@runpod/ai-sdk-provider 1.2.0 → 1.4.0

package/CHANGELOG.md

@@ -1,5 +1,23 @@
 # @runpod/ai-sdk-provider
 
+## 1.4.0
+
+### Minor Changes
+
+- 2e6efbd: Accept aiApiId (endpoint ID) as a valid model ID for image models and add video generation support.
+
+  Image models now use the same fallback pattern as speech, transcription, and video models: any unrecognized model ID is used directly as `https://api.runpod.ai/v2/{modelId}` instead of incorrectly appending `/openai/v1`. This means aiApiIds like `wan-2-6-t2i` or `black-forest-labs-flux-1-schnell` work out of the box without needing explicit mappings. Console endpoint URLs are also now supported for image models.
+
+  Video generation support includes 15 models across multiple providers (Pruna, Vidu, Kling, Wan, Seedance, Sora) with async polling, provider options, and both text-to-video and image-to-video capabilities.
+
+- 32f06c4: Add support for the google/nano-banana-2-edit image model with resolution options (1k/2k/4k), 14 aspect ratios, output format, and safety checker.
+
+## 1.3.0
+
+### Minor Changes
+
+- 973fae6: Add support for the Tongyi-MAI Z-Image Turbo image model with validated sizes and aspect ratios.
+
 ## 1.2.0
 
 ### Minor Changes

package/README.md

@@ -285,12 +285,14 @@ Check out our [examples](https://github.com/runpod/examples/tree/main/ai-sdk/get
 | `pruna/p-image-edit`                   | edit | up to 1440x1440   | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3             |
 | `google/nano-banana-edit`              | edit | up to 4096x4096   | 1:1, 4:3, 3:4                                   |
 | `google/nano-banana-pro-edit`          | edit | 1k, 2k, 4k        | 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 21:9       |
+| `google/nano-banana-2-edit`           | edit | 1k, 2k, 4k        | 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9, 1:4, 4:1, 1:8, 8:1 |
 | `bytedance/seedream-3.0`               | t2i  | up to 4096x4096   | 1:1, 4:3, 3:4                                   |
 | `bytedance/seedream-4.0`               | t2i  | up to 4096x4096   | 1:1, 4:3, 3:4                                   |
 | `bytedance/seedream-4.0-edit`          | edit | up to 4096x4096   | uses size                                       |
 | `qwen/qwen-image`                      | t2i  | up to 4096x4096   | 1:1, 4:3, 3:4                                   |
 | `qwen/qwen-image-edit`                 | edit | up to 4096x4096   | 1:1, 4:3, 3:4                                   |
 | `qwen/qwen-image-edit-2511`            | edit | up to 1536x1536   | 1:1, 4:3, 3:4                                   |
+| `tongyi-mai/z-image-turbo`             | t2i  | up to 1536x1536   | 1:1, 4:3, 3:4, 3:2, 2:3, 16:9, 9:16             |
 | `black-forest-labs/flux-1-schnell`     | t2i  | up to 2048x2048   | 1:1, 4:3, 3:4                                   |
 | `black-forest-labs/flux-1-dev`         | t2i  | up to 2048x2048   | 1:1, 4:3, 3:4                                   |
 | `black-forest-labs/flux-1-kontext-dev` | edit | up to 2048x2048   | 1:1, 4:3, 3:4                                   |
@@ -435,6 +437,14 @@ const { image } = await generateImage({
 });
 ```
 
+#### Tongyi-MAI (Z-Image Turbo)
+
+Supported model: `tongyi-mai/z-image-turbo`
+
+- Supported sizes (validated by provider): 512x512, 768x768, 1024x1024, 1280x1280, 1536x1536, 512x768, 768x512, 1024x768, 768x1024, 1328x1328, 1472x1140, 1140x1472, 768x432, 1024x576, 1280x720, 1536x864, 432x768, 576x1024, 720x1280, 864x1536
+- Supported `aspectRatio` values: 1:1, 4:3, 3:4, 3:2, 2:3, 16:9, 9:16 (maps to sizes above; use `size` for exact dimensions)
+- Additional parameters: `strength`, `output_format`, `enable_safety_checker`, `seed`
+
 ## Speech Models
 
 Generate speech using the AI SDK's `generateSpeech` and `runpod.speech(...)`:
@@ -626,16 +636,16 @@ Check out our [examples](https://github.com/runpod/examples/tree/main/ai-sdk/get
 
 Use `providerOptions.runpod` for model-specific parameters:
 
-| Option              | Type      | Default | Description                                    |
-| ------------------- | --------- | ------- | ---------------------------------------------- |
-| `audio`             | `string`  | -       | URL to audio file (alternative to binary data) |
-| `prompt`            | `string`  | -       | Context prompt to guide transcription          |
-| `language`          | `string`  | Auto    | ISO-639-1 language code (e.g., 'en', 'es')     |
-| `word_timestamps`   | `boolean` | `false` | Include word-level timestamps                  |
-| `translate`         | `boolean` | `false` | Translate audio to English                     |
-| `enable_vad`        | `boolean` | `false` | Enable voice activity detection                |
-| `maxPollAttempts`   | `number`  | `120`   | Max polling attempts                           |
-| `pollIntervalMillis`| `number`  | `2000`  | Polling interval (ms)                          |
+| Option               | Type      | Default | Description                                    |
+| -------------------- | --------- | ------- | ---------------------------------------------- |
+| `audio`              | `string`  | -       | URL to audio file (alternative to binary data) |
+| `prompt`             | `string`  | -       | Context prompt to guide transcription          |
+| `language`           | `string`  | Auto    | ISO-639-1 language code (e.g., 'en', 'es')     |
+| `word_timestamps`    | `boolean` | `false` | Include word-level timestamps                  |
+| `translate`          | `boolean` | `false` | Translate audio to English                     |
+| `enable_vad`         | `boolean` | `false` | Enable voice activity detection                |
+| `maxPollAttempts`    | `number`  | `120`   | Max polling attempts                           |
+| `pollIntervalMillis` | `number`  | `2000`  | Polling interval (ms)                          |
 
 **Example (providerOptions):**
 
@@ -653,6 +663,97 @@ const result = await transcribe({
 });
 ```
 
