# Qwen 3.7 Flash

Qwen 3.7 Flash is the lowest-cost tier in Alibaba Cloud's Qwen 3.7 line. Qwen 3.7 Flash reads text, images, and video, runs with reasoning on by default, and targets high-volume multimodal agent work.

- **Model ID:** `alibaba/qwen3.7-flash`
- **Type:** chat
- **Providers:** alibaba
- **Context window:** 991,000
- **Maximum output tokens:** 64,000
- **Pricing:** $0.03/1M input tokens, $0.13/1M output tokens
- **Canonical page:** https://vercel.com/ai-gateway/models/qwen3.7-flash

## Supported parameters

Detailed capability metadata has not been reported for this model.

## Example

```ts
import { streamText } from 'ai'

const result = streamText({
  model: 'alibaba/qwen3.7-flash',
  prompt: 'Why is the sky blue?'
})
```

## About

Qwen 3.7 Flash is the Flash-tier release in Alibaba Cloud's Qwen 3.7 generation, sitting below Qwen3.7-Plus and Qwen3.7-Max. Released July 28, 2026 and available through Alibaba Cloud on AI Gateway, this native vision-language model takes text, images, and video in and returns text, within a context window of 991K tokens and up to 64K tokens per response.

Alibaba Cloud describes the Qwen 3.7 Flash series as a comprehensive upgrade over Qwen3.6-Flash in multimodal understanding and agent execution. The documented gains cover universal object recognition, real-world perception, and spatial intelligence. Qwen 3.7 Flash also targets search-agent and code-interpreter-agent scenarios with steadier end-to-end task execution, alongside tuning for multimodal coding.

Reasoning is on by default. You can turn thinking off per request for short lookups, or cap the thinking budget when latency and token spend matter more than reasoning depth. Reasoning traces can carry across turns, so a long agent loop keeps its chain of thought instead of restarting it on every tool call. Qwen 3.7 Flash supports function calling and structured output, with structured output available in non-thinking mode. Alibaba Cloud also documents built-in web search and code execution tools for the model.

Qwen 3.7 Flash accepts up to 16 million pixels per image, video up to two hours or 2 GB, and as many as 64 videos in one request. Each image consumes tokens in proportion to its resolution, so downscale screenshots that don't need full detail.

You can integrate Qwen 3.7 Flash through AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python.

## What to consider

Qwen 3.7 Flash runs reasoning by default, so every request spends thinking tokens unless you turn it off. High-volume classification and extraction jobs usually cost less with thinking disabled, so route simple calls that way.

Alibaba Cloud publishes no benchmark table for Qwen 3.7 Flash, so evaluate the model on representative inputs rather than assuming parity with the Plus tier. Image resolution drives token count directly, and full-resolution screenshots can dominate the cost of a high-volume pipeline.

## When to use

### Best For

- **High-volume multimodal pipelines** running classification, extraction, and routing over images and video at Flash-tier cost
- **Visual agent workflows** including search and code-interpreter agents that read screens and act on what they see
- **Spatial intelligence tasks** using stronger universal object recognition and improved real-world perception
- **Long video understanding** for clips up to two hours or 2 GB in a single request
- **Long-context multimodal input** holding full documents, screenshot histories, and frame sequences within 991K tokens

### Consider Alternatives When

- **Flagship multimodal quality** is required, where Qwen3.8-Max leads the Qwen lineup on the hardest visual and coding work
- **Balanced quality and cost** suits the workload better, where Qwen3.7-Plus sits between the Flash and Max tiers with a larger image allowance
- **Text-only agent workloads** run long tool-calling loops, where Qwen3.7-Max is the Max-tier release in the 3.7 line
- **Image or video generation** is required, which calls for a generation-class model rather than a multimodal understanding model

## Best for

- **High-Volume Multimodal Pipelines:** Classification, extraction, and routing over images and video at Flash-tier cost
- **Visual Agent Workflows:** Search and code-interpreter agents that read screens and act on what they see
- **Spatial Intelligence Tasks:** Stronger universal object recognition and improved real-world perception
- **Long Video Understanding:** Clips up to two hours or 2 GB in a single request
- **Long-Context Multimodal Input:** Full documents, screenshot histories, and frame sequences within 991K tokens

## Consider alternatives

- **Flagship Multimodal Quality:** Qwen3.8-Max leads the Qwen lineup on the hardest visual and coding work
- **Balanced Quality And Cost:** Qwen3.7-Plus sits between the Flash and Max tiers with a larger image allowance
- **Text-Only Agent Workloads:** Qwen3.7-Max is the Max-tier release in the 3.7 line for long tool-calling loops
- **Image Or Video Generation:** A generation-class model fits tasks that produce pixels rather than read them

## Frequently asked questions

### What inputs does Qwen 3.7 Flash accept?

Text, images, and video. Qwen 3.7 Flash is a native vision-language model and returns text only.

### What is the context window for Qwen 3.7 Flash?

The context window is 991K tokens, with up to 64K tokens per response.

### How does Qwen 3.7 Flash compare to Qwen3.6-Flash?

Alibaba Cloud describes the Qwen 3.7 Flash series as a comprehensive upgrade over Qwen3.6-Flash in multimodal understanding and agent execution. The listed gains cover universal object recognition, real-world perception, spatial intelligence, and steadier end-to-end execution in agent scenarios.

### Where does Qwen 3.7 Flash sit in the Qwen 3.7 lineup?

Below Qwen3.7-Plus and Qwen3.7-Max. Qwen 3.7 Flash is the Flash tier, built for throughput and low cost per token rather than the highest reasoning ceiling.

### Is reasoning enabled by default on Qwen 3.7 Flash?

Yes. Qwen 3.7 Flash runs in thinking mode by default. You can disable thinking per request for simple queries, or cap the thinking budget to limit how many reasoning tokens the model spends.

### Does Qwen 3.7 Flash support tool calling and structured output?

Yes. Qwen 3.7 Flash supports function calling and structured output, with structured output available in non-thinking mode. Alibaba Cloud also documents built-in web search and code execution tools for the model.

### How much video can Qwen 3.7 Flash process in one request?

Video up to two hours or 2 GB, and as many as 64 videos in a single request. Images are capped at 16 million pixels each, and higher resolution consumes more tokens.

### How do I access Qwen 3.7 Flash through AI Gateway?

Authenticate with an AI Gateway API key or OIDC token and reference `alibaba/qwen3.7-flash` as the model. You can call Qwen 3.7 Flash through AI SDK, Chat Completions API, Responses API, Messages API, or other API formats, from TypeScript or Python.

### What does Qwen 3.7 Flash cost?

See the pricing section on this page for today's rates. AI Gateway reflects each provider's pricing for Qwen 3.7 Flash with no markup.

### Does Qwen 3.7 Flash support zero data retention?

Yes, Zero Data Retention is available for this model. Zero Data Retention is offered on a per-provider basis. See https://vercel.com/docs/ai-gateway/capabilities/zdr for details.

## Links

- [Model page](https://vercel.com/ai-gateway/models/qwen3.7-flash)
- [AI Gateway documentation](https://vercel.com/docs/ai-gateway)
- [Provider model documentation](https://modelstudio.console.alibabacloud.com/ap-southeast-1?tab=doc#/doc/?type=model&url=2840914_2&modelId=qwen3.7-flash&serviceSite=international)