LiveKit docs › Models › LLM › DeepSeek

---

# DeepSeek LLM

> How to use DeepSeek models with LiveKit Agents.

- **[Use in Agent Builder](https://cloud.livekit.io/projects/p_/agents/builder/new?llm=deepseek-ai%2Fdeepseek-v3.1)**: Create a new agent in your browser using deepseek-ai/deepseek-v3.1

## Overview

DeepSeek models are available in LiveKit Agents through [LiveKit Inference](https://docs.livekit.io/agents/models/inference.md) and the [DeepSeek plugin](#plugin). With LiveKit Inference, your agent runs on LiveKit's infrastructure to minimize latency. No separate provider API key is required, and usage and rate limits are managed through LiveKit Cloud. Use the plugin instead if you want to manage your own billing and rate limits. Pricing for LiveKit Inference is available on the [pricing page](https://livekit.com/pricing/inference#llm).

## LiveKit Inference

Use [LiveKit Inference](https://docs.livekit.io/agents/models/inference.md) to access DeepSeek models without a separate DeepSeek API key.

| Model name | Model ID | Providers |
| ---------- | -------- | -------- |
| DeepSeek-V3 | `deepseek-ai/deepseek-v3` | `baseten` |
| DeepSeek-V3.1 | `deepseek-ai/deepseek-v3.1` | `baseten` |
| DeepSeek-V3.2 | `deepseek-ai/deepseek-v3.2` | `deepseek` |

### Usage

To use DeepSeek, use the `LLM` class from the `inference` module. You can use this LLM in the [Voice AI quickstart](https://docs.livekit.io/agents/start/voice-ai.md):

**Python**:

```python
from livekit.agents import AgentSession, inference

session = AgentSession(
    llm=inference.LLM(
        model="deepseek-ai/deepseek-v3.1",
        provider="baseten",
        extra_kwargs={
            "max_tokens": 1000
        }
    ),
    # ... tts, stt, vad, turn_handling, etc.
)

```

---

**Node.js**:

```typescript
import { AgentSession, inference } from '@livekit/agents';

const session = new AgentSession({
    llm: new inference.LLM({
        model: "deepseek-ai/deepseek-v3.1",
        provider: "baseten",
        modelOptions: {
            max_tokens: 1000
        }
    }),
    // ... tts, stt, vad, turnHandling, etc.
});

```

### Parameters

The following are parameters for configuring DeepSeek models with LiveKit Inference. For model behavior parameters like `temperature` and `max_tokens`, see [model parameters](#model-parameters).

- **`model`** _(string)_: The model ID from the [models list](#inference).

- **`provider`** _(string)_ (optional): Set a specific provider to use for the LLM. Refer to the [models list](#inference) for available providers. If not set, LiveKit Inference uses the best available provider, and bills accordingly.

- **`extra_kwargs`** _(dict)_ (optional): Additional parameters to pass to the provider's Chat Completions API, such as `max_tokens` or `temperature`. See [model parameters](#model-parameters) for supported fields.

In Node.js this parameter is called `modelOptions`.

#### Model parameters

Pass the following parameters inside `extra_kwargs` (Python) or `modelOptions` (Node.js). For more details about each parameter in the list, see [Inference parameters](https://docs.livekit.io/reference/agents/inference-llm-parameters.md).

| Parameter | Type | Default | Notes |
| temperature | `float` | `1` | Controls the randomness of the model's output. Valid range: `0`-`2`. |
| top_p | `float` | `1` | Alternative to `temperature`. Model considers the results of the tokens with `top_p` probability mass. Valid range: `0`-`1`. |
| max_tokens | `int` |  | The maximum number of tokens that can be generated in the chat completion. |
| frequency_penalty | `float` | `0` | Positive values decrease the model's likelihood to repeat the same line verbatim. Valid range: `-2.0`-`2.0`. |
| presence_penalty | `float` | `0` | Positive values increase the model's likelihood to talk about new topics. Valid range: `-2.0`-`2.0`. |
| stop | `str | list[str]` |  | List of up to 16 string sequences (for example, `["\n"]`) that cause the API to stop generating further tokens. |
| logprobs | `bool` |  | If true, returns the log probabilities of each output token. |
| top_logprobs | `int` |  | Number of most likely tokens to return at each token position with associated log probability.

Requires `logprobs: true`. Valid range: `0`-`20`. |
| tool_choice | `ToolChoice | Literal['auto', 'required', 'none']` | `"auto"` | Controls how the model uses tools. |

### String descriptors

As a shortcut, you can also pass a [model ID](#inference) string directly to the `llm` argument in your `AgentSession`:

**Python**:

```python
from livekit.agents import AgentSession

session = AgentSession(
    llm="deepseek-ai/deepseek-v3.1",
    # ... tts, stt, vad, turn_handling, etc.
)

```

---

**Node.js**:

```typescript
import { AgentSession } from '@livekit/agents';

const session = new AgentSession({
    llm: "deepseek-ai/deepseek-v3.1",
    // ... tts, stt, vad, turnHandling, etc.
});

```

## Plugin

LiveKit's plugin support for DeepSeek lets you connect directly to DeepSeek's API with your own API key.

Available in:
- [x] Node.js
- [x] Python

### Usage

Use the OpenAI plugin's `with_deepseek` method to set the default agent session LLM to DeepSeek:

**Python**:

```shell
uv add "livekit-agents[openai]~=1.5"

```

---

**Node.js**:

```shell
pnpm add @livekit/agents-plugin-openai@1.x

```

Set the following environment variable in your `.env` file:

```shell
DEEPSEEK_API_KEY=<your-deepseek-api-key>

```

You can use this LLM in the [Voice AI quickstart](https://docs.livekit.io/agents/start/voice-ai.md):

**Python**:

```python
from livekit.plugins import openai

session = AgentSession(
    llm=openai.LLM.with_deepseek(
        model="deepseek-chat", # this is DeepSeek-V3
    ),
)

```

---

**Node.js**:

```typescript
import * as openai from '@livekit/agents-plugin-openai';

const session = new voice.AgentSession({
   llm: openai.LLM.withDeepSeek({
    model: "deepseek-chat",  // this is DeepSeek-V3
   })
});

```

### Parameters

This section describes some of the available parameters. For a complete reference of all available parameters, see the plugin reference links in the [Additional resources](#additional-resources) section.

- **`model`** _(str | DeepSeekChatModels)_ (optional) - Default: `deepseek-chat`: DeepSeek model to use. See [models and pricing](https://api-docs.deepseek.com/quick_start/pricing) for a complete list.

- **`temperature`** _(float)_ (optional) - Default: `1.0`: Sampling temperature that controls the randomness of the model's output. Higher values make the output more random, while lower values make it more focused and deterministic. Range of valid values can vary by model.

Valid values are between `0` and `2`.

- **`parallel_tool_calls`** _(bool)_ (optional): Controls whether the model can make multiple tool calls in parallel. When enabled, the model can make multiple tool calls simultaneously, which can improve performance for complex tasks.

- **`tool_choice`** _(ToolChoice | Literal['auto', 'required', 'none'])_ (optional) - Default: `auto`: Controls how the model uses tools. String options are as follows:

- `'auto'`: Let the model decide.
- `'required'`: Force tool usage.
- `'none'`: Disable tool usage.

## Additional resources

The following links provide more information about the DeepSeek LLM integration.

- **[DeepSeek docs](https://platform.deepseek.com/docs)**: DeepSeek API documentation.

- **[Voice AI quickstart](https://docs.livekit.io/agents/start/voice-ai.md)**: Get started with LiveKit Agents and DeepSeek.

---

This document was rendered at 2026-06-07T11:35:11.130Z.
For the latest version of this document, see [https://docs.livekit.io/agents/models/llm/deepseek.md](https://docs.livekit.io/agents/models/llm/deepseek.md).

To explore all LiveKit documentation, see [llms.txt](https://docs.livekit.io/llms.txt).