+## Video Models
+
+Generate videos using the AI SDK's `experimental_generateVideo` and `runpod.video(...)`:
+
+```ts
+import { runpod } from '@runpod/ai-sdk-provider';
+import { experimental_generateVideo as generateVideo } from 'ai';
+
+// Text-to-video
+const result = await generateVideo({
+  model: runpod.video('alibaba/wan-2.6-t2v'),
+  prompt: 'A golden retriever running on a sunny beach, cinematic, 4k',
+});
+
+console.log(result.video.url);
+```
+
+```ts
+// Image-to-video
+const result = await generateVideo({
+  model: runpod.video('alibaba/wan-2.6-i2v'),
+  prompt: 'Animate this scene with gentle camera movement',
+  image: new URL('https://example.com/image.png'),
+});
+
+console.log(result.video.url);
+```
+
+**Returns:**
+
+- `result.video` - Generated video (`{ type: 'url', url, mediaType: 'video/mp4' }`)
+- `result.warnings` - Array of any warnings
+- `result.providerMetadata.runpod.jobId` - Runpod job ID
+
+### Examples
+
+Check out our [examples](https://github.com/runpod/examples/tree/main/ai-sdk/getting-started) for more code snippets on how to use all the different models.
+
+### Supported Models
+
+| Model ID                                | Type        | Company             |
+| --------------------------------------- | ----------- | ------------------- |
+| `pruna/p-video`                         | t2v         | Pruna AI            |
+| `vidu/q3-t2v`                           | t2v         | Shengshu Technology |
+| `vidu/q3-i2v`                           | i2v         | Shengshu Technology |
+| `kwaivgi/kling-v2.6-std-motion-control` | i2v + video | KwaiVGI (Kuaishou)  |
+| `kwaivgi/kling-video-o1-r2v`            | i2v         | KwaiVGI (Kuaishou)  |
+| `kwaivgi/kling-v2.1-i2v-pro`            | i2v         | KwaiVGI (Kuaishou)  |
+| `alibaba/wan-2.6-t2v`                   | t2v         | Alibaba             |
+| `alibaba/wan-2.6-i2v`                   | i2v         | Alibaba             |
+| `alibaba/wan-2.5`                       | i2v         | Alibaba             |
+| `alibaba/wan-2.2-t2v-720-lora`          | i2v         | Alibaba             |
+| `alibaba/wan-2.2-i2v-720`               | i2v         | Alibaba             |
+| `alibaba/wan-2.1-i2v-720`               | i2v         | Alibaba             |
+| `bytedance/seedance-v1.5-pro-i2v`       | i2v         | ByteDance           |
+| `openai/sora-2-pro-i2v`                 | i2v         | OpenAI              |
+| `openai/sora-2-i2v`                     | i2v         | OpenAI              |
+
+### Provider Options
+
+Use `providerOptions.runpod` for model-specific parameters:
+
+| Option                | Type     | Default | Description                          |
+| --------------------- | -------- | ------- | ------------------------------------ |
+| `negative_prompt`     | `string` | -       | What to avoid in the generated video |
+| `guidance_scale`      | `number` | -       | Guidance scale for prompt adherence  |
+| `num_inference_steps` | `number` | -       | Number of inference steps            |
+| `style`               | `string` | -       | Style preset (model-specific)        |
+| `maxPollAttempts`     | `number` | `120`   | Max polling attempts                 |
+| `pollIntervalMillis`  | `number` | `5000`  | Polling interval (ms)                |
+
+Any additional model-specific parameters can be passed through `providerOptions.runpod` and will be forwarded to the API.
+
+**Example (providerOptions):**
+
+```ts
+const result = await generateVideo({
+  model: runpod.video('alibaba/wan-2.6-t2v'),
+  prompt: 'A serene mountain landscape with flowing water',
+  duration: 5,
+  aspectRatio: '16:9',
+  seed: 42,
+  providerOptions: {
+    runpod: {
+      negative_prompt: 'blurry, low quality',
+      guidance_scale: 7.5,
+    },
+  },
+});
+```
+
 ## About Runpod
 
