@ai-sdk/deepinfra 2.0.17 → 2.0.19

package/CHANGELOG.md

@@ -1,5 +1,21 @@
 # @ai-sdk/deepinfra
 
+## 2.0.19
+
+### Patch Changes
+
+- 4de5a1d: chore: excluded tests from src folder in npm package
+- Updated dependencies [4de5a1d]
+  - @ai-sdk/openai-compatible@2.0.18
+  - @ai-sdk/provider@3.0.5
+  - @ai-sdk/provider-utils@4.0.9
+
+## 2.0.18
+
+### Patch Changes
+
+- 2b8369d: chore: add docs to package dist
+
 ## 2.0.17
 
 ### Patch Changes

package/dist/index.js

@@ -161,7 +161,7 @@ async function fileToBlob(file) {
 }
 
 // src/version.ts
-var VERSION = true ? "2.0.17" : "0.0.0-test";
+var VERSION = true ? "2.0.19" : "0.0.0-test";
 
 // src/deepinfra-provider.ts
 function createDeepInfra(options = {}) {

package/dist/index.mjs

@@ -150,7 +150,7 @@ async function fileToBlob(file) {
 }
 
 // src/version.ts
-var VERSION = true ? "2.0.17" : "0.0.0-test";
+var VERSION = true ? "2.0.19" : "0.0.0-test";
 
