> ## 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 3.7 Plus

> Alibaba's newest Plus flagship — 1M context, vision input, top agentic and reasoning quality.

## Overview

`qwen-3.7-plus` is Alibaba's newest Plus-tier flagship and the successor to `qwen-3.6-plus`. It is the first Plus model with vision input (text + image), runs a 1M context window, and ranks among the top agentic models. Reach for it when you want a frontier-quality general model that can also see images and handle very long inputs.

## Specs

| Field              | Value                                                         |
| ------------------ | ------------------------------------------------------------- |
| Model ID           | `qwen-3.7-plus`                                               |
| Best for           | General work, agentic coding, reasoning, vision, long context |
| Context window     | 1M                                                            |
| Max output tokens  | 32K                                                           |
| Input modalities   | Text, Image                                                   |
| Output modalities  | Text                                                          |
| Tool calling       | Yes                                                           |
| Structured outputs | Yes                                                           |
| Reasoning          | Yes                                                           |
| Prompt caching     | Yes                                                           |
| Speed              | Medium                                                        |
| Cost band          | Premium                                                       |
| Release stage      | Stable                                                        |

## Use this when

* You want the newest, highest-quality Qwen Plus model for general and agentic work.
* You need image input alongside text reasoning.
* You need a very large (1M) context window for long documents or codebases.
* You build agents that need reliable tool calling and JSON outputs.

## Pick something else when

* You want a cheaper strong default: use [`qwen-3.6-plus`](/models/qwen-3.6-plus).
* You want the strongest tool-heavy agent behavior: use [`kimi-k2.6`](/models/kimi-k2.6).
* You want top reasoning at lower cost: use [`deepseek-v4-pro`](/models/deepseek-v4-pro).

## Example

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

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

response = client.chat.completions.create(
    model="qwen-3.7-plus",
    messages=[
        {"role": "system", "content": "You are a senior software engineer."},
        {"role": "user", "content": "Review this migration plan and find the hidden risks."}
    ]
)
```

## Agent query example

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