feat (provider/deepinfra): Add DeepInfra provider. (#4158)

.changeset/rotten-tomatoes-scream.md

@@ -0,0 +1,6 @@
+---
+'@ai-sdk/openai-compatible': patch
+'@ai-sdk/deepinfra': patch
+---
+
+feat (provider/deepinfra): Add DeepInfra provider.

content/docs/02-foundations/02-providers-and-models.mdx

@@ -34,8 +34,9 @@ The AI SDK comes with several providers that you can use to interact with differ
 - [xAI Grok Provider](/providers/ai-sdk-providers/xai) (`@ai-sdk/xai`)
 - [Together.ai Provider](/providers/ai-sdk-providers/togetherai) (`@ai-sdk/togetherai`)
 - [Cohere Provider](/providers/ai-sdk-providers/cohere) (`@ai-sdk/cohere`)
-- [Fireworks](/providers/ai-sdk-providers/fireworks)
-- [Groq](/providers/ai-sdk-providers/groq) (`@ai-sdk/groq`)
+- [Fireworks Provider](/providers/ai-sdk-providers/fireworks) (`@ai-sdk/fireworks`)
+- [DeepInfra Provider](/providers/ai-sdk-providers/deepinfra) (`@ai-sdk/deepinfra`)
+- [Groq Provider](/providers/ai-sdk-providers/groq) (`@ai-sdk/groq`)
 
 You can also use the OpenAI provider with OpenAI-compatible APIs:
 

content/providers/01-ai-sdk-providers/27-deepinfra.mdx

@@ -0,0 +1,111 @@
+---
+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']}>
+  <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>
+</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/openai`.
+
+- **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` and `streamUI` functions (see [AI SDK Core](/docs/ai-sdk-core) and [AI SDK RSC](/docs/ai-sdk-rsc)).
+
+## Model Capabilities
+
+| Model                                          | Image Input         | Object Generation   | Tool Usage          | Tool Streaming      |
+| ---------------------------------------------- | ------------------- | ------------------- | ------------------- | ------------------- |
+| `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} /> |
+| `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. The table
+  above lists popular models. You can also pass any available provider model ID
+  as a string if needed.
+</Note>

examples/ai-core/.env.example

@@ -5,6 +5,7 @@ AWS_REGION=""
 AZURE_API_KEY=""
 AZURE_RESOURCE_NAME=""
 COHERE_API_KEY=""
+DEEPINFRA_API_KEY=""
 FIREWORKS_API_KEY=""
 GOOGLE_APPLICATION_CREDENTIALS=""
 GOOGLE_CLIENT_EMAIL=""

examples/ai-core/package.json

@@ -7,6 +7,7 @@
     "@ai-sdk/anthropic": "1.0.5",
     "@ai-sdk/azure": "1.0.12",
     "@ai-sdk/cohere": "1.0.5",
+    "@ai-sdk/deepinfra": "0.0.0",
     "@ai-sdk/fireworks": "0.0.3",
     "@ai-sdk/google": "1.0.11",
     "@ai-sdk/google-vertex": "2.0.11",