 // src/deepinfra-provider.ts
 function createDeepInfra(options = {}) {

package/docs/11-deepinfra.mdx

@@ -0,0 +1,292 @@
+---
+title: DeepInfra
+description: Learn how to use DeepInfra's models with the AI SDK.
+---
+
+# DeepInfra Provider
+
+The [DeepInfra](https://deepinfra.com) provider contains support for state-of-the-art models through the DeepInfra API, including Llama 3, Mixtral, Qwen, and many other popular open-source models.
+
+## Setup
+
+The DeepInfra provider is available via the `@ai-sdk/deepinfra` module. You can install it with:
+
+<Tabs items={['pnpm', 'npm', 'yarn', 'bun']}>
+  <Tab>
+    <Snippet text="pnpm add @ai-sdk/deepinfra" dark />
+  </Tab>
+  <Tab>
+    <Snippet text="npm install @ai-sdk/deepinfra" dark />
+  </Tab>
+  <Tab>
+    <Snippet text="yarn add @ai-sdk/deepinfra" dark />
+  </Tab>
+
+  <Tab>
+    <Snippet text="bun add @ai-sdk/deepinfra" dark />
+  </Tab>
+</Tabs>
+
+## Provider Instance
+
+You can import the default provider instance `deepinfra` from `@ai-sdk/deepinfra`:
+
+```ts
+import { deepinfra } from '@ai-sdk/deepinfra';
+```
+
+If you need a customized setup, you can import `createDeepInfra` from `@ai-sdk/deepinfra` and create a provider instance with your settings:
+
+```ts
+import { createDeepInfra } from '@ai-sdk/deepinfra';
+
+const deepinfra = createDeepInfra({
+  apiKey: process.env.DEEPINFRA_API_KEY ?? '',
+});
+```
+
+You can use the following optional settings to customize the DeepInfra provider instance:
+
+- **baseURL** _string_
+
+  Use a different URL prefix for API calls, e.g. to use proxy servers.
+  The default prefix is `https://api.deepinfra.com/v1`.
+
+  Note: Language models and embeddings use OpenAI-compatible endpoints at `{baseURL}/openai`,
+  while image models use `{baseURL}/inference`.
+
+- **apiKey** _string_
+
+  API key that is being sent using the `Authorization` header. It defaults to
+  the `DEEPINFRA_API_KEY` environment variable.
+
+- **headers** _Record&lt;string,string&gt;_
+
+  Custom headers to include in the requests.
+
+- **fetch** _(input: RequestInfo, init?: RequestInit) => Promise&lt;Response&gt;_
+
+  Custom [fetch](https://developer.mozilla.org/en-US/docs/Web/API/fetch) implementation.
+  Defaults to the global `fetch` function.
+  You can use it as a middleware to intercept requests,
+  or to provide a custom fetch implementation for e.g. testing.
+
+## Language Models
+
+You can create language models using a provider instance. The first argument is the model ID, for example:
+
+```ts
+import { deepinfra } from '@ai-sdk/deepinfra';
+import { generateText } from 'ai';
+
+const { text } = await generateText({
+  model: deepinfra('meta-llama/Meta-Llama-3.1-70B-Instruct'),
+  prompt: 'Write a vegetarian lasagna recipe for 4 people.',
+});
+```
+
+DeepInfra language models can also be used in the `streamText` function (see [AI SDK Core](/docs/ai-sdk-core)).
+
+## Model Capabilities
+
+| Model                                               | Image Input         | Object Generation   | Tool Usage          | Tool Streaming      |
+| --------------------------------------------------- | ------------------- | ------------------- | ------------------- | ------------------- |
+| `meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8` | <Check size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `meta-llama/Llama-4-Scout-17B-16E-Instruct`         | <Check size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `meta-llama/Llama-3.3-70B-Instruct-Turbo`           | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `meta-llama/Llama-3.3-70B-Instruct`                 | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `meta-llama/Meta-Llama-3.1-405B-Instruct`           | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo`      | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `meta-llama/Meta-Llama-3.1-70B-Instruct`            | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo`       | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> |
+| `meta-llama/Meta-Llama-3.1-8B-Instruct`             | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `meta-llama/Llama-3.2-11B-Vision-Instruct`          | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `meta-llama/Llama-3.2-90B-Vision-Instruct`          | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `mistralai/Mixtral-8x7B-Instruct-v0.1`              | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> |
