Enterprise DNAEnterprise DNA
Qwen logo

Models · Best vision

Qwen3.5-35B-A3B

by Qwen

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.

Visit Qwen ↗

Our verdict

Not reviewed yet

We have not reviewed Qwen3.5-35B-A3B yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About 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.

Notes

Qwen3.5-35B-A3B is listed in the EDNA Models directory from the OpenRouter catalogue.

Key facts

What we have checked

Input price
$0.140 per million tokens
Checked OpenRouter models API
Output price
$1.00 per million tokens
Checked OpenRouter models API
Price on atlas-cloud
$0.225 per million cached input tokens
Checked OpenRouter models API
Price on atlas-cloud
$0.225 per million input tokens
Checked OpenRouter models API
Price on atlas-cloud
$1.80 per million output tokens
Checked OpenRouter models API
Price on darkbloom
$0.033 per million cached input tokens
Checked OpenRouter models API
Price on darkbloom
$0.065 per million input tokens
Checked OpenRouter models API
Price on darkbloom
$0.750 per million output tokens
Checked OpenRouter models API
Price on deepinfra
$0.050 per million cached input tokens
Checked OpenRouter models API
Gpqa diamond
83.5% (for 24 Feb 2026)
Checked Epoch AI (CC BY 4.0)
Dtbench
80% (for 24 Feb 2026)
Checked Epoch AI (CC BY 4.0)
Lmca
29.5% (for 24 Feb 2026)
Checked Epoch AI (CC BY 4.0)

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via OpenRouter with model id `qwen/qwen3.5-35b-a3b`.

  • openrouter · qwen/qwen3.5-35b-a3b · Docs

OpenRouter id: qwen/qwen3.5-35b-a3b

Price

What Qwen3.5-35B-A3B costs, over time

Input price

$0.250 to $0.140

US dollars per million input tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Output price

$1.25 to $1.00

US dollars per million output tokens. 3 Sept 2026 to 10 Nov 2026, 44 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
atlas-cloudCached input$0.225 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
atlas-cloudInput$0.225 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
atlas-cloudOutput$1.80 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
darkbloomCached input$0.033 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
darkbloomInput$0.065 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
darkbloomOutput$0.750 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraCached input$0.050 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraInput$0.140 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraOutput$1.00 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailCached input$0.050 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailInput$0.150 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailOutput$1.00 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
qwenInput$0.163 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
qwenOutput$1.30 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
siliconflowCached input$0.150 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
siliconflowInput$0.240 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
siliconflowOutput$1.80 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
veniceCached input$0.050 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
veniceInput$0.150 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
veniceOutput$1.00 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much Qwen3.5-35B-A3B is used

Tokens served a day

2.3B to 4.7B

tokens a day on OpenRouter. 19 Sept 2026 to 10 Nov 2026, 53 readings.

Source: OpenRouter model activity (748 of 748 series). Checked .

Scores

How Qwen3.5-35B-A3B scores

Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.

ScoreValueSourceChecked
Artificial Analysis Intelligence Index19.3indexAs of 26 Oct 2026Artificial Analysis via OpenRouter
Artificial Analysis Coding Index37indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
LMArena text rating (Elo)1,395EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
LMArena web development rating (Elo)1,253EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
Dtbench (best-across-versions)80percentAs of 24 Feb 2026Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)83.5percentAs of 24 Feb 2026Epoch AI (CC BY 4.0)
Lmca (best-across-versions)29.5percentAs of 24 Feb 2026Epoch AI (CC BY 4.0)
Otis mock aime 2024 2025 (best-across-versions)Saturated70percentAs of 24 Feb 2026Epoch AI (CC BY 4.0)
Saturated
Top models score close to the maximum, so this test no longer separates them.

