC7B,IAAI,EAAE,SAAS,CAAA;CAChB,CAAA;AAED,MAAM,MAAM,cAAc,GAAG,kBAAkB,GAAG,gBAAgB,CAAA;AAElE,MAAM,MAAM,kBAAkB,GAAG;IAC/B,+CAA+C;IAC/C,WAAW,EAAE,OAAO,CAAA;IACpB,8DAA8D;IAC9D,YAAY,EAAE,OAAO,CAAA;IACrB,gDAAgD;IAChD,YAAY,EAAE,KAAK,CAAC,KAAK,GAAG,KAAK,GAAG,KAAK,GAAG,gBAAgB,GAAG,SAAS,CAAC,CAAA;IACzE,uCAAuC;IACvC,YAAY,CAAC,EAAE,MAAM,EAAE,CAAA;IACvB,qCAAqC;IACrC,WAAW,CAAC,EAAE,MAAM,EAAE,CAAA;IACtB,yCAAyC;IACzC,gBAAgB,CAAC,EAAE;QAAE,GAAG,EAAE,MAAM,CAAC;QAAC,GAAG,EAAE,MAAM,CAAA;KAAE,CAAA;IAC/C,IAAI,EAAE,OAAO,CAAA;IACb,cAAc,EAAE,OAAO,CAAA;CACxB,CAAA;AAED,MAAM,MAAM,eAAe,GAAG;IAC5B,EAAE,EAAE,MAAM,CAAA;IACV,IAAI,EAAE,MAAM,CAAA;IACZ,WAAW,CAAC,EAAE,MAAM,CAAA;IACpB,QAAQ,EAAE,MAAM,CAAA;IAChB,QAAQ,EAAE,OAAO,CAAA;IACjB,QAAQ,EAAE,MAAM,CAAA;IAChB,IAAI,EAAE,cAAc,CAAA;IACpB,QAAQ,EAAE,kBAAkB,CAAA;CAC7B,CAAA;AAID,eAAO,MAAM,aAAa,EAAE,eAAe,EA6O1C,CAAA;AAID,wBAAgB,cAAc,CAAC,EAAE,EAAE,MAAM,GAAG,eAAe,GAAG,SAAS,CAEtE"}
+{"version":3,"file":"video-model-catalog.d.ts","sourceRoot":"","sources":["../src/video-model-catalog.ts"],"names":[],"mappings":"AAIA,MAAM,MAAM,wBAAwB,GAAG;IACrC,sCAAsC;IACtC,aAAa,EAAE,MAAM,CAAA;IACrB,+DAA+D;IAC/D,UAAU,CAAC,EAAE,MAAM,CAAA;IACnB,kDAAkD;IAClD,IAAI,CAAC,EAAE,MAAM,CAAA;IACb,mCAAmC;IACnC,KAAK,CAAC,EAAE,OAAO,CAAA;CAChB,CAAA;AAED,MAAM,MAAM,kBAAkB,GAAG;IAC/B,IAAI,EAAE,kBAAkB,CAAA;IACxB,oEAAoE;IACpE,kBAAkB,EAAE,MAAM,CAAA;IAC1B,KAAK,EAAE,wBAAwB,EAAE,CAAA;CAClC,CAAA;AAED,MAAM,MAAM,gBAAgB,GAAG;IAC7B,IAAI,EAAE,SAAS,CAAA;CAChB,CAAA;AAED,MAAM,MAAM,cAAc,GAAG,kBAAkB,GAAG,gBAAgB,CAAA;AAElE,MAAM,MAAM,kBAAkB,GAAG;IAC/B,+CAA+C;IAC/C,WAAW,EAAE,OAAO,CAAA;IACpB,8DAA8D;IAC9D,YAAY,EAAE,OAAO,CAAA;IACrB,gDAAgD;IAChD,YAAY,EAAE,KAAK,CAAC,KAAK,GAAG,KAAK,GAAG,KAAK,GAAG,gBAAgB,GAAG,SAAS,CAAC,CAAA;IACzE,uCAAuC;IACvC,YAAY,CAAC,EAAE,MAAM,EAAE,CAAA;IACvB,qCAAqC;IACrC,WAAW,CAAC,EAAE,MAAM,EAAE,CAAA;IACtB,yCAAyC;IACzC,gBAAgB,CAAC,EAAE;QAAE,GAAG,EAAE,MAAM,CAAC;QAAC,GAAG,EAAE,MAAM,CAAA;KAAE,CAAA;IAC/C,IAAI,EAAE,OAAO,CAAA;IACb,cAAc,EAAE,OAAO,CAAA;CACxB,CAAA;AAED,MAAM,MAAM,eAAe,GAAG;IAC5B,EAAE,EAAE,MAAM,CAAA;IACV,IAAI,EAAE,MAAM,CAAA;IACZ,WAAW,CAAC,EAAE,MAAM,CAAA;IACpB,QAAQ,EAAE,MAAM,CAAA;IAChB,QAAQ,EAAE,OAAO,CAAA;IACjB,QAAQ,EAAE,MAAM,CAAA;IAChB,IAAI,EAAE,cAAc,CAAA;IACpB,QAAQ,EAAE,kBAAkB,CAAA;CAC7B,CAAA;AAID,eAAO,MAAM,aAAa,EAAE,eAAe,EA0S1C,CAAA;AAID,wBAAgB,cAAc,CAAC,EAAE,EAAE,MAAM,GAAG,eAAe,GAAG,SAAS,CAEtE"}

