How accurate is Qwen3.5 397B A17B?

Qwen3.5 397B A17B answered 26 of 80 questions correctly (32.5%) in our 2026-10-27 run, ranking #62 of 78 models.

How fast is Qwen3.5 397B A17B?

Qwen3.5 397B A17B generated a median of 240 output tokens per second in our 2026-10-27 run, ranking #5 of 78. Median time to first token was 0.6 s.

What is the latency of Qwen3.5 397B A17B?

Qwen3.5 397B A17B had a median time to first token of 0.6 s in our 2026-10-27 run, ranking #27 of 78 models.

How much does Qwen3.5 397B A17B cost?

Qwen3.5 397B A17B cost $0.013 per question on average as billed in our 2026-10-27 run, reasoning tokens included.

What is Qwen3.5 397B A17B API pricing?

Qwen3.5 397B A17B is listed at $0.5 per million input tokens and $3.6 per million output tokens on OpenRouter.

What is the context window of Qwen3.5 397B A17B?

Qwen3.5 397B A17B accepts up to 262,144 tokens of context, according to OpenRouter's model catalogue.

Is Qwen3.5 397B A17B open source?

Yes. Qwen3.5 397B A17B is an open-weights model: Qwen publishes the weights, so you can run it yourself as well as through an API.

Who makes Qwen3.5 397B A17B?

Qwen3.5 397B A17B is made by Qwen. We tested it through OpenRouter using the model ID qwen/qwen3.5-397b-a17b.

Where can I use Qwen3.5 397B A17B via API?

Through OpenRouter, Qwen3.5 397B A17B is served by 8 hosts: Alibaba, AtlasCloud, DeepInfra, GMICloud, Novita, Parasail, Phala, StreamLake.

QwenOpen weightsReleased 16 Feb 2026

Qwen3.5 397B A17B benchmarks, speed and API pricing

Reviewed by LLM Verifications team · Tested 27 Oct 2026

Compare

Available through OpenRouter on

Alibaba$0.39 in · $2.34 out
DeepInfra$0.45 in · $3 out
DigitalOcean$0.55 in · $3.5 out
Phala$0.55 in · $3.5 out
AtlasCloud$0.55 in · $3.5 out
Parasail$0.5 in · $3.6 out
StreamLake$0.6 in · $3.6 out
GMICloud$0.6 in · $3.6 out
Novita$0.6 in · $3.6 out
Venice$0.75 in · $4.5 out

Intelligence32.5% correct#62 of 72

Speed240tok/s#5 of 72

Cost$0.013per question#65 of 72List $0.5 in · $3.6 out per 1M

Verbosity4,010tokens per question#72 of 72

Summary

Answers 26 of 80 verification questions correctly (32.5%), placing #62 of 72 models tested on the current suite.
Generates 240 output tokens per second, faster than 94% of the models we measure.
Starts responding after 0.6 s (median time to first token), including thinking time.
Costs $0.013 per question as billed, #24 cheapest of 31 models priced over $1 per 1M tokens.

Specifications

Reasoning: Yes
Input: text, image, video
Output: text
Context window: 262k tokens
Weights: Open weights
Knowledge cutoff: —
OpenRouter ID: qwen/qwen3.5-397b-a17b
Last tested: 27 Oct 2026

Peer group: 34 models with a blended list price over $1 per 1M tokens (3 input : 1 output). Charts below compare Qwen3.5 397B A17B with all models; cost and speed charts focus on this peer group.

Intelligence

Verification score: the share of 80 questions from open datasets answered correctly. See the benchmark datasets.

Score vs. cost per question

Qwen3.5 397B A17B circled; dashed line joins models no cheaper model beats

Score vs. end-to-end response time

Qwen3.5 397B A17B circled · accurate and quick sits top left

Score vs. tokens per question

Qwen3.5 397B A17B circled · output tokens, reasoning included

Verification score

All models tested on the current suite

61 more models · see the full leaderboard

Cost

Average cost of one question, split into input, reasoning and answer tokens at each model's list price. Reasoning tokens are billed as output.