+| `deepseek-ai/DeepSeek-V3`                           | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `deepseek-ai/DeepSeek-R1`                           | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `deepseek-ai/DeepSeek-R1-Distill-Llama-70B`         | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `deepseek-ai/DeepSeek-R1-Turbo`                     | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `nvidia/Llama-3.1-Nemotron-70B-Instruct`            | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> |
+| `Qwen/Qwen2-7B-Instruct`                            | <Cross size={18} /> | <Check size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `Qwen/Qwen2.5-72B-Instruct`                         | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `Qwen/Qwen2.5-Coder-32B-Instruct`                   | <Cross size={18} /> | <Check size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `Qwen/QwQ-32B-Preview`                              | <Cross size={18} /> | <Check size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `google/codegemma-7b-it`                            | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `google/gemma-2-9b-it`                              | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `microsoft/WizardLM-2-8x22B`                        | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+
+<Note>
+  The table above lists popular models. Please see the [DeepInfra
+  docs](https://deepinfra.com) for a full list of available models. You can also
+  pass any available provider model ID as a string if needed.
+</Note>
+
+## Image Models
+
+You can create DeepInfra image models using the `.image()` factory method.
+For more on image generation with the AI SDK see [generateImage()](/docs/reference/ai-sdk-core/generate-image).
+
+```ts
+import { deepinfra } from '@ai-sdk/deepinfra';
+import { generateImage } from 'ai';
+
+const { image } = await generateImage({
+  model: deepinfra.image('stabilityai/sd3.5'),
+  prompt: 'A futuristic cityscape at sunset',
+  aspectRatio: '16:9',
+});
+```
+
+<Note>
+  Model support for `size` and `aspectRatio` parameters varies by model. Please
+  check the individual model documentation on [DeepInfra's models
+  page](https://deepinfra.com/models/text-to-image) for supported options and
+  additional parameters.
+</Note>
+
+### Model-specific options
+
+You can pass model-specific parameters using the `providerOptions.deepinfra` field:
+
+```ts
+import { deepinfra } from '@ai-sdk/deepinfra';
+import { generateImage } from 'ai';
+
+const { image } = await generateImage({
+  model: deepinfra.image('stabilityai/sd3.5'),
+  prompt: 'A futuristic cityscape at sunset',
+  aspectRatio: '16:9',
+  providerOptions: {
+    deepinfra: {
+      num_inference_steps: 30, // Control the number of denoising steps (1-50)
+    },
+  },
+});
+```
+
+### Image Editing
+
+DeepInfra supports image editing through models like `Qwen/Qwen-Image-Edit`. Pass input images via `prompt.images` to transform or edit existing images.
+
+#### Basic Image Editing
+
+Transform an existing image using text prompts:
+
+```ts
+const imageBuffer = readFileSync('./input-image.png');
+
+const { images } = await generateImage({
+  model: deepinfra.image('Qwen/Qwen-Image-Edit'),
+  prompt: {
+    text: 'Turn the cat into a golden retriever dog',
+    images: [imageBuffer],
+  },
+  size: '1024x1024',
+});
+```
+
+#### Inpainting with Mask
+
+Edit specific parts of an image using a mask. Transparent areas in the mask indicate where the image should be edited:
+
+```ts
+const image = readFileSync('./input-image.png');
+const mask = readFileSync('./mask.png');
+
+const { images } = await generateImage({
+  model: deepinfra.image('Qwen/Qwen-Image-Edit'),
+  prompt: {
+    text: 'A sunlit indoor lounge area with a pool containing a flamingo',
+    images: [image],
+    mask: mask,
+  },
+});
+```
+
+#### Multi-Image Combining
+
+Combine multiple reference images into a single output:
+
+```ts
+const cat = readFileSync('./cat.png');