package/dist/video-model-catalog.js

@@ -115,6 +115,67 @@ export const VIDEO_CATALOG = [
             multipleVideos: true,
         },
     },
+    // ── Vertex: Veo ──────────────────────────────────────────────────────
+    // Same Veo models routed through Vertex AI / Google Cloud billing.
+    // Use `egaki login --provider vertex --key <key>` to configure.
+    {
+        id: 'vertex/veo-3.1-generate-001',
+        name: 'Veo 3.1 (Vertex)',
+        provider: 'vertex',
+        strategy: 'video',
+        released: '2026-01',
+        cost: {
+            type: 'per-video-second',
+            defaultDurationSec: 8,
+            tiers: [
+                { resolution: '720p', audio: false, costPerSecond: 0.2 },
+                { resolution: '720p', audio: true, costPerSecond: 0.4 },
+                { resolution: '1080p', audio: false, costPerSecond: 0.2 },
+                { resolution: '1080p', audio: true, costPerSecond: 0.4 },
+                { resolution: '4k', audio: false, costPerSecond: 0.4 },
+                { resolution: '4k', audio: true, costPerSecond: 0.6 },
+            ],
+        },
+        features: {
+            textToVideo: true,
+            imageToVideo: false,
+            capabilities: ['t2v'],
+            aspectRatios: ['16:9', '9:16'],
+            resolutions: ['720p', '1080p', '4k'],
+            durationRangeSec: { min: 4, max: 8 },
+            seed: true,
+            multipleVideos: true,
+        },
+    },
+    {
+        id: 'vertex/veo-3.1-fast-generate-001',
+        name: 'Veo 3.1 Fast (Vertex)',
+        provider: 'vertex',
+        strategy: 'video',
+        released: '2026-01',
+        cost: {
+            type: 'per-video-second',
+            defaultDurationSec: 8,
+            tiers: [
+                { resolution: '720p', audio: false, costPerSecond: 0.1 },
+                { resolution: '720p', audio: true, costPerSecond: 0.15 },
+                { resolution: '1080p', audio: false, costPerSecond: 0.1 },
+                { resolution: '1080p', audio: true, costPerSecond: 0.15 },
+                { resolution: '4k', audio: false, costPerSecond: 0.3 },
+                { resolution: '4k', audio: true, costPerSecond: 0.35 },
+            ],
+        },
+        features: {
+            textToVideo: true,
+            imageToVideo: false,
+            capabilities: ['t2v'],
+            aspectRatios: ['16:9', '9:16'],
+            resolutions: ['720p', '1080p', '4k'],
+            durationRangeSec: { min: 4, max: 8 },
+            seed: true,
+            multipleVideos: true,
+        },
+    },
     {
         id: 'grok-imagine-video',
         name: 'Grok Imagine Video',

