DeepSeek 模型 | API 文件

# DeepSeek Models

DeepSeek V4 Flash, V4 Pro, and V4.1 Flash model IDs and Chat Completions availability.

POST https://api.apihop.ai/v1/chat-completions

DeepSeek models use the Common Chat Completions endpoint. To switch models, change only the `model` value; the endpoint and authentication stay the same.

```text
POST https://api.apihop.ai/v1/chat-completions
```

## Available Models

| `model` value | Positioning | Non-streaming | SSE streaming |
| --- | --- | --- | --- |
| `deepseek-v4-flash` | Flash tier and a practical starting point for routine chat or batch evaluations | Yes | Yes |
| `deepseek-v4-pro` | Pro tier for evaluations that prioritize complex reasoning and output quality | Yes | Yes |
| `deepseek-v4.1-flash` | DeepSeek V4.1 Flash; a distinct model ID, not a V4 Flash alias | After deployment and enablement | After deployment and enablement |

V4.1 Flash becomes available only after its routing configuration is deployed and enabled. Use it only when `GET https://api.apihop.ai/v1/models` returns `deepseek-v4.1-flash` for your API Key. This reference entry does not confirm a production rollout or a successful inference test. Existing V4 Flash and V4 Pro IDs remain unchanged.

This positioning helps you choose an initial model to test; it is not a latency, throughput, or quality SLA. Compare available models with your own prompts, output lengths, and concurrency before production use.

## Authentication

```http
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
```

## Non-streaming Request

The endpoint returns one complete Chat Completions response by default. The example includes `stream: false` explicitly so its behavior remains obvious when copied.

```json
{
  "model": "deepseek-v4-flash",
  "messages": [
    {
      "role": "system",
      "content": "You are a precise technical assistant."
    },
    {
      "role": "user",
      "content": "Explain three benefits of event-driven architecture."
    }
  ],
  "stream": false
}
```

To use the Pro model, change only the model field:

```json
{
  "model": "deepseek-v4-pro"
}
```

## Streaming Request

Set `stream: true` explicitly for streaming and process the response as SSE events until `[DONE]`.

```json
{
  "model": "deepseek-v4-pro",
  "messages": [
    {
      "role": "user",
      "content": "Create a checklist for a reversible database migration."
    }
  ],
  "stream": true
}
```

## Request Fields

### `model` (string, required)

Use `deepseek-v4-flash`, `deepseek-v4-pro`, or `deepseek-v4.1-flash`, as returned by `GET https://api.apihop.ai/v1/models`.

### `messages` (object[], required)

OpenAI Chat Completions style messages. Each message contains `role` and `content`.

### `stream` (boolean, Default: false)

`true` returns SSE; `false` returns one complete JSON response.

### `max_tokens` (integer)

Optional maximum output tokens, as a positive integer. Omit this field to use the upstream default for the selected model. Depending on the model, the budget may include reasoning tokens as well as final text. A small budget can truncate the answer or be exhausted before final text; increasing it may increase cost.

### `max_completion_tokens` (integer)

Optional compatibility alternative to `max_tokens`, with the same budget considerations. The selected model determines support; omit both fields to use the upstream default.

See [Common Chat Completions](https://apihop.ai/en/docs/api-reference/common-chat-completions) for shared fields such as `temperature`, `top_p`, `frequency_penalty`, `presence_penalty`, `stop`, and `n`. Support and semantic effects may vary by model; this guide does not establish V4.1 Flash support for every optional field.

## Success Response

```json
{
  "id": "chatcmpl_...",
  "object": "chat.completion",
  "created": 1787200000,
  "model": "deepseek-v4-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "1. Services can remain loosely coupled..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 31,
    "completion_tokens": 96,
    "total_tokens": 127
  }
}
```

Responses may contain additional usage details; treat them as optional.

## Usage Notes

- The current public contract is Chat Completions, including non-streaming and SSE streaming.
- These models are not currently available through OpenAI Responses or Claude Messages.
- Set the request body's `model` field to the exact ID: `deepseek-v4-flash`, `deepseek-v4-pro`, or `deepseek-v4.1-flash`.
- Use only model IDs returned by `GET https://api.apihop.ai/v1/models`.
- Use `GET https://api.apihop.ai/v1/models` for the models visible to the current API Key, and use the console for current pricing.

