Enterprise DNAEnterprise DNA
Qwen logo

Models · Best vision

Qwen3.5 397B A17B

by Qwen

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model.

Visit Qwen ↗

Our verdict

Not reviewed yet

We have not reviewed Qwen3.5 397B A17B 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 397B A17B

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.

Notes

Qwen3.5 397B A17B is listed in the EDNA Models directory from the OpenRouter catalogue.

Key facts

What we have checked

Input price
$0.600 per million tokens
Checked OpenRouter models API
Output price
$3.60 per million tokens
Checked OpenRouter models API
Price on atlas-cloud
$0.550 per million cached input tokens
Checked OpenRouter models API
Price on atlas-cloud
$0.550 per million input tokens
Checked OpenRouter models API
Price on atlas-cloud
$3.50 per million output tokens
Checked OpenRouter models API
Price on deepinfra
$0.220 per million cached input tokens
Checked OpenRouter models API
Price on deepinfra
$0.450 per million input tokens
Checked OpenRouter models API
Price on deepinfra
$3.00 per million output tokens
Checked OpenRouter models API
Price on digitalocean
$0.110 per million cached input tokens
Checked OpenRouter models API
Gpqa diamond
86.4% (for 13 Feb 2026)
Checked Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private
31.2% (for 13 Feb 2026)
Checked Epoch AI (CC BY 4.0)
Apex agents
24.9% (for 13 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/qwen3.5-397b-a17b`.

  • openrouter · qwen/qwen3.5-397b-a17b · Docs

OpenRouter id: qwen/qwen3.5-397b-a17b

Price

What Qwen3.5 397B A17B costs, over time

Input price

$0.550 to $0.600

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

Source: OpenRouter models API. Checked .

Output price

$3.50 to $3.60

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$0.550 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
atlas-cloudInput$0.550 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
atlas-cloudOutput$3.50 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraCached input$0.220 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraInput$0.450 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
deepinfraOutput$3.00 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanCached input$0.110 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanInput$0.550 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
digitaloceanOutput$3.50 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudInput$0.600 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
gmicloudOutput$3.60 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
novitaInput$0.600 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
novitaOutput$3.60 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailCached input$0.300 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailInput$0.500 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
parasailOutput$3.60 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
phalaCached input$0.225 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
phalaInput$0.550 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
phalaOutput$3.50 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
qwenInput$0.390 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
qwenOutput$2.34 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
streamlakeCached input$0.120 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
streamlakeInput$0.600 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
streamlakeOutput$3.60 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API
veniceInput$0.750 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
veniceOutput$4.50 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much Qwen3.5 397B A17B is used

Tokens served a day

4B to 3.2B

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 397B A17B 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 Index21.4indexAs of 26 Oct 2026Artificial Analysis via OpenRouter
Artificial Analysis Coding Index48.2indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
Artificial Analysis Agentic Index8.3indexAs of 10 Nov 2026Artificial Analysis via OpenRouter
LMArena text rating (Elo)1,438EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
LMArena web development rating (Elo)1,400EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
LMArena vision rating (Elo)1,262EloAs of 10 Nov 2026LMArena (CC-BY-4.0), published 2026-11-09
Design Arena rating (Elo)1,187EloAs of 10 Nov 2026Design Arena via OpenRouter
Apex agents (best-across-versions)24.9percentAs of 13 Feb 2026Epoch AI (CC BY 4.0)
Dtbench (best-across-versions)87.5percentAs of 13 Feb 2026Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private (best-across-versions)31.2percentAs of 13 Feb 2026Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)86.4percentAs of 13 Feb 2026Epoch AI (CC BY 4.0)
Lmca (best-across-versions)37.9percentAs of 13 Feb 2026Epoch AI (CC BY 4.0)
Show 2 more scores
ScoreValueSourceChecked
Mystery game puzzles (best-across-versions)18percentAs of 13 Feb 2026Epoch AI (CC BY 4.0)
Otis mock aime 2024 2025 (best-across-versions)Saturated88.9percentAs of 13 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: 0.5 to 0.6