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "egaki",
-  "version": "0.2.0",
+  "version": "0.3.0",
   "type": "module",
   "main": "./dist/cli.js",
   "types": "./dist/cli.d.ts",
@@ -33,6 +33,7 @@
   "files": [
     "src",
     "dist",
+    "skills",
     "README.md",
     "CHANGELOG.md"
   ],
@@ -48,6 +49,7 @@
   "dependencies": {
     "@ai-sdk/fal": "2.0.21",
     "@ai-sdk/google": "3.0.33",
+    "@ai-sdk/google-vertex": "^4.0.95",
     "@ai-sdk/openai": "3.0.36",
     "@ai-sdk/replicate": "2.0.20",
     "@clack/prompts": "^1.0.1",

package/skills/egaki/SKILL.md

@@ -0,0 +1,100 @@
+---
+name: egaki
+description: >
+  AI image and video generation CLI. Use this skill to install egaki, configure
+  auth, run help commands, and generate images or videos with provider keys or
+  an Egaki subscription.
+---
+
+# egaki
+
+Generate AI images and videos from the terminal.
+Use this for text-to-image, image editing, mask-based edits, text-to-video,
+image-to-video, and model discovery.
+
+## Install
+
+```bash
+pnpm add -g egaki
+```
+
+## Always check help first
+
+Run the full help output before using commands:
+
+```bash
+egaki --help
+```
+
+Do not truncate help output with `head`.
+
+For subcommand details: `egaki <command> --help` (e.g. `egaki image --help`, `egaki video --help`, `egaki login --help`)
+
+## Auth options
+
+You can authenticate in two ways:
+
+1. Egaki subscription key (recommended — all models, one key)
+2. Provider API keys (Google, OpenAI, Fal, Replicate) via `egaki login`
+
+If using Egaki subscription, set it up first with `egaki subscribe`, then store
+the key with `egaki login --provider egaki --key egaki_...`.
+
+## Login behavior for remote agents
+
+When login requires a URL flow, run login in the background and send the login URL
+to the user so they can complete auth interactively.
+
+## Example commands
+
+```bash
+# configure key interactively
+egaki login
+
+# show login status
+egaki login --show
+
+# subscribe to Egaki for all supported models
+egaki subscribe
+
+# check subscription usage
+egaki usage
+
+# generate an image
+egaki image "a watercolor fox reading a map" -o fox.png
+
+# select a model explicitly
+egaki image "isometric floating city, soft colors" -m imagen-4.0-generate-001 -o city.png
+
+# edit an existing image (local file or URL)
+egaki image "add a red scarf and make it winter" --input portrait.jpg -o portrait-winter.png
+egaki image "turn this into a manga panel" --input https://example.com/photo.jpg -o manga.png
+
+# inpainting with a mask
+egaki image "replace the sky with a dramatic sunset" --input scene.png --mask mask.png -o scene-sunset.png
+
+# generate a video — use a 5 minute timeout, video generation is slow
+egaki video "a paper boat drifting on a calm lake at sunrise" -o boat.mp4
+
+# generate a video with a specific model
+egaki video "timelapse of a stormy sea, cinematic" -m google/veo-3.1-fast-generate-001 --duration 6 -o storm.mp4
+
+# cheap video model
+egaki video "a cat walking on a rooftop at night" -m klingai/kling-v2.5-turbo-t2v --duration 5 -o cat.mp4
+
+# image-to-video (model must support i2v)
+egaki video "slowly animate the clouds" --input photo.jpg -m klingai/kling-v2.6-i2v -o animated.mp4
+
+# discover all models (image + video)
+egaki models
+
+# filter by type
+egaki models --type video
+egaki models --type image
+```
+
+## Video generation note for agents
+
+Video generation can be very slow — some models take 1–3 minutes per request.
+Always use a command timeout of **at least 5 minutes** when invoking `egaki video`
+from automation or agent workflows.