+const dog = readFileSync('./dog.png');
+
+const { images } = await generateImage({
+  model: deepinfra.image('Qwen/Qwen-Image-Edit'),
+  prompt: {
+    text: 'Create a scene with both animals together, playing as friends',
+    images: [cat, dog],
+  },
+});
+```
+
+<Note>
+  Input images can be provided as `Buffer`, `ArrayBuffer`, `Uint8Array`, or
+  base64-encoded strings. DeepInfra uses an OpenAI-compatible image editing API
+  at `https://api.deepinfra.com/v1/openai/images/edits`.
+</Note>
+
+### Model Capabilities
+
+For models supporting aspect ratios, the following ratios are typically supported:
+`1:1 (default), 16:9, 1:9, 3:2, 2:3, 4:5, 5:4, 9:16, 9:21`
+
+For models supporting size parameters, dimensions must typically be:
+
+- Multiples of 32
+- Width and height between 256 and 1440 pixels
+- Default size is 1024x1024
+
+| Model                              | Dimensions Specification | Notes                                                    |
+| ---------------------------------- | ------------------------ | -------------------------------------------------------- |
+| `stabilityai/sd3.5`                | Aspect Ratio             | Premium quality base model, 8B parameters                |
+| `black-forest-labs/FLUX-1.1-pro`   | Size                     | Latest state-of-art model with superior prompt following |
+| `black-forest-labs/FLUX-1-schnell` | Size                     | Fast generation in 1-4 steps                             |
+| `black-forest-labs/FLUX-1-dev`     | Size                     | Optimized for anatomical accuracy                        |
+| `black-forest-labs/FLUX-pro`       | Size                     | Flagship Flux model                                      |
+| `stabilityai/sd3.5-medium`         | Aspect Ratio             | Balanced 2.5B parameter model                            |
+| `stabilityai/sdxl-turbo`           | Aspect Ratio             | Optimized for fast generation                            |
+
+For more details and pricing information, see the [DeepInfra text-to-image models page](https://deepinfra.com/models/text-to-image).
+
+## Embedding Models
+
+You can create DeepInfra embedding models using the `.embedding()` factory method.
+For more on embedding models with the AI SDK see [embed()](/docs/reference/ai-sdk-core/embed).
+
+```ts
+import { deepinfra } from '@ai-sdk/deepinfra';
+import { embed } from 'ai';
+
+const { embedding } = await embed({
+  model: deepinfra.embedding('BAAI/bge-large-en-v1.5'),
+  value: 'sunny day at the beach',
+});
+```
+
+### Model Capabilities
+
+| Model                                                 | Dimensions | Max Tokens |
+| ----------------------------------------------------- | ---------- | ---------- |
+| `BAAI/bge-base-en-v1.5`                               | 768        | 512        |
+| `BAAI/bge-large-en-v1.5`                              | 1024       | 512        |
+| `BAAI/bge-m3`                                         | 1024       | 8192       |
+| `intfloat/e5-base-v2`                                 | 768        | 512        |
+| `intfloat/e5-large-v2`                                | 1024       | 512        |
+| `intfloat/multilingual-e5-large`                      | 1024       | 512        |
+| `sentence-transformers/all-MiniLM-L12-v2`             | 384        | 256        |
+| `sentence-transformers/all-MiniLM-L6-v2`              | 384        | 256        |
+| `sentence-transformers/all-mpnet-base-v2`             | 768        | 384        |
+| `sentence-transformers/clip-ViT-B-32`                 | 512        | 77         |
+| `sentence-transformers/clip-ViT-B-32-multilingual-v1` | 512        | 77         |
+| `sentence-transformers/multi-qa-mpnet-base-dot-v1`    | 768        | 512        |
+| `sentence-transformers/paraphrase-MiniLM-L6-v2`       | 384        | 128        |
+| `shibing624/text2vec-base-chinese`                    | 768        | 512        |
+| `thenlper/gte-base`                                   | 768        | 512        |
+| `thenlper/gte-large`                                  | 1024       | 512        |
+
+<Note>
+  For a complete list of available embedding models, see the [DeepInfra
+  embeddings page](https://deepinfra.com/models/embeddings).
+</Note>

