How much does Qwen3.5 397B A17B cost?

Qwen3.5 397B A17B costs $0.55 per million input tokens and $3.50 per million output tokens. For a typical conversation (~2,000 tokens), that's approximately $0.005 per message.

Is Qwen3.5 397B A17B open source?

Yes, Qwen3.5 397B A17B is open source.

How does Qwen3.5 397B A17B compare to Qwen3.7 Max?

Qwen3.5 397B A17B has an average score of 69.7 while Qwen3.7 Max scores 69.8. Qwen3.7 Max slightly outperforms Qwen3.5 397B A17B overall. Qwen3.5 397B A17B costs $0.55/1M input vs Qwen3.7 Max at $1.25/1M input. See full comparison →

Home/Models/Qwen3.5 397B A17B

Qwen3.5 397B A17B

Name: Qwen3.5 397B A17B · benchmarks, pricing and providers
Creator: BenchGecko

by Alibaba Qwen · Released Feb 2026

Open SourceMultimodal

69.7

avg score

Rank #38

Compare

Better than 88% of all models

Context

262K tokens (~131 books)

Input $/1M

$0.55

Output $/1M

$3.50

Type

multimodal

License

Open Source

Benchmarks

29 tested

Data as of 2026-10-05

About

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. It delivers...

Tested on 29 benchmarks · BenchGecko score 69.7. Top scores: Chatbot Arena Elo — Overall (1441.8%), Chatbot Arena Elo — Coding (1399.4%), OpenCompass — AIME2025 (92.3%).

Capabilities

coding

83.0

#4 globally

math

70.8

#40 globally

knowledge

58.8

#67 globally

agentic

24.9

#41 globally

speed

41.8

#57 globally

general

44.5

#51 globally

language

91.5

#9 globally

Benchmark Scores

Compare All

Tested on 29 benchmarks · Ranked across 8 categories

Score Distribution (all 312 models)

0255075100

▲ You are here

codingCompare coding →

OpenCompass — LiveCodeBenchV6

OpenCompass Live Code Bench v6. Fresh competitive programming problems to evaluate code generation without memorization.

83.0·

mathCompare math →

OpenCompass — AIME2025

OpenCompass evaluation on AIME 2025 problems. Tests mathematical reasoning on fresh competition problems.

92.3·

OTIS Mock AIME 2024-2025

Mock AIME (American Invitational Mathematics Exam) problems from OTIS. Tests mathematical competition performance.

88.9·

FrontierMath-Tiers-1-3-v2-Private

31.2·

knowledgeCompare knowledge →

OpenCompass — GPQA-Diamond

OpenCompass evaluation of GPQA Diamond. PhD-level science questions from the hardest subset.

88.4·

OpenCompass — MMLU-Pro

OpenCompass MMLU-Pro evaluation. Harder knowledge test with more answer choices.

87.6·

GPQA diamond

Graduate-level science questions written by PhD experts. Diamond subset contains questions where experts disagree, testing deep understanding.

81.8·

Quick compare:

vs Qwen3.7 Max

vs phi-3-medium 14B

vs GPT-5.2 Pro

Excellent (85+) Good (70-85) Average (50-70) Below (<50)

Model Family · Alibaba Qwen Qwen 3.5

Qwen3.5 397B A17BFeb 2026

69.7

$0.55/M in262Kctx29 benchmarks

Qwen3.5 Plus 2026-02-15Feb 2026

$0.26/M in(-0.29)1.0Mctx(+738K)

Qwen3.5 Plus 2026-04-20Apr 2026

$0.30/M in(+0.04)1.0Mctx

Qwen3.5-122B-A10BFeb 2026

$0.26/M in(-0.04)262Kctx(-738K)15 benchmarks

Qwen3.5-27BFeb 2026

$0.20/M in(-0.07)262Kctx5 benchmarks

Qwen3.5-35B-A3BFeb 2026

53.5-16.2

$0.15/M in(-0.05)262Kctx10 benchmarks

Qwen3.5-9BMar 2026

40.0-13.5

$0.10/M in(-0.05)262Kctx19 benchmarks

Qwen3.5-9B (batch)Mar 2026

$0.17/M in(+0.07)262Kctx

Qwen3.5-FlashFeb 2026

36.5-3.5

$0.07/M in(-0.11)1.0Mctx(+738K)12 benchmarks

See the full Qwen 3.5 family →

Recently Happened

Qwen3.5 397B A17B pricing increased 50%

Sep 9, 2026

Qwen3.5 397B A17B pricing dropped 33%

Sep 7, 2026

Qwen3.5 397B A17B pricing increased 50%

Sep 3, 2026

Qwen3.5 397B A17B pricing dropped 35%

Aug 26, 2026

Qwen3.5 397B A17B pricing increased 54%

Aug 24, 2026

Qwen3.5 397B A17B pricing dropped 35%

Aug 15, 2026

Similar Models

Links

Info

Alibaba Qwen Pricing explorer Developers · API

Research

Documentation

Community

Source Code

BenchGecko API

qwen3-5-397b-a17b

Specifications

Typemultimodal
Context262K tokens (~131 books)
ReleasedFeb 2026
LicenseOpen Source
StatusActive
Cost / Message~$0.005

Available On

Alibaba Qwen$0.55

Frequently Asked Questions

Qwen3.5 397B A17B is an open-source multimodal AI model by Alibaba Qwen, released in February 2026. It has an average benchmark score of 69.7. Context window: 262K tokens.

Benchmarks

Chatbot Arena Elo — Overall Chatbot Arena Elo — Coding OpenCompass — AIME2025 OpenCompass — IFEval OTIS Mock AIME 2024-2025

Alibaba Qwen · Provider Alibaba Qwen · Economy All Models Compare Models Pricing Developers · API Context Window · Glossary

Key facts · as of 2026-10-05

Qwen3.5 397B A17B by Alibaba Qwen. BenchGecko score 69.7, rank 38 of 312 scored models (normalized average of public benchmark scores).
List price $0.55 input · $3.50 output per 1M tokens (as of 2026-10-05).
Sold by 10 providers (as of 2026-10-05): Alibaba $0.39 in / $2.34 out · DeepInfra (fp8) $0.45 in / $3.00 out · Parasail (fp8) $0.50 in / $3.60 out · AtlasCloud (fp8) $0.55 in / $3.50 out · DigitalOcean $0.55 in / $3.50 out · and 5 more. Every provider

How to cite · data as of 2026-10-05

Qwen3.5 397B A17B · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/qwen3-5-397b-a17b

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP

Qwen3.5 397B A17B

Frequently Asked Questions

Related Models

Benchmarks

Related Pages

Key facts · as of 2026-10-05

How to cite · data as of 2026-10-05