package/src/cli.ts

@@ -98,6 +98,7 @@ cli
   .example('egaki login')
   .example('# Non-interactive login with flags')
   .example('egaki login --provider google --key AIza...')
+  .example('egaki login --provider vertex --key AIza...')
   .example('# Pipe key from stdin (useful in CI/scripts)')
   .example('echo "AIza..." | egaki login --provider google')
   .example('# Show configured providers')
@@ -283,6 +284,8 @@ cli
   .example('egaki image "fill with flowers" --input photo.jpg --mask mask.png')
   .example('# Generate with Gemini multimodal at 4K')
   .example('egaki image "dreamy landscape" -m gemini-2.5-flash-image --image-size 4K')
+  .example('# Route through Vertex AI (Google Cloud billing)')
+  .example('egaki image "product photo on marble" -m vertex/imagen-4.0-generate-001')
   .example('# Generate multiple images')
   .example('egaki image "abstract art" -n 4 -o art.png')
   .example('# Pipe to another tool')
@@ -410,6 +413,8 @@ cli
   .example('egaki video "A paper airplane gliding through clouds" -o airplane.mp4')
   .example('# Generate with Veo model + duration')
   .example('egaki video "cinematic rainy street at night" -m veo-3.1-fast-generate-001 --duration 6')
+  .example('# Route through Vertex AI (Google Cloud billing)')
+  .example('egaki video "storm over mountains" -m vertex/veo-3.1-fast-generate-001 --duration 6')
   .example('# Image-to-video (model support required)')
   .example('egaki video "animate subtle camera pan" --model luma-ray-2 --input frame.png -o animated.mp4')
   .example('# Generate multiple videos')
@@ -597,8 +602,12 @@ async function generateWithImageModel({
     ? { text: prompt, images: inputImages, ...(maskImage ? { mask: maskImage } : {}) }
     : prompt
 
+  const config = getModelConfig(model)
   const imageModel = await createImageModel(model)
 
+  // Use the correct providerOptions key based on provider (google vs vertex)
+  const providerOptionsKey = config.provider === 'vertex' ? 'vertex' : 'google'
+
   if (!stdout) {
     console.error(pc.cyan('Generating...'))
   }
@@ -610,7 +619,7 @@ async function generateWithImageModel({
     ...(aspectRatio ? { aspectRatio } : {}),
     ...(seed !== undefined ? { seed } : {}),
     providerOptions: {
-      google: {
+      [providerOptionsKey]: {
         ...(allowPeople ? { personGeneration: 'allow_all' } : {}),
         ...(aspectRatio ? { aspectRatio } : {}),
       },
@@ -640,7 +649,6 @@ async function generateWithImageModel({
     savedFiles.push(filePath)
   }
 
-  const config = getModelConfig(model)
   const cost = calculateCost(config.cost, result.usage, result.images.length)
   if (cost != null) {
     console.error(pc.dim(`Cost: ${formatCost(cost)}`))
@@ -680,6 +688,8 @@ async function generateWithTextModel({
   stdout: boolean
 }) {
   const textModel = await createTextModel(model)
+  const config = getModelConfig(model)
+  const providerOptionsKey = config.provider === 'vertex' ? 'vertex' : 'google'
 
   if (!stdout) {
     console.error(pc.cyan('Generating...'))
@@ -705,7 +715,7 @@ async function generateWithTextModel({
     model: textModel,
     ...(messages ? { messages } : { prompt }),
     providerOptions: {
-      google: {
+      [providerOptionsKey]: {
         responseModalities: ['TEXT', 'IMAGE'],
         ...(imageSize || aspectRatio
           ? {
@@ -750,7 +760,6 @@ async function generateWithTextModel({
     savedFiles.push(filePath)
   }
 
