Qwen: Qwen3.5-35B-A3B

apache-2.035B / 3B

The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency.

Context
262K
Max output
82K
Input price
$0.14/1M tokens
Output price
$1/1M tokens

Capabilities

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

Details

Model IDqwen/qwen3.5-35b-a3b
Provider OpenRouter
Creator Qwen
Familyqwen3.5
Licenseapache-2.0
Status—
Typechat
Input modalitiestext, image, video
Output modalitiestext
Open weightYes
Parameters35B / 3B
Architecture—
Context window262K tokens
Max input—
Max output82K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0.14
Output
$1
Cache write
—
Cache read
$0.05
Batch in
—
Batch out
—

Family Comparison: qwen3.5

ModelContextMax outPricing
Qwen: Qwen3.5-Flash1M66K$0.07$0.26
Qwen: Qwen3.5-35B-A3B262K82K$0.14$1
Qwen: Qwen3.5-9B (batch)262K236K$0.17$0.25
Qwen: Qwen3.5-9B262K236K$0.17$0.25
Qwen: Qwen3.5-122B-A10B262K66K$0.26$2.08
Qwen: Qwen3.5-27B262K82K$0.26$2.6
Qwen: Qwen3.5 Plus 2026-02-151M66K$0.26$1.56
Qwen: Qwen3.5 Plus 2026-04-201M66K$0.3$1.8
Qwen: Qwen3.5 397B A17B262K236K$0.5$3.6

API

GET/v1/models/openrouter/qwen/qwen3.5-35b-a3b

Qwen: Qwen3.5-35B-A3B

qwen/qwen3.5-35b-a3b

The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency.

Changes · 24 entries
qwen/qwen3.5-35b-a3bupdateca7a400Nov 2, 2026, 03:02 AM
max_output_tokens262144→81920
pricinginput$0.15→$0.14
qwen/qwen3.5-35b-a3bupdate4e8b6afOct 21, 2026, 06:35 AM
max_output_tokens235929→81920
pricinginput$0.15→$0.14
qwen/qwen3.5-35b-a3bupdate63ba2aaOct 18, 2026, 06:34 AM
max_output_tokens16384→235929
qwen/qwen3.5-35b-a3bupdate0d5a9a1Oct 14, 2026, 06:38 AM
max_output_tokens32768→16384
pricinginput$0.08→$0.15output$0.75→$1cached input$0.04→$0.05
qwen/qwen3.5-35b-a3bupdate70614e7Oct 9, 2026, 06:39 AM
max_output_tokens235929→32768
pricinginput$0.15→$0.08output$1→$0.75cached input$0.05→$0.04
qwen/qwen3.5-35b-a3bupdate2b89bf1Oct 2, 2026, 06:39 AM
max_output_tokens65536→235929
pricinginput$0.163→$0.15output$1.3→$1cached input$0.156→$0.05
qwen/qwen3.5-35b-a3bupdatef41f4c4Sep 28, 2026, 06:53 AM
max_output_tokens16384→65536
pricinginput$0.313→$0.163output$1.25→$1.3
qwen/qwen3.5-35b-a3bupdate7bc8de4Sep 20, 2026, 06:33 AM
max_output_tokens65536→16384
pricinginput$0.163→$0.313output$1.3→$1.25
qwen/qwen3.5-35b-a3bupdatea6d63d7Sep 15, 2026, 06:39 AM
max_output_tokens16384→65536
pricinginput$0.313→$0.163output$1.25→$1.3
qwen/qwen3.5-35b-a3bupdate5cd8ca9Sep 6, 2026, 06:34 AM
max_output_tokens235929→16384
pricinginput$0.25→$0.313cached input$0.25→$0.156
qwen/qwen3.5-35b-a3bupdatee3d7dedAug 31, 2026, 04:13 AM
max_output_tokens65536→235929
pricinginput$0.225→$0.25output$1.8→$1.25cached input$0.225→$0.25
qwen/qwen3.5-35b-a3bupdatebe35184Aug 17, 2026, 04:02 AM
max_output_tokens262144→65536
pricinginput$0.25→$0.225output$1.25→$1.8cached input$0.25→$0.225
qwen/qwen3.5-35b-a3bupdate3cddff5Aug 13, 2026, 02:54 AM
pricinginput$0.14→$0.25output$1→$1.25cached input$0.05→$0.25
qwen/qwen3.5-35b-a3bupdate20c73acJul 17, 2026, 02:34 AM
max_output_tokens81920→262144
qwen/qwen3.5-35b-a3bupdate88d97e5Jun 30, 2026, 04:49 AM
max_output_tokens262144→81920
qwen/qwen3.5-35b-a3bupdatec4a5601Jun 20, 2026, 03:43 PM
max_output_tokens81920→262144
qwen/qwen3.5-35b-a3bupdateab879c8Jun 18, 2026, 08:32 AM
max_output_tokens262144→81920
qwen/qwen3.5-35b-a3bupdated657a45Jun 3, 2026, 03:19 AM
max_output_tokens81920→262144
pricinginput$0.139→$0.14
qwen/qwen3.5-35b-a3bupdate9e091d8May 23, 2026, 05:20 PM
pricinginput$0.14→$0.139
qwen/qwen3.5-35b-a3bupdatec3b810cMay 11, 2026, 07:02 AM
max_output_tokens262144→81920
pricinginput$0.15→$0.14
qwen/qwen3.5-35b-a3bupdate241c61aMay 7, 2026, 04:28 AM
max_output_tokens65536→262144
pricinginput$0.163→$0.15output$1.3→$1cached input$0.05
qwen/qwen3.5-35b-a3bupdate1cd659eMar 24, 2026, 04:19 AM
capabilitiesjson modeyes
qwen/qwen3.5-35b-a3bupdate2b100acMar 23, 2026, 05:30 AM
model_typechat
parameters35
active_parameters3
release_date2026-02-25
taglineThe Qwen3.5 Series 35B-A3B is a native vision-language mo...
tools["function_calling"]
qwen/qwen3.5-35b-a3bcreate7f5c66fMar 21, 2026, 05:16 AM