qwen3.5-flash

apache-2.0

Qwen-Flash is the fastest and most cost-effective model in the Qwen series, designed for simple jobs. Qwen-Flash features flexible tiered pricing, resulting in more reasonable billing compared to Qwen-Turbo. Usage \| API reference \| Try online \| Thinking #### International If you select the International deployment scope, model inference compute resources are dynamically scheduled worldwide, excluding the Chinese mainland. Static data is stored in your selected region. Supported region: Singapore.

Context
1M
Max output
64K
Input price
$0.1/1M tokens
Output price
$0.4/1M tokens

Capabilities

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

Details

Provider Alibaba Cloud
Creator Qwen
Familyqwen3.5
Licenseapache-2.0
Status—
Typechat
Input modalitiestext
Output modalitiestext
Open weightYes
Parameters—
Architecture—
Context window1M tokens
Max input—
Max output64K tokens
Reasoning tokensYes
Knowledge cutoff—
Release date—
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Endpoints

chatPOST
https://dashscope-intl.aliyuncs.com/compatible-mode/chat

Pricing

Input
$0.1
Output
$0.4
Cache write
—
Cache read
—
Batch in
—
Batch out
—

Family Comparison: qwen3.5

ModelContextMax outPricing
qwen3.5-122b-a10b256K64K—
qwen3.5-27b256K64K—
qwen3.5-35b-a3b256K64K—
qwen3.5-397b-a17b256K64K—
qwen3.5-livetranslate-flash-realtime———
qwen3.5-ocr———
qwen3.5-omni-flash-realtime262K66K—
qwen3.5-omni-flash262K——
qwen3.5-omni-plus-realtime262K66K—
qwen3.5-omni-plus256K——
qwen3.5-plus1M64K—
qwen3.5-flash1M64K$0.1$0.4

API

GET/v1/models/alibaba/qwen3.5-flash

qwen3.5-flash

Qwen-Flash is the fastest and most cost-effective model in the Qwen series, designed for simple jobs. Qwen-Flash features flexible tiered pricing, resulting in more reasonable billing compared to Qwen-Turbo. Usage \| API reference \| Try online \| Thinking #### International If you select the International deployment scope, model inference compute resources are dynamically scheduled worldwide, excluding the Chinese mainland. Static data is stored in your selected region. Supported region: Singapore.

Changes · 13 entries
qwen3.5-flashupdateca7a400Nov 2, 2026, 03:02 AM
context_window983616→1000000
max_output_tokens65536→64000
capabilitiestool callyesstructured outputyesbatchyesjson modeyes
page_urlhttps://www.alibabacloud.com/help/en/model-studio/models→https://www.alibabacloud.com/help/en/model-studio/text-ge...
tools["function_calling"]
reasoning_tokensyes
qwen3.5-flashupdate53ef452Jul 9, 2026, 02:32 AM
reasoning_tokensyes
qwen3.5-flashupdate80c574aJun 3, 2026, 07:05 AM
context_window983616→1000000
max_output_tokens65536→64000
page_urlhttps://www.alibabacloud.com/help/en/model-studio/models→https://www.alibabacloud.com/help/en/model-studio/text-ge...
tools["function_calling"]
qwen3.5-flashupdate6231fb5Apr 22, 2026, 02:50 AM
context_window1000000→983616
max_output_tokens81920→65536
descriptionQwen-Flash is the fastest and most cost-effective model i...→Qwen-Flash is the fastest and most cost-effective model i...
qwen3.5-flashupdate5c578c7Apr 8, 2026, 03:30 PM
descriptionThe fastest and most cost-effective model in the Qwen ser...→Qwen-Flash is the fastest and most cost-effective model i...
qwen3.5-flashupdate82e6976Apr 7, 2026, 02:37 PM
descriptionQwen-Flash is the fastest and most cost-effective model i...→The fastest and most cost-effective model in the Qwen ser...
qwen3.5-flashupdatec2a7935Apr 4, 2026, 01:05 AM
descriptionQwen-Flash is the fastest and most cost-effective model i...→Qwen-Flash is the fastest and most cost-effective model i...
qwen3.5-flashupdate22fb110Apr 1, 2026, 10:05 AM
descriptionThe fastest and most cost-effective model in the Qwen ser...→Qwen-Flash is the fastest and most cost-effective model i...
qwen3.5-flashupdate1cd659eMar 24, 2026, 04:19 AM
capabilitiesfine tuningyes
qwen3.5-flashupdateb301ebeMar 23, 2026, 11:47 PM
descriptionThe fastest and most cost-effective model in the Qwen ser...
page_urlhttps://www.alibabacloud.com/help/en/model-studio/models
taglineThe fastest and most cost-effective model in the Qwen ser...
qwen3.5-flashupdate2b100acMar 23, 2026, 05:30 AM
licenseapache-2.0
open_weightyes
qwen3.5-flashupdate7a4f1f6Mar 22, 2026, 05:43 AM
nameQwen3.5-Flash→qwen3.5-flash
capabilitiestool callyesreasoningyes
pricinginput$0.029→$0.1output$0.287→$0.4
max_output_tokens81920
model_typechat
modalitiesinput["text"]output["text"]
endpoints["chat"]
qwen3.5-flashcreate7f5c66fMar 21, 2026, 05:16 AM