Cost per question, by token type

Peer group: blended price over $1

Input Reasoning Answer

Cost per question, as billed

All models · lower is better

1Granite 4.0 Micro$0.000051
2gpt-oss-20b$0.000066
3Granite 4.2 8B$0.000077
4Nova Micro 1.0$0.000087
5Mercury 2.5$0.00011
6Phi 4$0.00012
7gpt-oss-120b$0.00013
8GLM 5.3 Flash$0.00015
9Ministral 3 3B 2512$0.00019
10GPT-6 Luna$0.00025
65Qwen3.5 397B A17B$0.013

61 more models · see the full leaderboard

Speed and latency

Median of 3 streamed runs of the same prompt, measured 25 Oct 2026.

Output speed

Peer group (over $1) · higher is better

19 more models · see the full leaderboard

Time to first token

Peer group (over $1) · lower is better

21 more models · see the full leaderboard

End-to-end response time

Peer group (over $1) · lower is better

21 more models · see the full leaderboard

Latency vs. output speed

Qwen3.5 397B A17B circled · quick to start and fast sits top left

Results by category

Questions answered correctly in each category

Science10/30

Engineering0/15

Medicine2/11

Economics5/9

Law1/6

Humanities & social science8/9

More from Qwen

Qwen#15Qwen3.8 Max (0902)75.0% verification score46 tok/s1.2 s first token$0.011 / question

Qwen#34Qwen3.8 27B63.8% verification score49 tok/s0.5 s first token$0.0043 / question

Qwen#36Qwen3 Coder Next62.5% verification score106 tok/s0.4 s first token$0.0017 / question

All Qwen models →

Compare Qwen3.5 397B A17B

Head to head with its closest rivals, other Qwen models and the top models overall.

Hosts and prices

Every host serving this model through OpenRouter, from OpenRouter's catalogue

Host	Input / 1M	Output / 1M	Context	Max output	Quantization
Alibaba	$0.39	$2.34	262k	66k	—
DeepInfra	$0.45	$3	262k	82k	fp8
DigitalOcean	$0.55	$3.5	131k	118k	—
Phala	$0.55	$3.5	262k	236k	—
AtlasCloud	$0.55	$3.5	262k	66k	fp8
Parasail	$0.5	$3.6	262k	236k	fp8
StreamLake	$0.6	$3.6	256k	64k	—
GMICloud	$0.6	$3.6	262k	236k	fp8
Novita	$0.6	$3.6	262k	66k	—
Venice	$0.75	$4.5	128k	33k	—

Sources

Scores, speed and billed cost are our own measurements. Prices, context window and hosts come from OpenRouter's catalogue on the test date.

Qwen3.5 397B A17B on OpenRouter: list prices and hosts
Model card on Hugging Face: weights and licence
SuperGPQA (paper): 50 of the questions, ODC-BY 1.0
MMLU-Pro (paper): 30 of the questions, MIT
OpenRouter generation records: where billed cost and native token counts come from
Our methodology and editorial standards

