Qwen: Qwen3.6 Flash

apache-2.0

Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series.

Context
1M
Max output
66K
Input price
$0.19/1M tokens
Output price
$1.13/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
Structured Output
JSON Mode
Infrastructure
Streaming
Batch Processing
Fine-tuning

Details

Model IDqwen/qwen3.6-flash
Provider OpenRouter
Creator Qwen
Familyqwen3.6
Licenseapache-2.0
Status—
Typechat
Input modalitiestext, image, video
Output modalitiestext
Open weightYes
Parameters—
Architecture—
Context window1M tokens
Max input—
Max output66K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0.19
Output
$1.13
Cache write
—
Cache read
—
Batch in
—
Batch out
—

Family Comparison: qwen3.6

ModelContextMax outPricing
Qwen: Qwen3.6 Plus (free)1M66K—
Qwen: Qwen3.6 Plus Preview (free)1M32K—
Qwen: Qwen3.6 35B A3B262K236K$0.1$0.9
Qwen: Qwen3.6 Flash1M66K$0.19$1.13
Qwen: Qwen3.6 27B262K82K$0.32$3.2
Qwen: Qwen3.6 Plus1M66K$0.33$1.95
Qwen: Qwen3.6 Max Preview262K66K$1.03$6.16

API

GET/v1/models/openrouter/qwen/qwen3.6-flash

Qwen: Qwen3.6 Flash

qwen/qwen3.6-flash

Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series.

Changes · 3 entries
qwen/qwen3.6-flashupdateca7a400Nov 2, 2026, 03:02 AM
pricinginput$0.25→$0.188output$1.5→$1.125
qwen/qwen3.6-flashupdate73d11c6May 18, 2026, 03:39 AM
pricinginput$0.25→$0.188output$1.5→$1.125
qwen/qwen3.6-flashcreatebc0fb7dMay 2, 2026, 02:14 AM