Qwen: Qwen3.5-27B

Name: Qwen: Qwen3.5-27B
Author: OpenRouter

apache-2.027B

The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance.

Context

262K

Max output

82K

Input price

$0.26/1M tokens

Output price

$2.6/1M tokens

Capabilities

Show unsupported (1)

Reasoning & Interaction

Reasoning

Tool Calling

Output Control

Structured Output

JSON Mode

Infrastructure

Streaming

Batch Processing

Fine-tuning

Details

Model IDqwen/qwen3.5-27b

ProviderOpenRouter

CreatorQwen

Familyqwen3.5

Licenseapache-2.0

Status—

Typechat

Input modalitiestext, image, video

Output modalitiestext

Open weightYes

Parameters27B

Architecture—

Context window262K tokens

Max input—

Max output82K tokens

Reasoning tokens—

Knowledge cutoff—

Release date2026-02-25

Sourceofficial

Tools

Function Callingfunction_calling

Call external functions and APIs

Pricing

Input

$0.26

Output

$2.6

Cache write

—

Cache read

$0.27

Batch in

—

Batch out

—

Family Comparison: qwen3.5

Model	Caps	Perf	Speed	Context	Max out	Pricing
Qwen: Qwen3.5-Flash	RTJJM	—	—	1M	66K	$0.07$0.26
Qwen: Qwen3.5-35B-A3B	RTJJMSBF	—	—	262K	82K	$0.14$1
Qwen: Qwen3.5-9B (batch)	RTJJM	—	—	262K	236K	$0.17$0.25
Qwen: Qwen3.5-9B	RTJJM	—	—	262K	236K	$0.17$0.25
Qwen: Qwen3.5-122B-A10B	RTJJMSBF	—	—	262K	66K	$0.26$2.08
Qwen: Qwen3.5-27B	RTJJMSBF	—	—	262K	82K	$0.26$2.6
Qwen: Qwen3.5 Plus 2026-02-15	RTJJM	—	—	1M	66K	$0.26$1.56
Qwen: Qwen3.5 Plus 2026-04-20	RTJJMSB	—	—	1M	66K	$0.3$1.8
Qwen: Qwen3.5 397B A17B	RTJJMSBF	—	—	262K	236K	$0.5$3.6

API

GET/v1/models/openrouter/qwen/qwen3.5-27b

Qwen: Qwen3.5-27B

qwen/qwen3.5-27b

The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance.

Changes · 8 entries

qwen/qwen3.5-27bupdateca7a400Nov 2, 2026, 03:02 AM

max_output_tokens65536→81920

pricinginput$0.195→$0.26output$1.56→$2.6cached input$0.27

qwen/qwen3.5-27bupdateb2f45bfOct 29, 2026, 03:29 AM

max_output_tokens65536→81920

pricinginput$0.27→$0.26output$2.16→$2.6

qwen/qwen3.5-27bupdate42a9895Oct 20, 2026, 06:39 AM

pricinginput$0.195→$0.27output$1.56→$2.16cached input$0.27

qwen/qwen3.5-27bupdate49ce653Oct 19, 2026, 06:45 AM

max_output_tokens81920→65536

pricinginput$0.26→$0.195output$2.6→$1.56

qwen/qwen3.5-27bupdateda0e420Oct 8, 2026, 06:41 AM

max_output_tokens65536→81920

pricinginput$0.195→$0.26output$1.56→$2.6

qwen/qwen3.5-27bupdate1cd659eMar 24, 2026, 04:19 AM

capabilitiesjson modeyes

qwen/qwen3.5-27bupdate2b100acMar 23, 2026, 05:30 AM

model_typechat

parameters27

release_date2026-02-25

taglineThe Qwen3.5 27B native vision-language Dense model incorp...

tools["function_calling"]

qwen/qwen3.5-27bcreate7f5c66fMar 21, 2026, 05:16 AM