@ai-sdk/togetherai 0.0.0-1c33ba03-20260114162300 → 0.0.0-4115c213-20260122152721

package/docs/24-togetherai.mdx

@@ -0,0 +1,365 @@
+---
+title: Together.ai
+description: Learn how to use Together.ai's models with the AI SDK.
+---
+
+# Together.ai Provider
+
+The [Together.ai](https://together.ai) provider contains support for 200+ open-source models through the [Together.ai API](https://docs.together.ai/reference).
+
+## Setup
+
+The Together.ai provider is available via the `@ai-sdk/togetherai` module. You can
+install it with
+
+<Tabs items={['pnpm', 'npm', 'yarn', 'bun']}>
+  <Tab>
+    <Snippet text="pnpm add @ai-sdk/togetherai" dark />
+  </Tab>
+  <Tab>
+    <Snippet text="npm install @ai-sdk/togetherai" dark />
+  </Tab>
+  <Tab>
+    <Snippet text="yarn add @ai-sdk/togetherai" dark />
+  </Tab>
+
+  <Tab>
+    <Snippet text="bun add @ai-sdk/togetherai" dark />
+  </Tab>
+</Tabs>
+
+## Provider Instance
+
+You can import the default provider instance `togetherai` from `@ai-sdk/togetherai`:
+
+```ts
+import { togetherai } from '@ai-sdk/togetherai';
+```
+
+If you need a customized setup, you can import `createTogetherAI` from `@ai-sdk/togetherai`
+and create a provider instance with your settings:
+
+```ts
+import { createTogetherAI } from '@ai-sdk/togetherai';
+
+const togetherai = createTogetherAI({
+  apiKey: process.env.TOGETHER_AI_API_KEY ?? '',
+});
+```
+
+You can use the following optional settings to customize the Together.ai provider instance:
+
+- **baseURL** _string_
+
+  Use a different URL prefix for API calls, e.g. to use proxy servers.
+  The default prefix is `https://api.together.xyz/v1`.
+
+- **apiKey** _string_
+
+  API key that is being sent using the `Authorization` header. It defaults to
+  the `TOGETHER_AI_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 [Together.ai models](https://docs.together.ai/docs/serverless-models) using a provider instance. The first argument is the model id, e.g. `google/gemma-2-9b-it`.
+
+```ts
+const model = togetherai('google/gemma-2-9b-it');
+```
+
+### Reasoning Models
+
+Together.ai exposes the thinking of `deepseek-ai/DeepSeek-R1` in the generated text using the `<think>` tag.
+You can use the `extractReasoningMiddleware` to extract this reasoning and expose it as a `reasoning` property on the result:
+
+```ts
+import { togetherai } from '@ai-sdk/togetherai';
+import { wrapLanguageModel, extractReasoningMiddleware } from 'ai';
+
+const enhancedModel = wrapLanguageModel({
+  model: togetherai('deepseek-ai/DeepSeek-R1'),
+  middleware: extractReasoningMiddleware({ tagName: 'think' }),
+});
+```
+
+You can then use that enhanced model in functions like `generateText` and `streamText`.
+
+### Example
+
+You can use Together.ai language models to generate text with the `generateText` function:
+
+```ts
+import { togetherai } from '@ai-sdk/togetherai';
+import { generateText } from 'ai';
+
+const { text } = await generateText({
+  model: togetherai('meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo'),
+  prompt: 'Write a vegetarian lasagna recipe for 4 people.',
+});
+```
+
+Together.ai language models can also be used in the `streamText` function
+(see [AI SDK Core](/docs/ai-sdk-core)).
+
+The Together.ai provider also supports [completion models](https://docs.together.ai/docs/serverless-models#language-models) via (following the above example code) `togetherai.completion()` and [embedding models](https://docs.together.ai/docs/serverless-models#embedding-models) via `togetherai.embedding()`.
+
+## Model Capabilities
+
+| Model                                          | Image Input         | Object Generation   | Tool Usage          | Tool Streaming      |
+| ---------------------------------------------- | ------------------- | ------------------- | ------------------- | ------------------- |
+| `meta-llama/Meta-Llama-3.3-70B-Instruct-Turbo` | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo`  | <Cross size={18} /> | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `mistralai/Mixtral-8x22B-Instruct-v0.1`        | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `mistralai/Mistral-7B-Instruct-v0.3`           | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |
+| `deepseek-ai/DeepSeek-V3`                      | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `google/gemma-2b-it`                           | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `Qwen/Qwen2.5-72B-Instruct-Turbo`              | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+| `databricks/dbrx-instruct`                     | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> | <Cross size={18} /> |
+
+<Note>
+  The table above lists popular models. Please see the [Together.ai
+  docs](https://docs.together.ai/docs/serverless-models) 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 Together.ai 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 { togetherai } from '@ai-sdk/togetherai';
+import { generateImage } from 'ai';
+
+const { images } = await generateImage({
+  model: togetherai.image('black-forest-labs/FLUX.1-dev'),
+  prompt: 'A delighted resplendent quetzal mid flight amidst raindrops',
+});
+```
+
+You can pass optional provider-specific request parameters using the `providerOptions` argument.
+
+```ts
+import { togetherai } from '@ai-sdk/togetherai';
+import { generateImage } from 'ai';
+
+const { images } = await generateImage({
+  model: togetherai.image('black-forest-labs/FLUX.1-dev'),
+  prompt: 'A delighted resplendent quetzal mid flight amidst raindrops',
+  size: '512x512',
+  // Optional additional provider-specific request parameters
+  providerOptions: {
+    togetherai: {
+      steps: 40,
+    },
+  },
+});
+```
+
+For a complete list of available provider-specific options, see the [Together.ai Image Generation API Reference](https://docs.together.ai/reference/post_images-generations).
+
+### Image Editing
+
+Together AI supports image editing through FLUX Kontext models. Pass input images via `prompt.images` to transform or edit existing images.
+
+<Note>
+  Together AI does not support mask-based inpainting. Instead, use descriptive
+  prompts to specify what you want to change in the image.
+</Note>
+
+#### Basic Image Editing
+
+Transform an existing image using text prompts:
+
+```ts
+const imageBuffer = readFileSync('./input-image.png');
+
+const { images } = await generateImage({
+  model: togetherai.image('black-forest-labs/FLUX.1-kontext-pro'),
+  prompt: {
+    text: 'Turn the cat into a golden retriever dog',
+    images: [imageBuffer],
+  },
+  size: '1024x1024',
+  providerOptions: {
+    togetherai: {
+      steps: 28,
+    },
+  },
+});
+```
+
+#### Editing with URL Reference
+
+You can also pass image URLs directly:
+
+```ts
+const { images } = await generateImage({
+  model: togetherai.image('black-forest-labs/FLUX.1-kontext-pro'),
+  prompt: {
+    text: 'Make the background a lush rainforest',
+    images: ['https://example.com/photo.png'],
+  },
+  size: '1024x1024',
+  providerOptions: {
+    togetherai: {
+      steps: 28,
+    },
+  },
+});
+```
+
+<Note>
+  Input images can be provided as `Buffer`, `ArrayBuffer`, `Uint8Array`,
+  base64-encoded strings, or URLs. Together AI only supports a single input
+  image per request.
+</Note>
+
+#### Supported Image Editing Models
+
+| Model                                  | Description                        |
+| -------------------------------------- | ---------------------------------- |
+| `black-forest-labs/FLUX.1-kontext-pro` | Production quality, balanced speed |
+| `black-forest-labs/FLUX.1-kontext-max` | Maximum image fidelity             |
+| `black-forest-labs/FLUX.1-kontext-dev` | Development and experimentation    |
+
+### Model Capabilities
+
+Together.ai image models support various image dimensions that vary by model. Common sizes include 512x512, 768x768, and 1024x1024, with some models supporting up to 1792x1792. The default size is 1024x1024.
+
+| Available Models                           |
+| ------------------------------------------ |
+| `stabilityai/stable-diffusion-xl-base-1.0` |
+| `black-forest-labs/FLUX.1-dev`             |
+| `black-forest-labs/FLUX.1-dev-lora`        |
+| `black-forest-labs/FLUX.1-schnell`         |
+| `black-forest-labs/FLUX.1-canny`           |
+| `black-forest-labs/FLUX.1-depth`           |
+| `black-forest-labs/FLUX.1-redux`           |
+| `black-forest-labs/FLUX.1.1-pro`           |
+| `black-forest-labs/FLUX.1-pro`             |
+| `black-forest-labs/FLUX.1-schnell-Free`    |
+
+<Note>
+  Please see the [Together.ai models
+  page](https://docs.together.ai/docs/serverless-models#image-models) for a full
+  list of available image models and their capabilities.
+</Note>
+
+## Embedding Models
+
