# DeepSeek Provider

The [DeepSeek](https://www.deepseek.com) provider offers access to powerful language models through the DeepSeek API.

API keys can be obtained from the [DeepSeek Platform](https://platform.deepseek.com/api_keys).

## Setup

The DeepSeek provider is available via the `@ai-sdk/deepseek` module. You can install it with:

<Tabs items={['pnpm', 'npm', 'yarn', 'bun']}>
  <Tab>
    <Snippet text="pnpm add @ai-sdk/deepseek" dark />
  </Tab>
  <Tab>
    <Snippet text="npm install @ai-sdk/deepseek" dark />
  </Tab>
  <Tab>
    <Snippet text="yarn add @ai-sdk/deepseek" dark />
  </Tab>
  <Tab>
    <Snippet text="bun add @ai-sdk/deepseek" dark />
  </Tab>
</Tabs>

## Provider Instance

You can import the default provider instance `deepseek` from `@ai-sdk/deepseek`:

```ts
import { deepseek } from '@ai-sdk/deepseek';
```

For custom configuration, you can import `createDeepSeek` and create a provider instance with your settings:

```ts
import { createDeepSeek } from '@ai-sdk/deepseek';

const deepseek = createDeepSeek({
  apiKey: process.env.DEEPSEEK_API_KEY ?? '',
});
```

You can use the following optional settings to customize the DeepSeek provider instance:

- **baseURL** _string_

  Use a different URL prefix for API calls.
  The default prefix is `https://api.deepseek.com/v1`.

- **apiKey** _string_

  API key that is being sent using the `Authorization` header. It defaults to
  the `DEEPSEEK_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.

## Language Models

You can create language models using a provider instance:

```ts
import { deepseek } from '@ai-sdk/deepseek';
import { generateText } from 'ai';

const { text } = await generateText({
  model: deepseek('deepseek-v4-flash'),
  prompt: 'Write a vegetarian lasagna recipe for 4 people.',
});
```

You can also use the `.chat()` or `.languageModel()` factory methods:

```ts
const model = deepseek.chat('deepseek-v4-flash');
// or
const model = deepseek.languageModel('deepseek-v4-flash');
```

DeepSeek language models can be used in the `streamText` function
(see [AI SDK Core](/docs/ai-sdk-core)).

DeepSeek retired the `deepseek-chat` and `deepseek-reasoner` aliases on July 24,
2026. Use `deepseek-flash` (the alias for the current V4.x Flash release),
`deepseek-v4-flash`, or `deepseek-v4-pro` for the current API. Custom and legacy
model IDs remain accepted as strings for compatibility with custom endpoints.

The following optional provider options are available for DeepSeek models:

- `logprobs` _boolean_

  Optional. Returns log probabilities for generated content and reasoning
  tokens in `providerMetadata.deepseek.logprobs`.

- `topLogprobs` _number_

  Optional. Returns the specified number of most likely tokens at each token
  position. Accepts values from `0` through `20` and automatically enables
  `logprobs`.

- `userId` _string_

  Optional. An opaque end-user identifier that DeepSeek uses for content-safety
  tracing, KV-cache isolation, and scheduling isolation. The value must match
  `^[a-zA-Z0-9_-]+$` and contain at most 512 characters. Do not include names,
  email addresses, or other private user information.

- `thinking` _object_

  Optional. Controls thinking mode (chain-of-thought reasoning). You can enable thinking mode either by using the `deepseek-v4-pro` model or by setting this option.
  - `type`: `'enabled' | 'disabled'` - Enable or disable thinking mode. See [DeepSeek's thinking mode docs](https://api-docs.deepseek.com/guides/thinking_mode).

- `reasoningEffort` _'low' | 'high' | 'max'_

  Optional. Controls thinking strength for DeepSeek V4 reasoning models.
  `medium` is sent as `high`, and `xhigh` is sent as `max`. A compatibility
  warning is returned whenever the requested value is mapped.