 [Runpod](https://runpod.io) is the foundation for developers to build, deploy, and scale custom AI systems.

package/dist/index.d.mts

@@ -1,4 +1,4 @@
-import { LanguageModelV3, ImageModelV3, SpeechModelV3, TranscriptionModelV3 } from '@ai-sdk/provider';
+import { LanguageModelV3, ImageModelV3, SpeechModelV3, TranscriptionModelV3, Experimental_VideoModelV3 } from '@ai-sdk/provider';
 import { FetchFunction } from '@ai-sdk/provider-utils';
 export { OpenAICompatibleErrorData as RunpodErrorData } from '@ai-sdk/openai-compatible';
 import { z } from 'zod';
@@ -64,6 +64,14 @@ interface RunpodProvider {
   Creates a transcription model for audio transcription.
   */
     transcription(modelId: string): TranscriptionModelV3;
+    /**
+  Creates a video model for video generation.
+  */
+    videoModel(modelId: string): Experimental_VideoModelV3;
+    /**
+  Creates a video model for video generation.
+  */
+    video(modelId: string): Experimental_VideoModelV3;
 }
 declare function createRunpod(options?: RunpodProviderSettings): RunpodProvider;
 declare const runpod: RunpodProvider;
@@ -72,7 +80,7 @@ type RunpodChatModelId = 'qwen/qwen3-32b-awq' | (string & {});
 
 type RunpodCompletionModelId = 'qwen/qwen3-32b-awq' | (string & {});
 
-type RunpodImageModelId = 'qwen/qwen-image' | 'qwen/qwen-image-edit' | 'qwen/qwen-image-edit-2511' | 'bytedance/seedream-3.0' | 'bytedance/seedream-4.0' | 'bytedance/seedream-4.0-edit' | 'black-forest-labs/flux-1-kontext-dev' | 'black-forest-labs/flux-1-schnell' | 'black-forest-labs/flux-1-dev' | 'alibaba/wan-2.6' | 'google/nano-banana-edit' | 'nano-banana-edit';
+type RunpodImageModelId = 'qwen/qwen-image' | 'qwen/qwen-image-edit' | 'qwen/qwen-image-edit-2511' | 'bytedance/seedream-3.0' | 'bytedance/seedream-4.0' | 'bytedance/seedream-4.0-edit' | 'black-forest-labs/flux-1-kontext-dev' | 'black-forest-labs/flux-1-schnell' | 'black-forest-labs/flux-1-dev' | 'alibaba/wan-2.6' | 'tongyi-mai/z-image-turbo' | 'google/nano-banana-edit' | 'nano-banana-edit' | 'google/nano-banana-2-edit';
 
 type RunpodTranscriptionModelId = 'pruna/whisper-v3-large' | (string & {});
 interface RunpodTranscriptionProviderOptions {
@@ -133,6 +141,41 @@ interface RunpodTranscriptionProviderOptions {
     pollIntervalMillis?: number;
 }
 
