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

# Kimi K2.5

> Moonshot's K2.5 — long-context Chinese-language flagship, strong on extraction and document QA.

**Vendor:** Moonshot
**Model ID:** `kimi-k2-5`
**Capability:** 256K context · tool use · streaming · structured output · CJK-native
**Pricing:** per-token, mid tier ([live rate](https://bytespike.ai/pricing#text))

Kimi K2.5 is Moonshot's prior flagship. Native Chinese / Japanese /
Korean prompt understanding, and the 256K context window made it the
default for long-document extraction in the Chinese market. Still
production-capable; for new work, [Kimi K2.6](/api-reference/text/kimi-k2-6)
is the recommended starting point.

## Request

```bash theme={null}
curl https://llm.bytespike.ai/v1/chat/completions \
  -H "Authorization: Bearer $BYTESPIKE_API_KEY" \
  -H "content-type: application/json" \
  -d '{
    "model": "kimi-k2-5",
    "messages": [{"role": "user", "content": "提取这篇合同里的关键条款。"}]
  }'
```

### Body parameters

| Field             | Type    | Required | Default   | Notes                       |
| ----------------- | ------- | -------- | --------- | --------------------------- |
| `model`           | string  | yes      | —         | `kimi-k2-5`                 |
| `messages`        | array   | yes      | —         | CJK accepted natively.      |
| `max_tokens`      | integer | no       | model max | Max: 8192.                  |
| `tools`           | array   | no       | —         | Function calling supported. |
| `response_format` | object  | no       | —         | JSON mode.                  |
| `stream`          | boolean | no       | false     | SSE streaming.              |

## Response

```json theme={null}
{
  "id": "chatcmpl-…",
  "object": "chat.completion",
  "model": "kimi-k2-5",
  "choices": [{"index": 0, "message": {"role": "assistant", "content": "..."}, "finish_reason": "stop"}],
  "usage": {"prompt_tokens": 84210, "completion_tokens": 312, "total_tokens": 84522}
}
```

## Code examples

<CodeGroup>
  ```bash cURL theme={null}
  curl https://llm.bytespike.ai/v1/chat/completions \
    -H "Authorization: Bearer $BYTESPIKE_API_KEY" \
    -H "content-type: application/json" \
    -d '{"model": "kimi-k2-5", "messages": [{"role": "user", "content": "提取关键条款"}]}'
  ```

  ```python Python theme={null}
  from openai import OpenAI

  client = OpenAI(base_url="https://llm.bytespike.ai/v1", api_key="$BYTESPIKE_API_KEY")
  resp = client.chat.completions.create(
      model="kimi-k2-5",
      messages=[{"role": "user", "content": "提取这篇合同里的关键条款。"}],
  )
  print(resp.choices[0].message.content)
  ```

  ```javascript Node theme={null}
  import OpenAI from "openai"

  const client = new OpenAI({
    baseURL: "https://llm.bytespike.ai/v1",
    apiKey: process.env.BYTESPIKE_API_KEY,
  })
  const resp = await client.chat.completions.create({
    model: "kimi-k2-5",
    messages: [{ role: "user", content: "提取这篇合同里的关键条款。" }],
  })
  console.log(resp.choices[0].message.content)
  ```
</CodeGroup>

## Streaming + caching

`"stream": true` for SSE. Automatic prompt caching.

## Errors

| Code                        | Trigger  | Billed?         |
| --------------------------- | -------- | --------------- |
| 400 / 401 / 402 / 422 / 429 | Standard | No              |
| 5xx                         | Upstream | No (auto-retry) |

## When to use

* Long-document extraction in Chinese / Japanese / Korean.
* Existing code validated against this exact version.
* For new work, prefer [Kimi K2.6](/api-reference/text/kimi-k2-6).

## Limits

| Limit                   | Value       |
| ----------------------- | ----------- |
| Context window          | 256K tokens |
| Max output              | 8192 tokens |
| Supports tool use       | Yes         |
| Supports vision         | No          |
| Supports streaming      | Yes         |
| Supports prompt caching | Automatic   |