    Source: OpenRouter models API

  2. Price changed

    output per mtok: 3.5 to 3.6

    Source: OpenRouter models API

  3. Price changed

    input per mtok: 0.55 to 0.5

    Source: OpenRouter models API

  4. Price changed

    output per mtok: 3 to 3.5

    Source: OpenRouter models API

  5. Price changed

    input per mtok: 0.45 to 0.55

    Source: OpenRouter models API

  6. Price changed

    output per mtok: 3.5 to 3

    Source: OpenRouter models API

  7. Price changed

    input per mtok: 0.55 to 0.45

    Source: OpenRouter models API

  8. Price changed

    output per mtok: 2.34 to 3.5

    Source: OpenRouter models API

  9. Price changed

    input per mtok: 0.39 to 0.55

    Source: OpenRouter models API

  10. Price changed

    output per mtok: 3 to 2.34

    Source: OpenRouter models API

  11. Price changed

    input per mtok: 0.45 to 0.39

    Source: OpenRouter models API

  12. Price changed

    output per mtok: 2.45 to 3

    Source: OpenRouter models API

  13. Price changed

    input per mtok: 0.385 to 0.45

    Source: OpenRouter models API

USAGE / OPENROUTER

How much Qwen3.5 397B A17B is used

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

Tokens, last 7 days
19.4B ▲22.3%
Requests, last 7 days
3.5M
Tool calls, last 7 days
244K
People's vote
1438
Average cost per request
66.1¢
Price per million tokens
$0.6 in · $3.6 out
025B50B19 Sept: 4B tokens, 421K requests20 Sept: 2.8B tokens, 183K requests21 Sept: 2.3B tokens, 320K requests22 Sept: 26.8B tokens, 766K requests23 Sept: 3.3B tokens, 573K requests24 Sept: 6.9B tokens, 342K requests25 Sept: 4.7B tokens, 318K requests26 Sept: 3.4B tokens, 350K requests27 Sept: 2.3B tokens, 294K requests28 Sept: 4.5B tokens, 321K requests29 Sept: 13B tokens, 574K requests30 Sept: 5.5B tokens, 490K requests1 Oct: 6B tokens, 494K requests2 Oct: 10.7B tokens, 694K requests3 Oct: 5.7B tokens, 374K requests4 Oct: 2B tokens, 276K requests5 Oct: 3.5B tokens, 363K requests6 Oct: 7.2B tokens, 528K requests7 Oct: 8.4B tokens, 867K requests8 Oct: 6.1B tokens, 531K requests9 Oct: 5.7B tokens, 616K requests10 Oct: 5.3B tokens, 323K requests11 Oct: 1.3B tokens, 185K requests12 Oct: 6.5B tokens, 621K requests13 Oct: 11.7B tokens, 1.2M requests14 Oct: 3.6B tokens, 560K requests15 Oct: 5.1B tokens, 460K requests16 Oct: 4.9B tokens, 538K requests17 Oct: 4.9B tokens, 390K requests18 Oct: 2.5B tokens, 384K requests19 Oct: 4.3B tokens, 388K requests20 Oct: 2.7B tokens, 349K requests21 Oct: 1.8B tokens, 251K requests22 Oct: 2.5B tokens, 497K requests23 Oct: 2.3B tokens, 643K requests24 Oct: 3.5B tokens, 156K requests25 Oct: 631M tokens, 113K requests26 Oct: 3.7B tokens, 302K requests27 Oct: 3.2B tokens, 324K requests28 Oct: 2.9B tokens, 593K requests29 Oct: 1.9B tokens, 429K requests30 Oct: 1.9B tokens, 180K requests31 Oct: 3.8B tokens, 173K requests1 Nov: 1.2B tokens, 172K requests2 Nov: 2B tokens, 230K requests3 Nov: 2.2B tokens, 374K requests4 Nov: 2.8B tokens, 485K requests5 Nov: 3.7B tokens, 345K requests6 Nov: 2.2B tokens, 479K requests7 Nov: 3.1B tokens, 899K requests8 Nov: 1.7B tokens, 421K requests9 Nov: 2.8B tokens, 602K requests10 Nov: 3.2B tokens, 311K requests19 Sept3 Oct17 Oct31 Oct10 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with Qwen3.5 397B A17B.

Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-09. Hosting routes and app features can differ.

DeveloperQwen
Exact model identifierqwen/qwen3.5-397b-a17b
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
16 Feb 2026
Listed retirement date
Not established
Inspect the sources and their scope
catalogue source ↗

qwen/qwen3.5-397b-a17b: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-09
openrouter.ai ↗

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

Checked 2026-11-09
Licence source ↗

Licence declared in the Qwen/Qwen3.5-397B-A17B 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: 48.2 (2026-11-09) ↗Agentic Index: 8.3 (2026-11-09) ↗Design Arena: 1187 (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 →