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-sdk/deepinfra",
-  "version": "2.0.17",
+  "version": "2.0.19",
   "license": "Apache-2.0",
   "sideEffects": false,
   "main": "./dist/index.js",
@@ -8,10 +8,18 @@
   "types": "./dist/index.d.ts",
   "files": [
     "dist/**/*",
+    "docs/**/*",
     "src",
+    "!src/**/*.test.ts",
+    "!src/**/*.test-d.ts",
+    "!src/**/__snapshots__",
+    "!src/**/__fixtures__",
     "CHANGELOG.md",
     "README.md"
   ],
+  "directories": {
+    "doc": "./docs"
+  },
   "exports": {
     "./package.json": "./package.json",
     ".": {
@@ -21,16 +29,16 @@
     }
   },
   "dependencies": {
-    "@ai-sdk/openai-compatible": "2.0.17",
-    "@ai-sdk/provider": "3.0.4",
-    "@ai-sdk/provider-utils": "4.0.8"
+    "@ai-sdk/openai-compatible": "2.0.18",
+    "@ai-sdk/provider": "3.0.5",
+    "@ai-sdk/provider-utils": "4.0.9"
   },
   "devDependencies": {
     "@types/node": "20.17.24",
     "tsup": "^8",
     "typescript": "5.8.3",
     "zod": "3.25.76",
-    "@ai-sdk/test-server": "1.0.2",
+    "@ai-sdk/test-server": "1.0.3",
     "@vercel/ai-tsconfig": "0.0.0"
   },
   "peerDependencies": {
@@ -56,7 +64,7 @@
   "scripts": {
     "build": "pnpm clean && tsup --tsconfig tsconfig.build.json",
     "build:watch": "pnpm clean && tsup --watch",
-    "clean": "del-cli dist *.tsbuildinfo",
+    "clean": "del-cli dist docs *.tsbuildinfo",
     "lint": "eslint \"./**/*.ts*\"",
     "type-check": "tsc --build",
     "prettier-check": "prettier --check \"./**/*.ts*\"",