+You can create Together.ai 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 { togetherai } from '@ai-sdk/togetherai';
+import { embed } from 'ai';
+
+const { embedding } = await embed({
+  model: togetherai.embedding('togethercomputer/m2-bert-80M-2k-retrieval'),
+  value: 'sunny day at the beach',
+});
+```
+
+### Model Capabilities
+
+| Model                                            | Dimensions | Max Tokens |
+| ------------------------------------------------ | ---------- | ---------- |
+| `togethercomputer/m2-bert-80M-2k-retrieval`      | 768        | 2048       |
+| `togethercomputer/m2-bert-80M-8k-retrieval`      | 768        | 8192       |
+| `togethercomputer/m2-bert-80M-32k-retrieval`     | 768        | 32768      |
+| `WhereIsAI/UAE-Large-V1`                         | 1024       | 512        |
+| `BAAI/bge-large-en-v1.5`                         | 1024       | 512        |
+| `BAAI/bge-base-en-v1.5`                          | 768        | 512        |
+| `sentence-transformers/msmarco-bert-base-dot-v5` | 768        | 512        |
+| `bert-base-uncased`                              | 768        | 512        |
+
+<Note>
+  For a complete list of available embedding models, see the [Together.ai models
+  page](https://docs.together.ai/docs/serverless-models#embedding-models).
+</Note>
+
+## Reranking Models
+
+You can create Together.ai reranking models using the `.reranking()` factory method.
+For more on reranking with the AI SDK see [rerank()](/docs/reference/ai-sdk-core/rerank).
+
+```ts
+import { togetherai } from '@ai-sdk/togetherai';
+import { rerank } from 'ai';
+
+const documents = [
+  'sunny day at the beach',
+  'rainy afternoon in the city',
+  'snowy night in the mountains',
+];
+
+const { ranking } = await rerank({
+  model: togetherai.reranking('Salesforce/Llama-Rank-v1'),
+  documents,
+  query: 'talk about rain',
+  topN: 2,
+});
+
+console.log(ranking);
+// [
+//   { originalIndex: 1, score: 0.9, document: 'rainy afternoon in the city' },
+//   { originalIndex: 0, score: 0.3, document: 'sunny day at the beach' }
+// ]
+```
+
+Together.ai reranking models support additional provider options for object documents. You can specify which fields to use for ranking:
+
+```ts
+import { togetherai } from '@ai-sdk/togetherai';
+import { rerank } from 'ai';
+
+const documents = [
+  {
+    from: 'Paul Doe',
+    subject: 'Follow-up',
+    text: 'We are happy to give you a discount of 20%.',
+  },
+  {
+    from: 'John McGill',
+    subject: 'Missing Info',
+    text: 'Here is the pricing from Oracle: $5000/month',
+  },
+];
+
+const { ranking } = await rerank({
+  model: togetherai.reranking('Salesforce/Llama-Rank-v1'),
+  documents,
+  query: 'Which pricing did we get from Oracle?',
+  providerOptions: {
+    togetherai: {
+      rankFields: ['from', 'subject', 'text'], // Specify which fields to rank by
+    },
+  },
+});
+```
+
+The following provider options are available:
+
+- **rankFields** _string[]_
+
+  Array of field names to use for ranking when documents are JSON objects. If not specified, all fields are used.
+
+### Model Capabilities
+
+| Model                                 |
+| ------------------------------------- |
+| `Salesforce/Llama-Rank-v1`            |
+| `mixedbread-ai/Mxbai-Rerank-Large-V2` |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-sdk/togetherai",
-  "version": "0.0.0-1c33ba03-20260114162300",
+  "version": "0.0.0-4115c213-20260122152721",
   "license": "Apache-2.0",
   "sideEffects": false,
   "main": "./dist/index.js",
@@ -8,9 +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",
     ".": {
@@ -20,17 +29,17 @@
     }
   },
   "dependencies": {
-    "@ai-sdk/openai-compatible": "0.0.0-1c33ba03-20260114162300",
-    "@ai-sdk/provider": "3.0.3",
-    "@ai-sdk/provider-utils": "0.0.0-1c33ba03-20260114162300"
+    "@ai-sdk/openai-compatible": "0.0.0-4115c213-20260122152721",
+    "@ai-sdk/provider": "0.0.0-4115c213-20260122152721",
+    "@ai-sdk/provider-utils": "0.0.0-4115c213-20260122152721"
   },
   "devDependencies": {
     "@types/node": "20.17.24",
     "tsup": "^8",
     "typescript": "5.8.3",
     "zod": "3.25.76",
-    "@vercel/ai-tsconfig": "0.0.0",
-    "@ai-sdk/test-server": "1.0.1"
+    "@ai-sdk/test-server": "0.0.0-4115c213-20260122152721",
+    "@vercel/ai-tsconfig": "0.0.0"
   },
   "peerDependencies": {
     "zod": "^3.25.76 || ^4.1.8"
@@ -55,7 +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/index.ts