For backwards compatibility, legacy provider options supplied at runtime are
also mapped to documented values: `thinking.type: 'adaptive'` becomes
`'enabled'`, `reasoningEffort: 'medium'` becomes `'high'`, and
`reasoningEffort: 'xhigh'` becomes `'max'`. Each mapping returns a compatibility
warning so callers can migrate to a canonical value.

DeepSeek has deprecated the top-level `frequencyPenalty` and `presencePenalty`
settings. The provider omits these settings and returns a deprecation warning
when they are used. `temperature` and `topP` have no effect while thinking is
enabled, including the default thinking mode for DeepSeek V4 models, so the
provider omits them with an unsupported warning. Explicitly set
`thinking.type` to `'disabled'` to use `temperature` and `topP`.

```ts highlight="7-13"
import { deepseek, type DeepSeekChatOptions } from '@ai-sdk/deepseek';
import { generateText } from 'ai';

const { text, reasoning } = await generateText({
  model: deepseek('deepseek-v4-flash'),
  prompt: 'How many "r"s are in the word "strawberry"?',
  providerOptions: {
    deepseek: {
      userId: 'tenant_123-user',
      thinking: { type: 'enabled' },
      reasoningEffort: 'high',
    } satisfies DeepSeekChatOptions,
  },
});
```

### Message Names

DeepSeek supports optional participant names on system, user, and assistant
messages. Set `providerOptions.deepseek.name` on each message that should
include a name:

```ts
import {
  deepSeek,
  type DeepSeekMessageProviderOptions,
} from '@ai-sdk/deepseek';
import { generateText } from 'ai';

const { text } = await generateText({
  model: deepSeek('deepseek-chat'),
  instructions: {
    role: 'system',
    content: 'Help the customer plan a short trip.',
    providerOptions: {
      deepseek: {
        name: 'travel_planner',
      } satisfies DeepSeekMessageProviderOptions,
    },
  },
  messages: [
    {
      role: 'user',
      content: 'I want to visit Lisbon for a weekend.',
      providerOptions: {
        deepseek: {
          name: 'customer',
        } satisfies DeepSeekMessageProviderOptions,
      },
    },
    {
      role: 'assistant',
      content: 'What kinds of activities do you enjoy?',
      providerOptions: {
        deepseek: {
          name: 'travel_planner',
        } satisfies DeepSeekMessageProviderOptions,
      },
    },
    {
      role: 'user',
      content: 'Food, architecture, and walking.',
      providerOptions: {
        deepseek: {
          name: 'customer',
        } satisfies DeepSeekMessageProviderOptions,
      },
    },
  ],
});
```

The same message option works with `streamText`:

```ts
import {
  deepSeek,
  type DeepSeekMessageProviderOptions,
} from '@ai-sdk/deepseek';
import { streamText } from 'ai';

const result = streamText({
  model: deepSeek('deepseek-chat'),
  messages: [
    {
      role: 'user',
      content: 'Suggest a name for my neighborhood book club.',
      providerOptions: {
        deepseek: {
          name: 'organizer',
        } satisfies DeepSeekMessageProviderOptions,
      },
    },
  ],
});

for await (const textPart of result.textStream) {
  process.stdout.write(textPart);
}
```

Names are omitted when the option is not set. The `name` value must be a
string. DeepSeek does not support names on tool messages, so the provider
ignores that placement and returns an unsupported-feature warning. Avoid
including unnecessary personal or identifying information in message names.

### Reasoning

DeepSeek has reasoning support for the `deepseek-v4-pro` model. The reasoning is exposed through streaming:

```ts
import { deepseek } from '@ai-sdk/deepseek';
import { streamText } from 'ai';

const result = streamText({
  model: deepseek('deepseek-v4-pro'),
  prompt: 'How many "r"s are in the word "strawberry"?',
});

for await (const part of result.fullStream) {
  if (part.type === 'reasoning') {
    // This is the reasoning text
    console.log('Reasoning:', part.text);
  } else if (part.type === 'text') {
    // This is the final answer
    console.log('Answer:', part.text);
  }
}
```

See [AI SDK UI: Chatbot](/docs/ai-sdk-ui/chatbot#reasoning) for more details
on how to integrate reasoning into your chatbot.