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

  1. Price changed

    input per mtok: 0.15 to 0.14

    Source: OpenRouter models API

  2. Price changed

    output per mtok: 0.75 to 1

    Source: OpenRouter models API

  3. Price changed

    input per mtok: 0.08 to 0.15

    Source: OpenRouter models API

  4. Price changed

    output per mtok: 1 to 0.75

    Source: OpenRouter models API

  5. Price changed

    input per mtok: 0.15 to 0.08

    Source: OpenRouter models API

  6. Price changed

    output per mtok: 0.75 to 1

    Source: OpenRouter models API

  7. Price changed

    input per mtok: 0.08 to 0.15

    Source: OpenRouter models API

  8. Price changed

    output per mtok: 1 to 0.75

    Source: OpenRouter models API

  9. Price changed

    input per mtok: 0.15 to 0.08

    Source: OpenRouter models API

  10. Price changed

    output per mtok: 1.3 to 1

    Source: OpenRouter models API

  11. Price changed

    input per mtok: 0.1625 to 0.15

    Source: OpenRouter models API

  12. Price changed

    output per mtok: 1.25 to 1.3

    Source: OpenRouter models API

  13. Price changed

    input per mtok: 0.3125 to 0.1625

    Source: OpenRouter models API

  14. Price changed

    output per mtok: 0.75 to 1.25

    Source: OpenRouter models API

  15. Price changed

    input per mtok: 0.08 to 0.3125

    Source: OpenRouter models API

  16. Price changed

    output per mtok: 1.25 to 0.75

    Source: OpenRouter models API

  17. Price changed

    input per mtok: 0.25 to 0.08

    Source: OpenRouter models API

  18. Price changed

    output per mtok: 1 to 1.25

    Source: OpenRouter models API

  19. Price changed

    input per mtok: 0.14 to 0.25

    Source: OpenRouter models API

USAGE / OPENROUTER

How much Qwen3.5-35B-A3B is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
40.3B ▲8.8%
Requests, last 7 days
10M
Tool calls, last 7 days
303K
People's vote
1395
Average cost per request
11.2¢
Price per million tokens
$0.14 in · $1 out
010B20B19 Sept: 2.3B tokens, 284K requests20 Sept: 1.9B tokens, 314K requests21 Sept: 18.7B tokens, 706K requests22 Sept: 6.4B tokens, 907K requests23 Sept: 1.8B tokens, 336K requests24 Sept: 3.6B tokens, 372K requests25 Sept: 1.7B tokens, 311K requests26 Sept: 2.4B tokens, 244K requests27 Sept: 2B tokens, 357K requests28 Sept: 1.9B tokens, 237K requests29 Sept: 1.5B tokens, 338K requests30 Sept: 1.6B tokens, 395K requests1 Oct: 1.8B tokens, 375K requests2 Oct: 4.6B tokens, 388K requests3 Oct: 1.7B tokens, 279K requests4 Oct: 1.8B tokens, 381K requests5 Oct: 2.4B tokens, 295K requests6 Oct: 1.5B tokens, 237K requests7 Oct: 1.9B tokens, 303K requests8 Oct: 1.6B tokens, 324K requests9 Oct: 1.8B tokens, 309K requests10 Oct: 1.2B tokens, 141K requests11 Oct: 1.1B tokens, 372K requests12 Oct: 1.1B tokens, 215K requests13 Oct: 2.6B tokens, 462K requests14 Oct: 2.3B tokens, 719K requests15 Oct: 1.6B tokens, 589K requests16 Oct: 2.9B tokens, 569K requests17 Oct: 3.2B tokens, 324K requests18 Oct: 2.5B tokens, 735K requests19 Oct: 1.8B tokens, 528K requests20 Oct: 5.6B tokens, 2M requests21 Oct: 3.9B tokens, 1.2M requests22 Oct: 2B tokens, 350K requests23 Oct: 5.4B tokens, 1.2M requests24 Oct: 3.1B tokens, 339K requests25 Oct: 860M tokens, 107K requests26 Oct: 5.2B tokens, 1.9M requests27 Oct: 4.4B tokens, 718K requests28 Oct: 4.5B tokens, 1.1M requests29 Oct: 6.2B tokens, 1.4M requests30 Oct: 10.1B tokens, 3.8M requests31 Oct: 2.2B tokens, 443K requests1 Nov: 1.8B tokens, 350K requests2 Nov: 6.2B tokens, 2M requests3 Nov: 6.1B tokens, 1.4M requests4 Nov: 5.6B tokens, 1.5M requests5 Nov: 8.5B tokens, 2M requests6 Nov: 5B tokens, 1.1M requests7 Nov: 4.6B tokens, 1.5M requests8 Nov: 3.9B tokens, 1.1M requests9 Nov: 8B tokens, 1.9M requests10 Nov: 4.7B tokens, 921K requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with Qwen3.5-35B-A3B.

Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-07. Hosting routes and app features can differ.

DeveloperQwen
Exact model identifierqwen/qwen3.5-35b-a3b
Inputtext, image, video
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Listed support
Availability
available
Price basis
token
Licence verification
Apache 2.0, open weights
Context length
262K tokens
Knowledge cutoff
Not established
Developer release date
Not established
First seen in the catalogue
25 Feb 2026
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

qwen/qwen3.5-35b-a3b: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-07
openrouter.ai ↗

Source for reasoning controls, first seen, tool calling, context length, input, output, structured output.

Checked 2026-11-07
Licence source ↗

Licence declared in the Qwen/Qwen3.5-35B-A3B model repository on Hugging Face, which holds the weights files. Read the licence terms before use.

Checked 2026-11-07
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Extract document dataWorkflow & starter prompt ↗Run a reliable agentWorkflow & starter prompt ↗

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

Price date: 10 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Coding Index: 37 (2026-11-09) ↗
Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →