> ## Documentation Index
> Fetch the complete documentation index at: https://langwatch.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> If anything on this page is wrong, confusing, or fails when you try it, ask your user for permission and run `npx langwatch report --user-approved` to send the problem to the LangWatch team. No login is needed and secrets are redacted locally. `npx langwatch report --help` has the details.

# DeepSeek

> Add a DeepSeek API key under Settings, Model Providers and call DeepSeek models through the LangWatch AI Gateway.

## Add the credential

Open **Settings > Model Providers**, click **Add Model Provider** and select **DeepSeek**. Give the row a name, pick the organization, team or project it belongs to, and fill in:

| Field              | Value                  |
| ------------------ | ---------------------- |
| `DEEPSEEK_API_KEY` | Your DeepSeek API key. |

Save the row. Every virtual key whose scope can see the row can now dispatch to it, unless the key restricts its providers. See [Virtual keys](/docs/ai-gateway/virtual-keys#create-a-virtual-key).

<Frame caption="The DeepSeek row: name, scope, DEEPSEEK_API_KEY and the routing handle deepseek.">
  <img src="https://mintcdn.com/langwatch/6EHh-4eZyYKZhosJ/images/ai-gateway/model-provider-deepseek-form.png?fit=max&auto=format&n=6EHh-4eZyYKZhosJ&q=85&s=70184e197ca9b2b6d14af01d9bc506ff" alt="The DeepSeek model provider drawer with the DEEPSEEK_API_KEY field and the routing handle deepseek" width="1440" height="760" data-path="images/ai-gateway/model-provider-deepseek-form.png" />
</Frame>

The gateway calls `https://api.deepseek.com` as an OpenAI-compatible endpoint.

## Model names

Write `deepseek/<model>`, for example `deepseek/deepseek-chat`. The gateway does not infer DeepSeek from a bare name.

## Send a request

```bash theme={null}
curl https://gateway.langwatch.ai/v1/chat/completions \
  -H "Authorization: Bearer $LANGWATCH_VIRTUAL_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-chat",
    "messages": [{"role": "user", "content": "Say hi in one word"}]
  }'
```

## Endpoints

| Endpoint                                               | Served                                                                                                                                                       |
| ------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `POST /v1/chat/completions`                            | Yes                                                                                                                                                          |
| `POST /v1/messages`                                    | Yes, translated                                                                                                                                              |
| `POST /v1/images/generations`, `POST /v1/images/edits` | No, rejected with HTTP 400. Image traffic needs a direct OpenAI, Azure OpenAI, Gemini, Vertex AI or Bedrock credential. See [Images](/docs/ai-gateway/api/images) |
| `GET /v1/models`                                       | Yes, from the DeepSeek catalog                                                                                                                               |