## Related Docs

- [Common Chat Completions](https://apihop.ai/en/docs/api-reference/common-chat-completions)
- [Model Catalog](https://apihop.ai/en/docs/api-reference/models)

DeepSeek 模型使用共用 Chat Completions 端點。切換模型時只需更改 model 值；端點與驗證方式不變。

text

POST https://api.apihop.ai/v1/chat-completions

可用模型

`model` 值	定位	非串流	SSE 串流
`deepseek-v4-flash`	Flash 層級，適合作為日常對話或批次評估的實用起點	支援	支援
`deepseek-v4-pro`	Pro 層級，用於重視複雜推理與輸出品質的評估	支援	支援
`deepseek-v4.1-flash`	DeepSeek V4.1 Flash；獨立模型 ID，不是 V4 Flash 別名	部署並啟用後	部署並啟用後

V4.1 Flash 僅在路由設定部署並啟用後可用。只有當你的 API 金鑰透過 GET https://api.apihop.ai/v1/models 取得 deepseek-v4.1-flash 時才使用。本參考條目不代表已部署至正式環境或已成功通過推論測試。既有 V4 Flash 與 V4 Pro ID 不變。

此定位協助選擇最初測試的模型，不是延遲、吞吐量或品質 SLA。投入正式環境前，請用自己的提示詞、輸出長度及並行數比較可用模型。

驗證

http

Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

非串流請求

此端點預設回傳一個完整 Chat Completions 回應。範例明確加入 stream: false，讓複製後的行為仍然清楚。

json

{
  "model": "deepseek-v4-flash",
  "messages": [
    {
      "role": "system",
      "content": "You are a precise technical assistant."
    },
    {
      "role": "user",
      "content": "Explain three benefits of event-driven architecture."
    }
  ],
  "stream": false
}

使用 Pro 模型時，只更改模型欄位：

json

{
  "model": "deepseek-v4-pro"
}

串流請求

串流請明確設定 stream: true，並將回應作為 SSE 事件處理，直到 [DONE]。

json

{
  "model": "deepseek-v4-pro",
  "messages": [
    {
      "role": "user",
      "content": "Create a checklist for a reversible database migration."
    }
  ],
  "stream": true
}

請求欄位

modelstring必填

使用 deepseek-v4-flash 或 deepseek-v4-pro 或 deepseek-v4.1-flash，以 GET https://api.apihop.ai/v1/models 回傳為準。

messagesobject[]必填

OpenAI Chat Completions 風格的訊息，每則訊息包含 role 與 content。

streamboolean預設: false

true 回傳 SSE；false 回傳一個完整 JSON 回應。

max_tokensinteger

選填的輸出 Token 上限，須為正整數。省略時使用所選模型的上游預設值。依模型而定，此額度可能同時包含推理 Token 與最終文字。過小的額度可能截斷回答，或在產生最終文字前耗盡；提高額度可能增加費用。

max_completion_tokensinteger

max_tokens 的選填相容替代欄位，具有相同額度注意事項。支援情況由所選模型決定；省略兩個欄位可使用上游預設值。

關於 temperature、top_p、frequency_penalty、presence_penalty、stop 與 n 等共用欄位，請參閱共用 Chat Completions。支援與語意效果可能依模型而異；本指南不表示 V4.1 Flash 支援每個選填欄位。

成功回應

json

{
  "id": "chatcmpl_...",
  "object": "chat.completion",
  "created": 1787200000,
  "model": "deepseek-v4-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "1. Services can remain loosely coupled..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 31,
    "completion_tokens": 96,
    "total_tokens": 127
  }
}

回應可能含有額外用量明細，請將其視為選填。

使用注意事項

目前公開協定為 Chat Completions，包含非串流與 SSE 串流。
這些模型目前無法透過 OpenAI Responses 或 Claude Messages 使用。
請將主體的 model 設為精確 ID：deepseek-v4-flash、deepseek-v4-pro 或 deepseek-v4.1-flash。
只使用 GET https://api.apihop.ai/v1/models 回傳的模型 ID。
以 GET https://api.apihop.ai/v1/models 查看目前金鑰可見的模型，並在控制台查看現行價格。