Qwen3.5 397B A17B: frequently asked questions

How accurate is Qwen3.5 397B A17B?: Qwen3.5 397B A17B answered 26 of 80 questions correctly (32.5%) in our 2026-10-27 run, ranking #62 of 78 models.
How fast is Qwen3.5 397B A17B?: Qwen3.5 397B A17B generated a median of 240 output tokens per second in our 2026-10-27 run, ranking #5 of 78. Median time to first token was 0.6 s.
What is the latency of Qwen3.5 397B A17B?: Qwen3.5 397B A17B had a median time to first token of 0.6 s in our 2026-10-27 run, ranking #27 of 78 models.
How much does Qwen3.5 397B A17B cost?: Qwen3.5 397B A17B cost $0.013 per question on average as billed in our 2026-10-27 run, reasoning tokens included.
What is Qwen3.5 397B A17B API pricing?: Qwen3.5 397B A17B is listed at $0.5 per million input tokens and $3.6 per million output tokens on OpenRouter.
What is the context window of Qwen3.5 397B A17B?: Qwen3.5 397B A17B accepts up to 262,144 tokens of context, according to OpenRouter's model catalogue.
Is Qwen3.5 397B A17B open source?: Yes. Qwen3.5 397B A17B is an open-weights model: Qwen publishes the weights, so you can run it yourself as well as through an API.
Who makes Qwen3.5 397B A17B?: Qwen3.5 397B A17B is made by Qwen. We tested it through OpenRouter using the model ID qwen/qwen3.5-397b-a17b.
Where can I use Qwen3.5 397B A17B via API?: Through OpenRouter, Qwen3.5 397B A17B is served by 8 hosts: Alibaba, AtlasCloud, DeepInfra, GMICloud, Novita, Parasail, Phala, StreamLake.

QwenOpen weightsReleased 16 Feb 2026

Qwen3.5 397B A17B benchmarks, speed and API pricing

Reviewed by LLM Verifications team · Tested 27 Oct 2026

Compare

Available through OpenRouter on

Alibaba$0.39 in · $2.34 out
DeepInfra$0.45 in · $3 out
DigitalOcean$0.55 in · $3.5 out
Phala$0.55 in · $3.5 out
AtlasCloud$0.55 in · $3.5 out
Parasail$0.5 in · $3.6 out
StreamLake$0.6 in · $3.6 out
GMICloud$0.6 in · $3.6 out
Novita$0.6 in · $3.6 out
Venice$0.75 in · $4.5 out

Intelligence32.5% correct#62 of 72

Speed240tok/s#5 of 72

Cost$0.013per question#65 of 72List $0.5 in · $3.6 out per 1M

Verbosity4,010tokens per question#72 of 72

Summary

Answers 26 of 80 verification questions correctly (32.5%), placing #62 of 72 models tested on the current suite.
Generates 240 output tokens per second, faster than 94% of the models we measure.
Starts responding after 0.6 s (median time to first token), including thinking time.
Costs $0.013 per question as billed, #24 cheapest of 31 models priced over $1 per 1M tokens.

Specifications

Reasoning: Yes
Input: text, image, video
Output: text
Context window: 262k tokens
Weights: Open weights
Knowledge cutoff: —
OpenRouter ID: qwen/qwen3.5-397b-a17b
Last tested: 27 Oct 2026

Peer group: 34 models with a blended list price over $1 per 1M tokens (3 input : 1 output). Charts below compare Qwen3.5 397B A17B with all models; cost and speed charts focus on this peer group.

Intelligence

Verification score: the share of 80 questions from open datasets answered correctly. See the benchmark datasets.

Score vs. cost per question

Qwen3.5 397B A17B circled; dashed line joins models no cheaper model beats

Score vs. end-to-end response time

Qwen3.5 397B A17B circled · accurate and quick sits top left

Score vs. tokens per question

Qwen3.5 397B A17B circled · output tokens, reasoning included

Verification score

All models tested on the current suite

61 more models · see the full leaderboard

Cost

Average cost of one question, split into input, reasoning and answer tokens at each model's list price. Reasoning tokens are billed as output.

Cost per question, by token type

Peer group: blended price over $1

Input Reasoning Answer

Cost per question, as billed

All models · lower is better

1Granite 4.0 Micro$0.000051
2gpt-oss-20b$0.000066
3Granite 4.2 8B$0.000077
4Nova Micro 1.0$0.000087
5Mercury 2.5$0.00011
6Phi 4$0.00012
7gpt-oss-120b$0.00013
8GLM 5.3 Flash$0.00015
9Ministral 3 3B 2512$0.00019
10GPT-6 Luna$0.00025
65Qwen3.5 397B A17B$0.013

61 more models · see the full leaderboard

Speed and latency

Median of 3 streamed runs of the same prompt, measured 25 Oct 2026.