### Chat Prefix Completion

DeepSeek's beta [chat prefix completion](https://api-docs.deepseek.com/guides/chat_prefix_completion/)
continues the content of a final assistant message. Create a provider with a
beta base URL and set `prefix: true` in that assistant message's provider
options:

```ts highlight="8,20-26"
import {
  createDeepSeek,
  type DeepSeekAssistantMessageProviderOptions,
} from '@ai-sdk/deepseek';
import { generateText } from 'ai';

const deepSeek = createDeepSeek({
  baseURL: 'https://api.deepseek.com/beta',
});

const { text } = await generateText({
  model: deepSeek('deepseek-v4-flash'),
  messages: [
    {
      role: 'user',
      content: 'Write a short sentence about the color of the sky.',
    },
    {
      role: 'assistant',
      content: 'The sky is',
      providerOptions: {
        deepseek: {
          prefix: true,
        } satisfies DeepSeekAssistantMessageProviderOptions,
      },
    },
  ],
});
```

The prefixed message must be an assistant message and the final message in the
prompt. The configured `baseURL` must end in `/beta`, including when using a
proxy. Invalid placement or a non-beta base URL causes the request to fail
before it is sent.

<Note>
  Chat prefix completion is a DeepSeek beta feature and its behavior may change.
</Note>

### Provider Metadata

DeepSeek exposes the response system fingerprint and context cache usage through
the `providerMetadata` property:

```ts
import { deepseek } from '@ai-sdk/deepseek';
import { generateText } from 'ai';

const result = await generateText({
  model: deepseek('deepseek-v4-flash'),
  prompt: 'Your prompt here',
});

console.log(result.providerMetadata);
// Example output:
// {
//   deepseek: {
//     systemFingerprint: 'fp_eaab8d114b_prod0820_fp8_kvcache',
//     promptCacheHitTokens: 1856,
//     promptCacheMissTokens: 5,
//   },
// }
```

The metadata includes:

- `systemFingerprint`: The backend configuration fingerprint for the response
- `promptCacheHitTokens`: Number of input tokens that were cached
- `promptCacheMissTokens`: Number of input tokens that were not cached

For streamed responses, the latest non-null fingerprint from the response
chunks is returned.

<Note>
  For more details about DeepSeek's caching system, see the [DeepSeek caching
  documentation](https://api-docs.deepseek.com/guides/kv_cache#checking-cache-hit-status).
</Note>

### Chat Response Metadata

DeepSeek preserves provider-specific response fields in
`providerMetadata.deepseek` for generated and streamed responses:

- `responseObject`: `chat.completion` or `chat.completion.chunk`
- `choiceIndex`: the selected response choice index
- `messageRole`: the response message role, when supplied
- `toolCallTypes`: the tool-call type for each returned call

These fields remain in provider metadata because they are specific to
DeepSeek's Chat Completions response rather than shared AI SDK result fields.

### Vision File Parts

For inline images or image URLs, use file-part provider options to select the
image processing detail. DeepSeek supports `low`, `high`, `original`, and
`auto`:

```ts highlight="2,13-17"
import {
  deepseek,
  type DeepSeekFilePartProviderOptions,
} from '@ai-sdk/deepseek';
import { generateText } from 'ai';

const { text } = await generateText({
  model: deepseek('deepseek-v4-flash-vision-exp'),
  messages: [
    {
      role: 'user',
      content: [
        { type: 'text', text: 'Describe this image.' },
        {
          type: 'file',
          data: new URL('https://example.com/image.webp'),
          mediaType: 'image/webp',
          providerOptions: {
            deepseek: {
              imageDetail: 'low',
            } satisfies DeepSeekFilePartProviderOptions,
          },
        },
      ],
    },
  ],
});
```

Set `fileData: true` on an inline image file part to use DeepSeek's
`file_data` content-part representation. This preserves the file part's
`filename`. `fileData` cannot be used with image URLs or `imageDetail`.