+type RunpodVideoModelId = 'pruna/p-video' | 'vidu/q3-t2v' | 'vidu/q3-i2v' | 'kwaivgi/kling-v2.6-std-motion-control' | 'kwaivgi/kling-video-o1-r2v' | 'kwaivgi/kling-v2.1-i2v-pro' | 'alibaba/wan-2.6-t2v' | 'alibaba/wan-2.6-i2v' | 'alibaba/wan-2.5' | 'alibaba/wan-2.2-t2v-720-lora' | 'alibaba/wan-2.2-i2v-720' | 'alibaba/wan-2.1-i2v-720' | 'bytedance/seedance-v1.5-pro-i2v' | 'openai/sora-2-pro-i2v' | 'openai/sora-2-i2v' | (string & {});
+interface RunpodVideoProviderOptions {
+    /**
+     * Negative prompt to guide what to avoid in the generated video.
+     */
+    negative_prompt?: string;
+    /**
+     * Style preset for video generation (model-specific).
+     */
+    style?: string;
+    /**
+     * Guidance scale for prompt adherence.
+     */
+    guidance_scale?: number;
+    /**
+     * Number of inference steps.
+     */
+    num_inference_steps?: number;
+    /**
+     * Maximum number of polling attempts before timing out.
+     * @default 120
+     */
+    maxPollAttempts?: number;
+    /**
+     * Interval between polling attempts in milliseconds.
+     * @default 5000
+     */
+    pollIntervalMillis?: number;
+    /**
+     * Additional model-specific parameters are passed through via
+     * index signature.
+     */
+    [key: string]: unknown;
+}
+
 declare const runpodImageErrorSchema: z.ZodObject<{
     error: z.ZodOptional<z.ZodString>;
     message: z.ZodOptional<z.ZodString>;
@@ -145,4 +188,4 @@ declare const runpodImageErrorSchema: z.ZodObject<{
 }>;
 type RunpodImageErrorData = z.infer<typeof runpodImageErrorSchema>;
 
-export { type RunpodChatModelId, type RunpodCompletionModelId, type RunpodImageErrorData, type RunpodImageModelId, type RunpodProvider, type RunpodProviderSettings, type RunpodTranscriptionModelId, type RunpodTranscriptionProviderOptions, createRunpod, runpod };
+export { type RunpodChatModelId, type RunpodCompletionModelId, type RunpodImageErrorData, type RunpodImageModelId, type RunpodProvider, type RunpodProviderSettings, type RunpodTranscriptionModelId, type RunpodTranscriptionProviderOptions, type RunpodVideoModelId, type RunpodVideoProviderOptions, createRunpod, runpod };

package/dist/index.d.ts

@@ -1,4 +1,4 @@
-import { LanguageModelV3, ImageModelV3, SpeechModelV3, TranscriptionModelV3 } from '@ai-sdk/provider';
+import { LanguageModelV3, ImageModelV3, SpeechModelV3, TranscriptionModelV3, Experimental_VideoModelV3 } from '@ai-sdk/provider';
 import { FetchFunction } from '@ai-sdk/provider-utils';
 export { OpenAICompatibleErrorData as RunpodErrorData } from '@ai-sdk/openai-compatible';
 import { z } from 'zod';
@@ -64,6 +64,14 @@ interface RunpodProvider {
   Creates a transcription model for audio transcription.
   */
     transcription(modelId: string): TranscriptionModelV3;
+    /**
+  Creates a video model for video generation.
+  */
+    videoModel(modelId: string): Experimental_VideoModelV3;
+    /**
+  Creates a video model for video generation.
+  */
+    video(modelId: string): Experimental_VideoModelV3;
 }
 declare function createRunpod(options?: RunpodProviderSettings): RunpodProvider;
 declare const runpod: RunpodProvider;
@@ -72,7 +80,7 @@ type RunpodChatModelId = 'qwen/qwen3-32b-awq' | (string & {});
 
 type RunpodCompletionModelId = 'qwen/qwen3-32b-awq' | (string & {});
 