package/src/deepinfra-image-model.test.ts

@@ -1,431 +0,0 @@
-import { createTestServer } from '@ai-sdk/test-server/with-vitest';
-import { describe, expect, it } from 'vitest';
-import { DeepInfraImageModel } from './deepinfra-image-model';
-import { FetchFunction } from '@ai-sdk/provider-utils';
-
-const prompt = 'A cute baby sea otter';
-
-function createBasicModel({
-  headers,
-  fetch,
-  currentDate,
-}: {
-  headers?: () => Record<string, string>;
-  fetch?: FetchFunction;
-  currentDate?: () => Date;
-} = {}) {
-  return new DeepInfraImageModel('stability-ai/sdxl', {
-    provider: 'deepinfra',
-    baseURL: 'https://api.example.com',
-    headers: headers ?? (() => ({ 'api-key': 'test-key' })),
-    fetch,
-    _internal: {
-      currentDate,
-    },
-  });
-}
-
-describe('DeepInfraImageModel', () => {
-  const testDate = new Date('2024-01-01T00:00:00Z');
-  const server = createTestServer({
-    'https://api.example.com/*': {
-      response: {
-        type: 'json-value',
-        body: {
-          images: ['data:image/png;base64,test-image-data'],
-        },
-      },
-    },
-  });
-
-  describe('doGenerate', () => {
-    it('should pass the correct parameters including aspect ratio and seed', async () => {
-      const model = createBasicModel();
-
-      await model.doGenerate({
-        prompt,
-        files: undefined,
-        mask: undefined,
-        n: 1,
-        size: undefined,
-        aspectRatio: '16:9',
-        seed: 42,
-        providerOptions: { deepinfra: { additional_param: 'value' } },
-      });
-
-      expect(await server.calls[0].requestBodyJson).toStrictEqual({
-        prompt,
-        aspect_ratio: '16:9',
-        seed: 42,
-        num_images: 1,
-        additional_param: 'value',
-      });
-    });
-
-    it('should call the correct url', async () => {
-      const model = createBasicModel();
-
-      await model.doGenerate({
-        prompt,
-        files: undefined,
-        mask: undefined,
-        n: 1,
-        size: undefined,
-        aspectRatio: undefined,
-        seed: undefined,
-        providerOptions: {},
-      });
-
-      expect(server.calls[0].requestMethod).toStrictEqual('POST');
-      expect(server.calls[0].requestUrl).toStrictEqual(
-        'https://api.example.com/stability-ai/sdxl',
-      );
-    });
-
-    it('should pass headers', async () => {
-      const modelWithHeaders = createBasicModel({
-        headers: () => ({
-          'Custom-Provider-Header': 'provider-header-value',
-        }),
-      });
-
-      await modelWithHeaders.doGenerate({
-        prompt,
-        files: undefined,
-        mask: undefined,
-        n: 1,
-        size: undefined,
-        aspectRatio: undefined,
-        seed: undefined,
-        providerOptions: {},
-        headers: {
-          'Custom-Request-Header': 'request-header-value',
-        },
-      });
-
-      expect(server.calls[0].requestHeaders).toStrictEqual({
-        'content-type': 'application/json',
-        'custom-provider-header': 'provider-header-value',
-        'custom-request-header': 'request-header-value',
-      });
-    });
-
-    it('should handle API errors', async () => {
-      server.urls['https://api.example.com/*'].response = {
-        type: 'error',
-        status: 400,
-        body: JSON.stringify({
-          error: {
-            message: 'Bad Request',
-          },
-        }),
-      };
-
-      const model = createBasicModel();
-      await expect(
-        model.doGenerate({
-          prompt,
-          files: undefined,
-          mask: undefined,
-          n: 1,
-          size: undefined,
-          aspectRatio: undefined,
-          seed: undefined,
-          providerOptions: {},
-        }),
-      ).rejects.toThrow('Bad Request');
-    });
-
-    it('should handle size parameter', async () => {
-      const model = createBasicModel();
-
-      await model.doGenerate({
-        prompt,
-        files: undefined,
-        mask: undefined,
-        n: 1,
-        size: '1024x768',
-        aspectRatio: undefined,
-        seed: 42,
-        providerOptions: {},
-      });
-
-      expect(await server.calls[0].requestBodyJson).toStrictEqual({
-        prompt,
-        width: '1024',
-        height: '768',
-        seed: 42,
-        num_images: 1,
-      });
-    });
-
-    it('should respect the abort signal', async () => {
-      const model = createBasicModel();
-      const controller = new AbortController();
-
-      const generatePromise = model.doGenerate({
-        prompt,
-        files: undefined,
-        mask: undefined,
-        n: 1,
-        size: undefined,
-        aspectRatio: undefined,
-        seed: undefined,
-        providerOptions: {},
-        abortSignal: controller.signal,
-      });
-
-      controller.abort();
-
-      await expect(generatePromise).rejects.toThrow(
-        'This operation was aborted',
-      );
-    });
-
-    describe('response metadata', () => {
-      it('should include timestamp, headers and modelId in response', async () => {
-        const model = createBasicModel({
-          currentDate: () => testDate,
-        });
-
-        const result = await model.doGenerate({
-          prompt,
-          files: undefined,
-          mask: undefined,
-          n: 1,
-          size: undefined,
-          aspectRatio: undefined,
-          seed: undefined,
-          providerOptions: {},
-        });
-
-        expect(result.response).toStrictEqual({
-          timestamp: testDate,
-          modelId: 'stability-ai/sdxl',
-          headers: expect.any(Object),
-        });
-      });
-
-      it('should include response headers from API call', async () => {
-        server.urls['https://api.example.com/*'].response = {
-          type: 'json-value',
-          headers: {
-            'x-request-id': 'test-request-id',
-          },
-          body: {
-            images: ['data:image/png;base64,test-image-data'],
-          },
-        };
-
-        const model = createBasicModel();