@@ -0,0 +1,9 @@
+export type { OpenAICompatibleErrorData as TogetherAIErrorData } from '@ai-sdk/openai-compatible';
+export type { TogetherAIRerankingOptions } from './reranking/togetherai-reranking-options';
+export { createTogetherAI, togetherai } from './togetherai-provider';
+export type {
+  TogetherAIProvider,
+  TogetherAIProviderSettings,
+} from './togetherai-provider';
+export type { TogetherAIImageProviderOptions } from './togetherai-image-model';
+export { VERSION } from './version';

package/src/reranking/togetherai-reranking-api.ts

@@ -0,0 +1,43 @@
+import { JSONObject } from '@ai-sdk/provider';
+import { lazySchema, zodSchema } from '@ai-sdk/provider-utils';
+import { z } from 'zod/v4';
+
+// https://docs.together.ai/reference/rerank-1
+export type TogetherAIRerankingInput = {
+  model: string;
+  query: string;
+  documents: JSONObject[] | string[];
+  top_n: number | undefined;
+  return_documents: boolean | undefined;
+  rank_fields: string[] | undefined;
+};
+
+export const togetheraiErrorSchema = lazySchema(() =>
+  zodSchema(
+    z.object({
+      error: z.object({
+        message: z.string(),
+      }),
+    }),
+  ),
+);
+
+export const togetheraiRerankingResponseSchema = lazySchema(() =>
+  zodSchema(
+    z.object({
+      id: z.string().nullish(),
+      model: z.string().nullish(),
+      results: z.array(
+        z.object({
+          index: z.number(),
+          relevance_score: z.number(),
+        }),
+      ),
+      usage: z.object({
+        prompt_tokens: z.number(),
+        completion_tokens: z.number(),
+        total_tokens: z.number(),
+      }),
+    }),
+  ),
+);