-type RunpodImageModelId = 'qwen/qwen-image' | 'qwen/qwen-image-edit' | 'qwen/qwen-image-edit-2511' | 'bytedance/seedream-3.0' | 'bytedance/seedream-4.0' | 'bytedance/seedream-4.0-edit' | 'black-forest-labs/flux-1-kontext-dev' | 'black-forest-labs/flux-1-schnell' | 'black-forest-labs/flux-1-dev' | 'alibaba/wan-2.6' | 'google/nano-banana-edit' | 'nano-banana-edit';
+type RunpodImageModelId = 'qwen/qwen-image' | 'qwen/qwen-image-edit' | 'qwen/qwen-image-edit-2511' | 'bytedance/seedream-3.0' | 'bytedance/seedream-4.0' | 'bytedance/seedream-4.0-edit' | 'black-forest-labs/flux-1-kontext-dev' | 'black-forest-labs/flux-1-schnell' | 'black-forest-labs/flux-1-dev' | 'alibaba/wan-2.6' | 'tongyi-mai/z-image-turbo' | 'google/nano-banana-edit' | 'nano-banana-edit' | 'google/nano-banana-2-edit';
 
 type RunpodTranscriptionModelId = 'pruna/whisper-v3-large' | (string & {});
 interface RunpodTranscriptionProviderOptions {
@@ -133,6 +141,41 @@ interface RunpodTranscriptionProviderOptions {
     pollIntervalMillis?: number;
 }
 
+type RunpodVideoModelId = 'pruna/p-video' | 'vidu/q3-t2v' | 'vidu/q3-i2v' | 'kwaivgi/kling-v2.6-std-motion-control' | 'kwaivgi/kling-video-o1-r2v' | 'kwaivgi/kling-v2.1-i2v-pro' | 'alibaba/wan-2.6-t2v' | 'alibaba/wan-2.6-i2v' | 'alibaba/wan-2.5' | 'alibaba/wan-2.2-t2v-720-lora' | 'alibaba/wan-2.2-i2v-720' | 'alibaba/wan-2.1-i2v-720' | 'bytedance/seedance-v1.5-pro-i2v' | 'openai/sora-2-pro-i2v' | 'openai/sora-2-i2v' | (string & {});
+interface RunpodVideoProviderOptions {
+    /**
+     * Negative prompt to guide what to avoid in the generated video.
+     */
+    negative_prompt?: string;
+    /**
+     * Style preset for video generation (model-specific).
+     */
+    style?: string;
+    /**
+     * Guidance scale for prompt adherence.
+     */
+    guidance_scale?: number;
+    /**
+     * Number of inference steps.
+     */
+    num_inference_steps?: number;
+    /**
+     * Maximum number of polling attempts before timing out.
+     * @default 120
+     */
+    maxPollAttempts?: number;
+    /**
+     * Interval between polling attempts in milliseconds.
+     * @default 5000
+     */
+    pollIntervalMillis?: number;
+    /**
+     * Additional model-specific parameters are passed through via
+     * index signature.
+     */
+    [key: string]: unknown;
+}
+
 declare const runpodImageErrorSchema: z.ZodObject<{
     error: z.ZodOptional<z.ZodString>;
     message: z.ZodOptional<z.ZodString>;
@@ -145,4 +188,4 @@ declare const runpodImageErrorSchema: z.ZodObject<{
 }>;
 type RunpodImageErrorData = z.infer<typeof runpodImageErrorSchema>;
 
-export { type RunpodChatModelId, type RunpodCompletionModelId, type RunpodImageErrorData, type RunpodImageModelId, type RunpodProvider, type RunpodProviderSettings, type RunpodTranscriptionModelId, type RunpodTranscriptionProviderOptions, createRunpod, runpod };
+export { type RunpodChatModelId, type RunpodCompletionModelId, type RunpodImageErrorData, type RunpodImageModelId, type RunpodProvider, type RunpodProviderSettings, type RunpodTranscriptionModelId, type RunpodTranscriptionProviderOptions, type RunpodVideoModelId, type RunpodVideoProviderOptions, createRunpod, runpod };