-        const result = await model.doGenerate({
-          prompt,
-          files: undefined,
-          mask: undefined,
-          n: 1,
-          size: undefined,
-          aspectRatio: undefined,
-          seed: undefined,
-          providerOptions: {},
-        });
-
-        expect(result.response.headers).toStrictEqual({
-          'content-length': '52',
-          'x-request-id': 'test-request-id',
-          'content-type': 'application/json',
-        });
-      });
-    });
-  });
-
-  describe('constructor', () => {
-    it('should expose correct provider and model information', () => {
-      const model = createBasicModel();
-
-      expect(model.provider).toBe('deepinfra');
-      expect(model.modelId).toBe('stability-ai/sdxl');
-      expect(model.specificationVersion).toBe('v3');
-      expect(model.maxImagesPerCall).toBe(1);
-    });
-  });
-
-  describe('Image Editing', () => {
-    const editServer = createTestServer({
-      'https://edit.example.com/openai/images/edits': {
-        response: {
-          type: 'json-value',
-          body: {
-            created: 1234567890,
-            data: [{ b64_json: 'edited-image-base64' }],
-          },
-        },
-      },
-    });
-
-    // Model with baseURL that will resolve to edit endpoint
-    const editModel = new DeepInfraImageModel(
-      'black-forest-labs/FLUX.1-Kontext-dev',
-      {
-        provider: 'deepinfra',
-        baseURL: 'https://edit.example.com/inference',
-        headers: () => ({ 'api-key': 'test-key' }),
-      },
-    );
-
-    it('should send edit request with files', async () => {
-      const imageData = new Uint8Array([137, 80, 78, 71]); // PNG magic bytes
-
-      const result = await editModel.doGenerate({
-        prompt: 'Turn the cat into a dog',
-        files: [
-          {
-            type: 'file',
-            data: imageData,
-            mediaType: 'image/png',
-          },
-        ],
-        mask: undefined,
-        n: 1,
-        size: '1024x1024',
-        aspectRatio: undefined,
-        seed: undefined,
-        providerOptions: {},
-      });
-
-      expect(result.images).toStrictEqual(['edited-image-base64']);
-      expect(editServer.calls[0].requestUrl).toBe(
-        'https://edit.example.com/openai/images/edits',
-      );
-    });
-
-    it('should send edit request with files and mask', async () => {
-      const imageData = new Uint8Array([137, 80, 78, 71]);
-      const maskData = new Uint8Array([255, 255, 255, 0]);
-
-      const result = await editModel.doGenerate({
-        prompt: 'Add a flamingo to the pool',
-        files: [
-          {
-            type: 'file',
-            data: imageData,
-            mediaType: 'image/png',
-          },
-        ],
-        mask: {
-          type: 'file',
-          data: maskData,
-          mediaType: 'image/png',
-        },
-        n: 1,
-        size: undefined,
-        aspectRatio: undefined,
-        seed: undefined,
-        providerOptions: {},
-      });
-
-      expect(result.images).toStrictEqual(['edited-image-base64']);
-      expect(editServer.calls[0].requestUrl).toBe(
-        'https://edit.example.com/openai/images/edits',
-      );
-    });
-
-    it('should send edit request with multiple images', async () => {
-      const image1 = new Uint8Array([137, 80, 78, 71]);
-      const image2 = new Uint8Array([137, 80, 78, 71]);
-
-      const result = await editModel.doGenerate({
-        prompt: 'Combine these images',
-        files: [
-          {
-            type: 'file',
-            data: image1,
-            mediaType: 'image/png',
-          },
-          {
-            type: 'file',
-            data: image2,
-            mediaType: 'image/png',
-          },
-        ],
-        mask: undefined,
-        n: 1,
-        size: undefined,
-        aspectRatio: undefined,
-        seed: undefined,
-        providerOptions: {},
-      });
-
-      expect(result.images).toStrictEqual(['edited-image-base64']);
-    });
-
-    it('should include response metadata for edit requests', async () => {
-      const testDate = new Date('2024-01-01T00:00:00Z');
-      const modelWithDate = new DeepInfraImageModel(
-        'black-forest-labs/FLUX.1-Kontext-dev',
-        {
-          provider: 'deepinfra',
-          baseURL: 'https://edit.example.com/inference',
-          headers: () => ({ 'api-key': 'test-key' }),
-          _internal: {
-            currentDate: () => testDate,
-          },
-        },
-      );
-
-      const imageData = new Uint8Array([137, 80, 78, 71]);
-
-      const result = await modelWithDate.doGenerate({
-        prompt: 'Edit this image',
-        files: [
-          {
-            type: 'file',
-            data: imageData,
-            mediaType: 'image/png',
-          },
-        ],
-        mask: undefined,
-        n: 1,
-        size: undefined,
-        aspectRatio: undefined,
-        seed: undefined,
-        providerOptions: {},
-      });
-
-      expect(result.response).toStrictEqual({
-        timestamp: testDate,
-        modelId: 'black-forest-labs/FLUX.1-Kontext-dev',
-        headers: expect.any(Object),
-      });
-    });
-
-    it('should pass provider options in edit request', async () => {
-      const imageData = new Uint8Array([137, 80, 78, 71]);
-
-      await editModel.doGenerate({
-        prompt: 'Edit with custom options',
-        files: [
-          {
-            type: 'file',
-            data: imageData,
-            mediaType: 'image/png',
-          },
-        ],
-        mask: undefined,
-        n: 1,
-        size: undefined,
-        aspectRatio: undefined,
-        seed: undefined,
-        providerOptions: {
-          deepinfra: {
-            guidance: 7.5,
-          },
-        },
-      });
-
-      // The request should have been made to the edit endpoint
-      expect(editServer.calls[0].requestUrl).toBe(
-        'https://edit.example.com/openai/images/edits',
-      );
-    });
-  });
-});