package/src/reranking/togetherai-reranking-model.ts

@@ -0,0 +1,101 @@
+import { RerankingModelV3 } from '@ai-sdk/provider';
+import {
+  combineHeaders,
+  createJsonErrorResponseHandler,
+  createJsonResponseHandler,
+  FetchFunction,
+  parseProviderOptions,
+  postJsonToApi,
+} from '@ai-sdk/provider-utils';
+import {
+  togetheraiErrorSchema,
+  TogetherAIRerankingInput,
+  togetheraiRerankingResponseSchema,
+} from './togetherai-reranking-api';
+import {
+  TogetherAIRerankingModelId,
+  togetheraiRerankingOptionsSchema,
+} from './togetherai-reranking-options';
+
+type TogetherAIRerankingConfig = {
+  provider: string;
+  baseURL: string;
+  headers: () => Record<string, string | undefined>;
+  fetch?: FetchFunction;
+};
+
+export class TogetherAIRerankingModel implements RerankingModelV3 {
+  readonly specificationVersion = 'v3';
+  readonly modelId: TogetherAIRerankingModelId;
+
+  private readonly config: TogetherAIRerankingConfig;
+
+  constructor(
+    modelId: TogetherAIRerankingModelId,
+    config: TogetherAIRerankingConfig,
+  ) {
+    this.modelId = modelId;
+    this.config = config;
+  }
+
+  get provider(): string {
+    return this.config.provider;
+  }
+
+  // see https://docs.together.ai/reference/rerank-1
+  async doRerank({
+    documents,
+    headers,
+    query,
+    topN,
+    abortSignal,
+    providerOptions,
+  }: Parameters<RerankingModelV3['doRerank']>[0]): Promise<
+    Awaited<ReturnType<RerankingModelV3['doRerank']>>
+  > {
+    const rerankingOptions = await parseProviderOptions({
+      provider: 'togetherai',
+      providerOptions,
+      schema: togetheraiRerankingOptionsSchema,
+    });
+
+    const {
+      responseHeaders,
+      value: response,
+      rawValue,
+    } = await postJsonToApi({
+      url: `${this.config.baseURL}/rerank`,
+      headers: combineHeaders(this.config.headers(), headers),
+      body: {
+        model: this.modelId,
+        documents: documents.values,
+        query,
+        top_n: topN,
+        rank_fields: rerankingOptions?.rankFields,
+        return_documents: false, // reduce response size
+      } satisfies TogetherAIRerankingInput,
+      failedResponseHandler: createJsonErrorResponseHandler({
+        errorSchema: togetheraiErrorSchema,
+        errorToMessage: data => data.error.message,
+      }),
+      successfulResponseHandler: createJsonResponseHandler(
+        togetheraiRerankingResponseSchema,
+      ),
+      abortSignal,
+      fetch: this.config.fetch,
+    });
+
+    return {
+      ranking: response.results.map(result => ({
+        index: result.index,
+        relevanceScore: result.relevance_score,
+      })),
+      response: {
+        id: response.id ?? undefined,
+        modelId: response.model ?? undefined,
+        headers: responseHeaders,
+        body: rawValue,
+      },
+    };
+  }
+}

package/src/reranking/togetherai-reranking-options.ts

@@ -0,0 +1,27 @@
+import { FlexibleSchema, lazySchema, zodSchema } from '@ai-sdk/provider-utils';
+import { z } from 'zod/v4';
+
+// see https://docs.together.ai/docs/serverless-models#rerank-models
+export type TogetherAIRerankingModelId =
+  | 'Salesforce/Llama-Rank-v1'
+  | 'mixedbread-ai/Mxbai-Rerank-Large-V2'
+  | (string & {});
+
+export type TogetherAIRerankingOptions = {
+  /**
+   * List of keys in the JSON Object document to rank by.
+   * Defaults to use all supplied keys for ranking.
+   *
+   * @example ["title", "text"]
+   */
+  rankFields?: string[];
+};
+
+export const togetheraiRerankingOptionsSchema: FlexibleSchema<TogetherAIRerankingOptions> =
+  lazySchema(() =>
+    zodSchema(
+      z.object({
+        rankFields: z.array(z.string()).optional(),
+      }),
+    ),
+  );

