Qwen 3.5 9B (Q4_K_M)

Alibaba · 1 configuration

Intelligence—

Input / 1M—

Output / 1M—

Context32.8K

Tariff: Atomic Chat · Source: models-dev · USD per million tokens

Thinking configuration

What does more thinking buy you?

Compare this model’s measured thinking configurations.

◌

Change the filters or pick another benchmark. Missing values are not estimated.

Log scaleSelected: thinking default · Click a point to switch configuration

Qwen vision-language model for visual reasoning, documents, and agent tasks

This model is in the catalog but has no imported benchmarks. Capabilities are not estimated.

Inputtext, image

Outputtext

Tool callingYes

Structured outputNot available

SpeedNot available

First tokenNot available

Maximum output8.2K

Catalog listing date2026-03-05