package/src/deepinfra-provider.test.ts

@@ -1,184 +0,0 @@
-import { DeepInfraImageModel } from './deepinfra-image-model';
-import { createDeepInfra } from './deepinfra-provider';
-import {
-  OpenAICompatibleChatLanguageModel,
-  OpenAICompatibleCompletionLanguageModel,
-  OpenAICompatibleEmbeddingModel,
-} from '@ai-sdk/openai-compatible';
-import { LanguageModelV3, EmbeddingModelV3 } from '@ai-sdk/provider';
-import { loadApiKey } from '@ai-sdk/provider-utils';
-import { describe, it, expect, vi, beforeEach, Mock } from 'vitest';
-
-// Add type assertion for the mocked class
-const OpenAICompatibleChatLanguageModelMock =
-  OpenAICompatibleChatLanguageModel as unknown as Mock;
-
-vi.mock('@ai-sdk/openai-compatible', () => ({
-  OpenAICompatibleChatLanguageModel: vi.fn(),
-  OpenAICompatibleCompletionLanguageModel: vi.fn(),
-  OpenAICompatibleEmbeddingModel: vi.fn(),
-}));
-
-vi.mock('@ai-sdk/provider-utils', async () => {
-  const actual = await vi.importActual('@ai-sdk/provider-utils');
-  return {
-    ...actual,
-    loadApiKey: vi.fn().mockReturnValue('mock-api-key'),
-    withoutTrailingSlash: vi.fn(url => url),
-  };
-});
-
-vi.mock('./deepinfra-image-model', () => ({
-  DeepInfraImageModel: vi.fn(),
-}));
-
-describe('DeepInfraProvider', () => {
-  let mockLanguageModel: LanguageModelV3;
-  let mockEmbeddingModel: EmbeddingModelV3;
-
-  beforeEach(() => {
-    // Mock implementations of models
-    mockLanguageModel = {
-      // Add any required methods for LanguageModelV3
-    } as LanguageModelV3;
-    mockEmbeddingModel = {
-      // Add any required methods for EmbeddingModelV3
-    } as EmbeddingModelV3;
-
-    // Reset mocks
-    vi.clearAllMocks();
-  });
-
-  describe('createDeepInfra', () => {
-    it('should create a DeepInfraProvider instance with default options', () => {
-      const provider = createDeepInfra();
-      const model = provider('model-id');
-
-      // Use the mocked version
-      const constructorCall =
-        OpenAICompatibleChatLanguageModelMock.mock.calls[0];
-      const config = constructorCall[1];
-      config.headers();
-
-      expect(loadApiKey).toHaveBeenCalledWith({
-        apiKey: undefined,
-        environmentVariableName: 'DEEPINFRA_API_KEY',
-        description: "DeepInfra's API key",
-      });
-    });
-
-    it('should create a DeepInfraProvider instance with custom options', () => {
-      const options = {
-        apiKey: 'custom-key',
-        baseURL: 'https://custom.url',
-        headers: { 'Custom-Header': 'value' },
-      };
-      const provider = createDeepInfra(options);
-      const model = provider('model-id');
-
-      const constructorCall =
-        OpenAICompatibleChatLanguageModelMock.mock.calls[0];
-      const config = constructorCall[1];
-      config.headers();
-
-      expect(loadApiKey).toHaveBeenCalledWith({
-        apiKey: 'custom-key',
-        environmentVariableName: 'DEEPINFRA_API_KEY',
-        description: "DeepInfra's API key",
-      });
-    });
-
-    it('should return a chat model when called as a function', () => {
-      const provider = createDeepInfra();
-      const modelId = 'foo-model-id';
-
-      const model = provider(modelId);
-      expect(model).toBeInstanceOf(OpenAICompatibleChatLanguageModel);
-    });
-  });
-
-  describe('chatModel', () => {
-    it('should construct a chat model with correct configuration', () => {
-      const provider = createDeepInfra();
-      const modelId = 'deepinfra-chat-model';
-
-      const model = provider.chatModel(modelId);
-
-      expect(model).toBeInstanceOf(OpenAICompatibleChatLanguageModel);
-      expect(OpenAICompatibleChatLanguageModelMock).toHaveBeenCalledWith(
-        modelId,
-        expect.objectContaining({
-          provider: 'deepinfra.chat',
-        }),
-      );
-    });
-  });
-
-  describe('completionModel', () => {
-    it('should construct a completion model with correct configuration', () => {
-      const provider = createDeepInfra();
-      const modelId = 'deepinfra-completion-model';
-
-      const model = provider.completionModel(modelId);
-
-      expect(model).toBeInstanceOf(OpenAICompatibleCompletionLanguageModel);
-    });
-  });
-
-  describe('embeddingModel', () => {
-    it('should construct a text embedding model with correct configuration', () => {
-      const provider = createDeepInfra();
-      const modelId = 'deepinfra-embedding-model';
-
-      const model = provider.embeddingModel(modelId);
-
-      expect(model).toBeInstanceOf(OpenAICompatibleEmbeddingModel);
-    });
-  });
-
-  describe('image', () => {
-    it('should construct an image model with correct configuration', () => {
-      const provider = createDeepInfra();
-      const modelId = 'deepinfra-image-model';
-
-      const model = provider.image(modelId);
-
-      expect(model).toBeInstanceOf(DeepInfraImageModel);
-      expect(DeepInfraImageModel).toHaveBeenCalledWith(
-        modelId,
-        expect.objectContaining({
-          provider: 'deepinfra.image',
-          baseURL: 'https://api.deepinfra.com/v1/inference',
-        }),
-      );
-    });
-
-    it('should use default settings when none provided', () => {
-      const provider = createDeepInfra();
-      const modelId = 'deepinfra-image-model';
-
-      const model = provider.image(modelId);
-
-      expect(model).toBeInstanceOf(DeepInfraImageModel);
-      expect(DeepInfraImageModel).toHaveBeenCalledWith(
-        modelId,
-        expect.any(Object),
-      );
-    });
-
-    it('should respect custom baseURL', () => {
-      const customBaseURL = 'https://custom.api.deepinfra.com';
-      const provider = createDeepInfra({ baseURL: customBaseURL });
-      const modelId = 'deepinfra-image-model';
-
-      const model = provider.image(modelId);
-
-      expect(DeepInfraImageModel).toHaveBeenCalledWith(
-        modelId,
-        expect.objectContaining({
-          baseURL: `${customBaseURL}/inference`,
-        }),
-      );
-    });
-  });
-});