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

# Qwen 3.8 27B

> Alibaba's open-weight (Apache-2.0) dense 27B vision-language model from the Qwen 3.8 line. 1M context, text, image and video input, reasoning, tool calling and structured outputs — the open checkpoint next to the closed Qwen 3.8 Max and Flash.

## Overview

`qwen3.8-27b` — Alibaba's open-weight (Apache-2.0) dense 27B vision-language model from the Qwen 3.8 line. 1M context, text, image and video input, reasoning, tool calling and structured outputs — the open checkpoint next to the closed Qwen 3.8 Max and Flash.

## Specs

| Field              | Value                                          |
| ------------------ | ---------------------------------------------- |
| Model ID           | `qwen3.8-27b`                                  |
| Best for           | Open-weight multimodal reasoning at 1M context |
| Context window     | 1M                                             |
| Max output tokens  | 131K                                           |
| Input modalities   | Text, Image, Video                             |
| Output modalities  | Text                                           |
| Tool calling       | Yes                                            |
| Structured outputs | Yes                                            |
| Prompt caching     | No                                             |
| Speed              | Medium                                         |
| Cost band          | Premium                                        |
| Release stage      | Stable                                         |

## Pricing

|        | Per 1M tokens |
| ------ | :-----------: |
| Input  |    \$0.567    |
| Output |     \$4.05    |

## Example

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

client = OpenAI(base_url="https://kymaapi.com/v1", api_key="kyma-...")

response = client.chat.completions.create(
    model="qwen3.8-27b",
    messages=[{"role": "user", "content": "..."}],
    tools=[...],  # function calling supported
)
```

## Agent query example

Ask the API which models fit, instead of hardcoding an id:

```bash theme={null}
curl "https://kymaapi.com/v1/models?recommended_for=chat&tools=true&quality_tier=strong"
```