package/src/togetherai-chat-options.ts

@@ -0,0 +1,36 @@
+// https://docs.together.ai/docs/serverless-models#chat-models
+export type TogetherAIChatModelId =
+  | 'meta-llama/Llama-3.3-70B-Instruct-Turbo'
+  | 'meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo'
+  | 'meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo'
+  | 'meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo'
+  | 'meta-llama/Meta-Llama-3-8B-Instruct-Turbo'
+  | 'meta-llama/Meta-Llama-3-70B-Instruct-Turbo'
+  | 'meta-llama/Llama-3.2-3B-Instruct-Turbo'
+  | 'meta-llama/Meta-Llama-3-8B-Instruct-Lite'
+  | 'meta-llama/Meta-Llama-3-70B-Instruct-Lite'
+  | 'meta-llama/Llama-3-8b-chat-hf'
+  | 'meta-llama/Llama-3-70b-chat-hf'
+  | 'nvidia/Llama-3.1-Nemotron-70B-Instruct-HF'
+  | 'Qwen/Qwen2.5-Coder-32B-Instruct'
+  | 'Qwen/QwQ-32B-Preview'
+  | 'microsoft/WizardLM-2-8x22B'
+  | 'google/gemma-2-27b-it'
+  | 'google/gemma-2-9b-it'
+  | 'databricks/dbrx-instruct'
+  | 'deepseek-ai/deepseek-llm-67b-chat'
+  | 'deepseek-ai/DeepSeek-V3'
+  | 'google/gemma-2b-it'
+  | 'Gryphe/MythoMax-L2-13b'
+  | 'meta-llama/Llama-2-13b-chat-hf'
+  | 'mistralai/Mistral-7B-Instruct-v0.1'
+  | 'mistralai/Mistral-7B-Instruct-v0.2'
+  | 'mistralai/Mistral-7B-Instruct-v0.3'
+  | 'mistralai/Mixtral-8x7B-Instruct-v0.1'
+  | 'mistralai/Mixtral-8x22B-Instruct-v0.1'
+  | 'NousResearch/Nous-Hermes-2-Mixtral-8x7B-DPO'
+  | 'Qwen/Qwen2.5-7B-Instruct-Turbo'
+  | 'Qwen/Qwen2.5-72B-Instruct-Turbo'
+  | 'Qwen/Qwen2-72B-Instruct'
+  | 'upstage/SOLAR-10.7B-Instruct-v1.0'
+  | (string & {});

package/src/togetherai-completion-options.ts

@@ -0,0 +1,9 @@
+// https://docs.together.ai/docs/serverless-models#language-models
+export type TogetherAICompletionModelId =
+  | 'meta-llama/Llama-2-70b-hf'
+  | 'mistralai/Mistral-7B-v0.1'
+  | 'mistralai/Mixtral-8x7B-v0.1'
+  | 'Meta-Llama/Llama-Guard-7b'
+  | 'codellama/CodeLlama-34b-Instruct-hf'
+  | 'Qwen/Qwen2.5-Coder-32B-Instruct'
+  | (string & {});

package/src/togetherai-embedding-options.ts

@@ -0,0 +1,11 @@
+// https://docs.together.ai/docs/serverless-models#embedding-models
+export type TogetherAIEmbeddingModelId =
+  | 'togethercomputer/m2-bert-80M-2k-retrieval'
+  | 'togethercomputer/m2-bert-80M-32k-retrieval'
+  | 'togethercomputer/m2-bert-80M-8k-retrieval'
+  | 'WhereIsAI/UAE-Large-V1'
+  | 'BAAI/bge-large-en-v1.5'
+  | 'BAAI/bge-base-en-v1.5'
+  | 'sentence-transformers/msmarco-bert-base-dot-v5'
+  | 'bert-base-uncased'
+  | (string & {});