Output speed

Peer group (over $1) · higher is better

19 more models · see the full leaderboard

Time to first token

Peer group (over $1) · lower is better

21 more models · see the full leaderboard

End-to-end response time

Peer group (over $1) · lower is better

21 more models · see the full leaderboard

Latency vs. output speed

Qwen3.5 397B A17B circled · quick to start and fast sits top left

Results by category

Questions answered correctly in each category

Science10/30

Engineering0/15

Medicine2/11

Economics5/9

Law1/6

Humanities & social science8/9

More from Qwen

Qwen#15Qwen3.8 Max (0902)75.0% verification score46 tok/s1.2 s first token$0.011 / question

Qwen#34Qwen3.8 27B63.8% verification score49 tok/s0.5 s first token$0.0043 / question

Qwen#36Qwen3 Coder Next62.5% verification score106 tok/s0.4 s first token$0.0017 / question

All Qwen models →

Compare Qwen3.5 397B A17B

Head to head with its closest rivals, other Qwen models and the top models overall.

Hosts and prices

Every host serving this model through OpenRouter, from OpenRouter's catalogue

Host	Input / 1M	Output / 1M	Context	Max output	Quantization
Alibaba	$0.39	$2.34	262k	66k	—
DeepInfra	$0.45	$3	262k	82k	fp8
DigitalOcean	$0.55	$3.5	131k	118k	—
Phala	$0.55	$3.5	262k	236k	—
AtlasCloud	$0.55	$3.5	262k	66k	fp8
Parasail	$0.5	$3.6	262k	236k	fp8
StreamLake	$0.6	$3.6	256k	64k	—
GMICloud	$0.6	$3.6	262k	236k	fp8
Novita	$0.6	$3.6	262k	66k	—
Venice	$0.75	$4.5	128k	33k	—

Sources

Scores, speed and billed cost are our own measurements. Prices, context window and hosts come from OpenRouter's catalogue on the test date.

Qwen3.5 397B A17B on OpenRouter: list prices and hosts
Model card on Hugging Face: weights and licence
SuperGPQA (paper): 50 of the questions, ODC-BY 1.0
MMLU-Pro (paper): 30 of the questions, MIT
OpenRouter generation records: where billed cost and native token counts come from
Our methodology and editorial standards

Qwen3.5 397B A17B: frequently asked questions

How accurate is Qwen3.5 397B A17B?: Qwen3.5 397B A17B answered 26 of 80 questions correctly (32.5%) in our 2026-10-27 run, ranking #62 of 78 models.
How fast is Qwen3.5 397B A17B?: Qwen3.5 397B A17B generated a median of 240 output tokens per second in our 2026-10-27 run, ranking #5 of 78. Median time to first token was 0.6 s.
What is the latency of Qwen3.5 397B A17B?: Qwen3.5 397B A17B had a median time to first token of 0.6 s in our 2026-10-27 run, ranking #27 of 78 models.
How much does Qwen3.5 397B A17B cost?: Qwen3.5 397B A17B cost $0.013 per question on average as billed in our 2026-10-27 run, reasoning tokens included.
What is Qwen3.5 397B A17B API pricing?: Qwen3.5 397B A17B is listed at $0.5 per million input tokens and $3.6 per million output tokens on OpenRouter.
What is the context window of Qwen3.5 397B A17B?: Qwen3.5 397B A17B accepts up to 262,144 tokens of context, according to OpenRouter's model catalogue.
Is Qwen3.5 397B A17B open source?: Yes. Qwen3.5 397B A17B is an open-weights model: Qwen publishes the weights, so you can run it yourself as well as through an API.
Who makes Qwen3.5 397B A17B?: Qwen3.5 397B A17B is made by Qwen. We tested it through OpenRouter using the model ID qwen/qwen3.5-397b-a17b.
Where can I use Qwen3.5 397B A17B via API?: Through OpenRouter, Qwen3.5 397B A17B is served by 8 hosts: Alibaba, AtlasCloud, DeepInfra, GMICloud, Novita, Parasail, Phala, StreamLake.