-  const config = getModelConfig(model)
   const cost = calculateCost(config.cost, result.usage, imageFiles.length)
   if (cost != null) {
     console.error(pc.dim(`Cost: ${formatCost(cost)}`))

package/src/credentials.ts

@@ -22,6 +22,11 @@ export const PROVIDERS: Record<
     label: 'Google AI (Gemini, Imagen)',
     hint: 'Get your key at https://aistudio.google.com/apikey',
   },
+  vertex: {
+    envVar: 'GOOGLE_VERTEX_API_KEY',
+    label: 'Google Vertex AI (Gemini, Imagen, Veo via Google Cloud)',
+    hint: 'Get an API key at https://console.cloud.google.com/apis/credentials',
+  },
   openai: {
     envVar: 'OPENAI_API_KEY',
     label: 'OpenAI (DALL-E)',

package/src/model-catalog.ts

@@ -109,6 +109,22 @@ const xaiImage = {
   strategy: 'image' as const,
 }
 
+const vertexImagen = {
+  provider: 'vertex',
+  strategy: 'image' as const,
+  features: {
+    ...googleImagen.features,
+  },
+}
+
+const vertexText = {
+  provider: 'vertex',
+  strategy: 'text' as const,
+  features: {
+    ...googleText.features,
+  },
+}
+
 const fluxAspectRatios = ['1:1', '3:4', '4:3', '9:16', '16:9', '9:21', '21:9']
 
 // ─── catalog ─────────────────────────────────────────────────────────────────
@@ -196,6 +212,64 @@ export const CATALOG: ModelEntry[] = [
     cost: { type: 'per-token', inputPerM: 0.5, outputPerM: 3.0 },
   },
 
+  // ── Vertex: Imagen ──────────────────────────────────────────────────────
+  // Same models as Google AI Studio but routed through Vertex AI / Google Cloud billing.
+  // Use `egaki login --provider vertex --key <key>` to configure.
+  {
+    id: 'vertex/imagen-4.0-generate-001',
+    name: 'Imagen 4 (Vertex)',
+    released: '2025-08-15',
+    ...vertexImagen,
+    cost: { type: 'per-image', perImage: 0.04 },
+  },
+  {
+    id: 'vertex/imagen-4.0-ultra-generate-001',
+    name: 'Imagen 4 Ultra (Vertex)',
+    released: '2025-08-15',
+    ...vertexImagen,
+    cost: { type: 'per-image', perImage: 0.06 },
+  },
+  {
+    id: 'vertex/imagen-4.0-fast-generate-001',
+    name: 'Imagen 4 Fast (Vertex)',
+    released: '2025-08-15',
+    ...vertexImagen,
+    cost: { type: 'per-image', perImage: 0.02 },
+  },
+
+  // ── Vertex: Gemini text+image ─────────────────────────────────────────
+  {
+    id: 'vertex/gemini-2.5-flash-image',
+    name: 'Gemini 2.5 Flash Image (Vertex)',
+    released: '2025-08-26',
+    ...vertexText,
+    cost: { type: 'per-token', inputPerM: 0.3, outputPerM: 30 },
+  },
+  {
+    id: 'vertex/gemini-3-pro-image-preview',
+    name: 'Gemini 3 Pro Image (Vertex)',
+    released: '2025-11-20',
+    ...vertexText,
+    cost: { type: 'per-token', inputPerM: 1.25, outputPerM: 10 },
+  },
+  {
+    id: 'vertex/gemini-3.1-flash-image-preview',
+    name: 'Gemini 3.1 Flash Image (Vertex)',
+    released: '2026-02-26',
+    ...vertexText,
+    features: {
+      ...vertexText.features,
+      aspectRatios: [
+        ...vertexText.features.aspectRatios,
+        '4:1',
+        '1:4',
+        '8:1',
+        '1:8',
+      ],
+    },
+    cost: { type: 'per-token', inputPerM: 0.5, outputPerM: 3.0 },
+  },
+
   // ── BFL (AI Gateway) ───────────────────────────────────────────────────
   {
     id: 'flux-kontext-max',

package/src/models.ts

@@ -29,6 +29,16 @@ export type { ModelEntry, VideoModelEntry }
 export const IMAGE_MODELS = CATALOG.map((m) => m.id) as [string, ...string[]]
 export const VIDEO_MODELS = VIDEO_CATALOG.map((m) => m.id) as [string, ...string[]]
 
