Qwen3.7 Flash

About

Qwen3.7 Flash is a Qwen vision-language reasoning model that accepts text, images, and video, and returns text. It supports tools and has a 1,000,000-token context window, with a maximum output of 65,536 tokens. Its listed rates are USD 0.03 per 1M input tokens and USD 0.13 per 1M output tokens. The summary describes it as suited to multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world tasks. The model ID is qwen/qwen3.7-flash, and its listed release date is 2026-07-27. For builders, its video input distinguishes its supported modalities from a text-only interface, while tool support and reasoning are relevant to agent workflows. Output remains text, despite its ability to process visual and video inputs.

Who it is for

It suits builders creating multimodal agents or workflows for visual coding, search, and computer interaction. Teams working with text, images, or video inputs can use its listed modalities and tool support.

Details

Lab

Qwenopenrouter.ai · 3 Oct 2026

Context

1,000Kopenrouter.ai · 3 Oct 2026

Input price

$0.03 / 1Mopenrouter.ai · 3 Oct 2026

Output price

$0.13 / 1Mopenrouter.ai · 3 Oct 2026

Max output

65,536 tokensopenrouter.ai · 3 Oct 2026

Inputs

text, image, videoopenrouter.ai · 3 Oct 2026

Open weights

Noopenrouter.ai · 3 Oct 2026

Listed on Inferse

• Newest Models in 2026466 listed
• Longest-Context Models in 2026466 listed
• Cheapest Language Models in 2026437 listed
• Models with Tool Calling in 2026395 listed
• Reasoning Models in 2026332 listed
• Vision Language Models in 2026295 listed
• Qwen Models: Pricing per 1M Tokens and Context (2026)52 listed

Sources

• openrouter.ai/qwen/qwen3.7-flash· checked 3 Oct 2026