# Qwen3.7 Plus

`alibaba/qwen3.7-plus` · Alibaba · text

Qwen3.7 Plus can answer from long documents and call tools. You can limit how much reasoning it uses on each request.

[Model page](https://sociaro.com/models/alibaba/qwen3.7-plus) · [JSON](https://sociaro.com/models/alibaba/qwen3.7-plus.json) · [Model pricing](https://sociaro.com/pricing?model=alibaba%2Fqwen3.7-plus) · [Documentation](https://docs.sociaro.com/models/alibaba-qwen3-7-plus/)

## Use cases

- Extract decisions from a meeting transcript
- Answer staff questions from a policy handbook

## Technical details

- API model ID — alibaba/qwen3.7-plus
- Provider — Alibaba
- Modality — Text
- Input — Chat messages
- Output — Text
- Endpoint — POST /v1/chat/completions

## Request parameters

- `messages`
- `temperature`
- `top_p`
- `max_tokens`
- `max_completion_tokens`
- `stream`
- `stream_options`
- `tools`
- `tool_choice`
- `parallel_tool_calls`
- `tool_stream`
- `response_format`
- `enable_thinking`
- `thinking_budget`
- `preserve_thinking`
- `seed`
- `stop`
- `presence_penalty`
- `top_k`
- `repetition_penalty`

## Pricing

Rates in USD. Catalogue timestamp 2026-11-21T02:23:44Z.

- USD 0.48 per 1M input tokens · active
- USD 1.92 per 1M output tokens · active
- USD 0.096 per 1M cached input tokens · active

- Thinking is on by default, and thinking tokens bill at the output rate.