+/**
+ * Strip provider prefix from a model ID (e.g. "vertex/imagen-4.0-generate-001" → "imagen-4.0-generate-001").
+ * Provider SDKs expect bare model IDs, but the catalog uses prefixed IDs for routing.
+ */
+function stripProviderPrefix(modelId: string): string {
+  const slash = modelId.indexOf('/')
+  if (slash === -1) return modelId
+  return modelId.slice(slash + 1)
+}
+
 export const DEFAULT_MODEL = 'nano-banana-pro-preview'
 export const DEFAULT_VIDEO_MODEL = 'veo-3.1-fast-generate-001'
 
@@ -66,6 +76,20 @@ export function ensureProviderKey(providerName: string): void {
   // If direct provider key exists, we're good
   if (hasDirectProviderKey(providerName)) return
 
+  // Vertex models require a direct key — the upstream Vercel AI Gateway
+  // does not support vertex/ routing, so egaki gateway can't proxy them.
+  if (providerName === 'vertex') {
+    console.error('')
+    console.error(pc.red(pc.bold('Vertex models require a direct Google Cloud API key')))
+    console.error('')
+    console.error(`  ${pc.cyan('egaki login --provider vertex --key <key>')}`)
+    console.error('')
+    console.error(pc.dim('Get a key at https://console.cloud.google.com/apis/credentials'))
+    console.error(pc.dim('Egaki subscription does not cover Vertex routing yet.'))
+    console.error('')
+    process.exit(1)
+  }
+
   // If egaki key exists, we'll route through the gateway
   if (hasEgakiKey()) return
 
@@ -109,8 +133,11 @@ async function createGatewayImageModel(modelId: string, provider: string): Promi
     apiKey: process.env['EGAKI_API_KEY']!,
     baseURL: EGAKI_GATEWAY_URL,
   })
-  // Gateway expects provider/model format for routing
-  const gatewayModelId = `${provider}/${modelId}`
+  // Gateway expects provider/model format for routing.
+  // For models that already have a prefix (e.g. vertex/imagen-4.0), strip it
+  // and use the catalog provider. For bare IDs, prepend the provider.
+  const bareId = stripProviderPrefix(modelId)
+  const gatewayModelId = `${provider}/${bareId}`
   return gateway.image(gatewayModelId)
 }
 
@@ -123,7 +150,8 @@ async function createGatewayTextModel(modelId: string, provider: string): Promis
     apiKey: process.env['EGAKI_API_KEY']!,
     baseURL: EGAKI_GATEWAY_URL,
   })
-  const gatewayModelId = `${provider}/${modelId}`
+  const bareId = stripProviderPrefix(modelId)
+  const gatewayModelId = `${provider}/${bareId}`
   return gateway(gatewayModelId)
 }
 
@@ -136,7 +164,8 @@ async function createGatewayVideoModel(modelId: string, provider: string) {
     apiKey: process.env['EGAKI_API_KEY']!,
     baseURL: EGAKI_GATEWAY_URL,
   })
-  const gatewayModelId = `${provider}/${modelId}`
+  const bareId = stripProviderPrefix(modelId)
+  const gatewayModelId = `${provider}/${bareId}`
   return gateway.video(gatewayModelId)
 }
 
