@ai-sdk/togetherai 2.0.24 → 2.0.26

package/CHANGELOG.md

@@ -1,5 +1,19 @@
 # @ai-sdk/togetherai
 
+## 2.0.26
+
+### Patch Changes
+
+- 1524271: chore: add skill information to README files
+- Updated dependencies [1524271]
+  - @ai-sdk/openai-compatible@2.0.23
+
+## 2.0.25
+
+### Patch Changes
+
+- 3988c08: docs: fix incorrect and outdated provider docs
+
 ## 2.0.24
 
 ### Patch Changes

package/README.md

@@ -10,6 +10,14 @@ The Together.ai provider is available in the `@ai-sdk/togetherai` module. You ca
 npm i @ai-sdk/togetherai
 ```
 
+## Skill for Coding Agents
+
+If you use coding agents such as Claude Code or Cursor, we highly recommend adding the AI SDK skill to your repository:
+
+```shell
+npx skills add vercel/ai
+```
+
 ## Provider Instance
 
 You can import the default provider instance `togetherai` from `@ai-sdk/togetherai`:

package/dist/index.js

@@ -272,7 +272,7 @@ var togetheraiImageProviderOptionsSchema = (0, import_provider_utils4.lazySchema
 );
 
 // src/version.ts
-var VERSION = true ? "2.0.24" : "0.0.0-test";
+var VERSION = true ? "2.0.26" : "0.0.0-test";
 
 // src/togetherai-provider.ts
 function createTogetherAI(options = {}) {

package/dist/index.mjs

@@ -267,7 +267,7 @@ var togetheraiImageProviderOptionsSchema = lazySchema3(
 );
 
 // src/version.ts
-var VERSION = true ? "2.0.24" : "0.0.0-test";
+var VERSION = true ? "2.0.26" : "0.0.0-test";
 
 // src/togetherai-provider.ts
 function createTogetherAI(options = {}) {

package/docs/24-togetherai.mdx

@@ -112,20 +112,20 @@ const { text } = await generateText({
 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()`.
+The Together.ai provider also supports [completion models](https://docs.together.ai/docs/serverless-models#language-models) via (following the above example code) `togetherai.completionModel()` and [embedding models](https://docs.together.ai/docs/serverless-models#embedding-models) via `togetherai.embeddingModel()`.
 
 ## 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} /> |
+| Model                                         | Image Input         | Object Generation   | Tool Usage          | Tool Streaming      |
+| --------------------------------------------- | ------------------- | ------------------- | ------------------- | ------------------- |
+| `meta-llama/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
@@ -168,7 +168,25 @@ const { images } = await generateImage({
 });
 ```
 
-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).
+The following provider options are available:
+
+- **steps** _number_
+
+  Number of generation steps. Higher values can improve quality.
+
+- **guidance** _number_
+
+  Guidance scale for image generation.
+
+- **negative_prompt** _string_
+
+  Negative prompt to guide what to avoid.
+
+- **disable_safety_checker** _boolean_
+
+  Disable the safety checker for image generation.
+  When true, the API will not reject images flagged as potentially NSFW.
+  Not available for Flux Schnell Free and Flux Pro models.
 
 ### Image Editing
 
@@ -251,6 +269,9 @@ Together.ai image models support various image dimensions that vary by model. Co
 | `black-forest-labs/FLUX.1.1-pro`           |
 | `black-forest-labs/FLUX.1-pro`             |
 | `black-forest-labs/FLUX.1-schnell-Free`    |
+| `black-forest-labs/FLUX.1-kontext-pro`     |
+| `black-forest-labs/FLUX.1-kontext-max`     |
+| `black-forest-labs/FLUX.1-kontext-dev`     |
 
 <Note>
   Please see the [Together.ai models
@@ -260,7 +281,7 @@ Together.ai image models support various image dimensions that vary by model. Co
 
 ## Embedding Models
 
-You can create Together.ai embedding models using the `.embedding()` factory method.
+You can create Together.ai embedding models using the `.embeddingModel()` factory method.
 For more on embedding models with the AI SDK see [embed()](/docs/reference/ai-sdk-core/embed).
 
 ```ts
@@ -268,7 +289,7 @@ import { togetherai } from '@ai-sdk/togetherai';
 import { embed } from 'ai';
 
 const { embedding } = await embed({
-  model: togetherai.embedding('togethercomputer/m2-bert-80M-2k-retrieval'),
+  model: togetherai.embeddingModel('togethercomputer/m2-bert-80M-2k-retrieval'),
   value: 'sunny day at the beach',
 });
 ```

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@ai-sdk/togetherai",
-  "version": "2.0.24",
+  "version": "2.0.26",
   "license": "Apache-2.0",
   "sideEffects": false,
   "main": "./dist/index.js",
@@ -29,7 +29,7 @@
     }
   },
   "dependencies": {
-    "@ai-sdk/openai-compatible": "2.0.22",
+    "@ai-sdk/openai-compatible": "2.0.23",
     "@ai-sdk/provider": "3.0.5",
     "@ai-sdk/provider-utils": "4.0.10"
   },