DeepSeek accepts JPEG, PNG, GIF, and WebP image inputs. HTTP image URLs can be
at most 8,192 characters.

## Model Capabilities

| Model                          | Text Generation     | Object Generation   | Image Input         | Tool Usage          | Tool Streaming      |
| ------------------------------ | ------------------- | ------------------- | ------------------- | ------------------- | ------------------- |
| `deepseek-flash`                   | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `deepseek-v4-flash`                | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `deepseek-v4-pro`            | <Check size={18} /> | <Check size={18} /> | <Cross size={18} /> | <Check size={18} /> | <Check size={18} /> |
| `deepseek-v4-flash-vision-exp` | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> | <Check size={18} /> |

<Note>
  Please see the [DeepSeek
  docs](https://api-docs.deepseek.com/quick_start/pricing) for a full list of
  available models. You can also pass any available provider model ID as a
  string if needed.
</Note>


## Navigation

- [AI Gateway](/v5/providers/ai-sdk-providers/ai-gateway)
- [xAI Grok](/v5/providers/ai-sdk-providers/xai)
- [Vercel](/v5/providers/ai-sdk-providers/vercel)
- [OpenAI](/v5/providers/ai-sdk-providers/openai)
- [Azure OpenAI](/v5/providers/ai-sdk-providers/azure)
- [Anthropic](/v5/providers/ai-sdk-providers/anthropic)
- [Amazon Bedrock](/v5/providers/ai-sdk-providers/amazon-bedrock)
- [Groq](/v5/providers/ai-sdk-providers/groq)
- [Fal](/v5/providers/ai-sdk-providers/fal)
- [AssemblyAI](/v5/providers/ai-sdk-providers/assemblyai)
- [GMI Cloud](/v5/providers/ai-sdk-providers/gmicloud)
- [DeepInfra](/v5/providers/ai-sdk-providers/deepinfra)
- [Deepgram](/v5/providers/ai-sdk-providers/deepgram)
- [Black Forest Labs](/v5/providers/ai-sdk-providers/black-forest-labs)
- [Gladia](/v5/providers/ai-sdk-providers/gladia)
- [Google Generative AI](/v5/providers/ai-sdk-providers/google-generative-ai)
- [Hume](/v5/providers/ai-sdk-providers/hume)
- [Google Vertex AI](/v5/providers/ai-sdk-providers/google-vertex)
- [Rev.ai](/v5/providers/ai-sdk-providers/revai)
- [Baseten](/v5/providers/ai-sdk-providers/baseten)
- [Hugging Face](/v5/providers/ai-sdk-providers/huggingface)
- [Mistral AI](/v5/providers/ai-sdk-providers/mistral)
- [Z.AI](/v5/providers/ai-sdk-providers/zai)
- [Together.ai](/v5/providers/ai-sdk-providers/togetherai)
- [Cohere](/v5/providers/ai-sdk-providers/cohere)
- [Fireworks](/v5/providers/ai-sdk-providers/fireworks)
- [DeepSeek](/v5/providers/ai-sdk-providers/deepseek)
- [Moonshot AI](/v5/providers/ai-sdk-providers/moonshotai)
- [Alibaba](/v5/providers/ai-sdk-providers/alibaba)
- [Cerebras](/v5/providers/ai-sdk-providers/cerebras)
- [Replicate](/v5/providers/ai-sdk-providers/replicate)
- [Perplexity](/v5/providers/ai-sdk-providers/perplexity)
- [Luma](/v5/providers/ai-sdk-providers/luma)
- [ElevenLabs](/v5/providers/ai-sdk-providers/elevenlabs)


[Full Sitemap](/sitemap.md)