Kimi 模型 | API 文件

# Kimi Model

Call Kimi K3 through the shared Chat Completions endpoint.

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

Kimi K3 is available through the Common Chat Completions endpoint, with both non-streaming and SSE streaming text responses.

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

## Available Model

| `model` value | Type | Non-streaming | SSE streaming |
| --- | --- | --- | --- |
| `kimi-k3` | Text chat | Yes | Yes |

## Authentication

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

## Non-streaming Request

```json
{
  "model": "kimi-k3",
  "messages": [
    {
      "role": "system",
      "content": "You are a product analysis assistant."
    },
    {
      "role": "user",
      "content": "Break this requirement into goals, constraints, and acceptance criteria."
    }
  ],
  "stream": false
}
```

## Streaming Request

```json
{
  "model": "kimi-k3",
  "messages": [
    {
      "role": "user",
      "content": "Create a pre-release checklist."
    }
  ],
  "stream": true
}
```

This endpoint returns one complete JSON response by default. Set `stream: true` explicitly when you need SSE streaming.

## Request Fields

### `model` (string, required)

Use `kimi-k3`.

### `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 output token allowance. Omit it to use the upstream default. Reasoning and the final answer share this allowance: a small value may end with `finish_reason: "length"` before any answer text is produced. A larger allowance may increase output usage and cost.

### `max_completion_tokens` (integer)

Compatibility alternative to `max_tokens`. The selected model determines support.

### `n` (integer, Default: 1)

Only `n=1` is supported. Each request returns one response choice.

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`, and `stop`. `kimi-k3` accepts these standard fields, but not every parameter necessarily produces a measurable semantic change.

## Success Response

```json
{
  "id": "chatcmpl_...",
  "object": "chat.completion",
  "created": 1787200000,
  "model": "kimi-k3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Goal: define the problem and expected outcome..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 86,
    "total_tokens": 110
  }
}
```

## Usage Notes

- The request body's `model` must be the public model ID listed in the Available Model table.
- Product names, display names, and other aliases are not accepted in place of the public model ID.
- This page applies only to Chat Completions requests sent to

`POST https://api.apihop.ai/v1/chat-completions`, not OpenAI Responses or Claude Messages.

- 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)

Kimi K3 可透過共用 Chat Completions 端點使用，支援非串流及 SSE 串流文字回應。

text

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

可用的模型

`model` 值	類型	非串流	SSE 串流
`kimi-k3`	文字對話	支援	支援

驗證

http

Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

非串流請求

json

{
  "model": "kimi-k3",
  "messages": [
    {
      "role": "system",
      "content": "You are a product analysis assistant."
    },
    {
      "role": "user",
      "content": "Break this requirement into goals, constraints, and acceptance criteria."
    }
  ],
  "stream": false
}

串流請求

json

{
  "model": "kimi-k3",
  "messages": [
    {
      "role": "user",
      "content": "Create a pre-release checklist."
    }
  ],
  "stream": true
}

此端點預設回傳一個完整 JSON 回應。需要 SSE 串流時，請明確設定 stream: true。

請求欄位

modelstring必填

使用 kimi-k3。

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 額度；省略時使用上游預設值。推理與最終回答共用此額度：過小可能在產生任何回答文字前以 finish_reason: "length" 結束。較大額度可能增加輸出用量與費用。

max_completion_tokensinteger

max_tokens 的相容替代欄位，支援情況依所選模型而定。

ninteger預設: 1

僅支援 n=1。每次請求回傳一個回答選項。

關於 temperature、top_p、frequency_penalty、presence_penalty 與 stop 等共用欄位，請參閱共用 Chat Completions。kimi-k3 接受這些標準欄位，但不是每個參數都一定產生可量測的語意變化。

成功回應

json

{
  "id": "chatcmpl_...",
  "object": "chat.completion",
  "created": 1787200000,
  "model": "kimi-k3",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Goal: define the problem and expected outcome..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 86,
    "total_tokens": 110
  }
}

使用注意事項

主體的 model 必須是可用模型表中的公開模型 ID。
不接受產品名稱、顯示名稱或其他別名取代公開模型 ID。
本頁僅適用於傳至 POST https://api.apihop.ai/v1/chat-completions 的 Chat Completions 請求，不適用 OpenAI Responses 或 Claude Messages。
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。