@@ -156,6 +185,10 @@ export async function createImageModel(modelId: string): Promise<ImageModel> {
         const { google } = await import('@ai-sdk/google')
         return google.image(modelId)
       }
+      case 'vertex': {
+        const { vertex } = await import('@ai-sdk/google-vertex')
+        return vertex.image(stripProviderPrefix(modelId))
+      }
       case 'openai': {
         const { openai } = await import('@ai-sdk/openai')
         return openai.image(modelId)
@@ -198,11 +231,15 @@ export async function createTextModel(
         const { google } = await import('@ai-sdk/google')
         return google(modelId)
       }
+      case 'vertex': {
+        const { vertex } = await import('@ai-sdk/google-vertex')
+        return vertex(stripProviderPrefix(modelId))
+      }
       default:
-        // Only Google supports generateText with responseModalities for images
+        // Only Google/Vertex support generateText with responseModalities for images
         console.error(
           pc.red(
-            `Text+image generation is only supported for Google models, got provider: ${config.provider}`,
+            `Text+image generation is only supported for Google/Vertex models, got provider: ${config.provider}`,
           ),
         )
         process.exit(1)
@@ -234,6 +271,10 @@ export async function createVideoModel(modelId: string): Promise<any> {
         const { google } = await import('@ai-sdk/google')
         return google.video(modelId)
       }
+      case 'vertex': {
+        const { vertex } = await import('@ai-sdk/google-vertex')
+        return vertex.video(stripProviderPrefix(modelId))
+      }
       case 'fal': {
         const { fal } = await import('@ai-sdk/fal')
         return fal.video(modelId)
@@ -241,7 +282,7 @@ export async function createVideoModel(modelId: string): Promise<any> {
       default:
         console.error(
           pc.red(
-            `Direct video generation is only supported for Google and Fal keys, got provider: ${config.provider}`,
+            `Direct video generation is only supported for Google, Vertex, and Fal keys, got provider: ${config.provider}`,
           ),
         )
         process.exit(1)

package/src/video-model-catalog.ts

@@ -169,6 +169,67 @@ export const VIDEO_CATALOG: VideoModelEntry[] = [
       multipleVideos: true,
     },
   },
+  // ── Vertex: Veo ──────────────────────────────────────────────────────
+  // Same Veo models routed through Vertex AI / Google Cloud billing.
+  // Use `egaki login --provider vertex --key <key>` to configure.
+  {
+    id: 'vertex/veo-3.1-generate-001',
+    name: 'Veo 3.1 (Vertex)',
+    provider: 'vertex',
+    strategy: 'video',
+    released: '2026-01',
+    cost: {
+      type: 'per-video-second',
+      defaultDurationSec: 8,
+      tiers: [
+        { resolution: '720p', audio: false, costPerSecond: 0.2 },
+        { resolution: '720p', audio: true, costPerSecond: 0.4 },
+        { resolution: '1080p', audio: false, costPerSecond: 0.2 },
+        { resolution: '1080p', audio: true, costPerSecond: 0.4 },
+        { resolution: '4k', audio: false, costPerSecond: 0.4 },
+        { resolution: '4k', audio: true, costPerSecond: 0.6 },
+      ],
+    },
+    features: {
+      textToVideo: true,
+      imageToVideo: false,
+      capabilities: ['t2v'],
+      aspectRatios: ['16:9', '9:16'],
+      resolutions: ['720p', '1080p', '4k'],
+      durationRangeSec: { min: 4, max: 8 },
+      seed: true,
+      multipleVideos: true,
+    },
+  },
+  {
+    id: 'vertex/veo-3.1-fast-generate-001',
+    name: 'Veo 3.1 Fast (Vertex)',
+    provider: 'vertex',
+    strategy: 'video',
+    released: '2026-01',
+    cost: {
+      type: 'per-video-second',
+      defaultDurationSec: 8,
+      tiers: [
+        { resolution: '720p', audio: false, costPerSecond: 0.1 },
+        { resolution: '720p', audio: true, costPerSecond: 0.15 },
+        { resolution: '1080p', audio: false, costPerSecond: 0.1 },
+        { resolution: '1080p', audio: true, costPerSecond: 0.15 },
+        { resolution: '4k', audio: false, costPerSecond: 0.3 },
+        { resolution: '4k', audio: true, costPerSecond: 0.35 },
+      ],
+    },
+    features: {
+      textToVideo: true,
+      imageToVideo: false,
+      capabilities: ['t2v'],
+      aspectRatios: ['16:9', '9:16'],
+      resolutions: ['720p', '1080p', '4k'],
+      durationRangeSec: { min: 4, max: 8 },
+      seed: true,
+      multipleVideos: true,
+    },
+  },
   {
     id: 'grok-imagine-video',
     name: 'Grok Imagine Video',