Qwen3.5 122B-A10B

The Qwen3.5 122B-A10B 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. In terms of overall performance, this model is second only to Qwen3.5-397B-A17B. Its text capabilities significantly outperform those of Qwen3-235B-2507, and its visual capabilities surpass those of Qwen3-VL-235B.

alibaba/qwen3.5-122b-a10b

Organization: Alibaba
Family: qwen
Providers: 18
Context: 262,144
Output limit: 65,536
Knowledge: —
Release: 2026-02-23
Updated: 2026-02-23
Weights: Open
Input: text, image, video, audio
Output: text
Capabilities: Tools, Reasoning, Structured, Temperature

Providers

Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.

24 offers · USD per million tokens

Provider	Model ID	Context	Output	Input / output · 1M	Reasoning	Tools	Structured	Details
AIHubMix	qwen3.5-122b-a10b	262,144	65,536	$0.1126 / $0.9008	Yes	Yes	Yes	View
Cortecs	qwen3.5-122b-a10b	262,144	262,144	$0.495 / $3.46	Yes	Yes	—	View
Deep Infra	Qwen/Qwen3.5-122B-A10B	262,144	65,536	$0.29 / $2.40	Yes	Yes	Yes	View
DevPass (LLM Gateway)	qwen3.5-122b-a10b	262,144	65,536	$0.40 / $3.20	Yes	Yes	Yes	View
EmpirioLabs AI	qwen3-5-122b-a10b	256,000	64,000	$0.115 / $0.917	Yes	Yes	Yes	View
Hugging Face	Qwen/Qwen3.5-122B-A10B	262,144	65,536	$0.40 / $3.20	Yes	Yes	Yes	View
Infomaniak	Qwen/Qwen3.5-122B-A10B-FP8	200,000	65,536	$0.50 / $3.97	Yes	Yes	Yes	View
Jalapeno Cloud	Qwen3.5-122B-A10B	262,144	65,536	$0.40 / $3.20	Yes	Yes	Yes	View
Kilo Gateway	qwen/qwen3.5-122b-a10b	262,144	65,536	$0.26 / $2.08	Yes	Yes	Yes	View
LLM Gateway	novita/qwen3.5-122b-a10b	262,144	65,536	$0.40 / $3.20	Yes	Yes	No	View
LLM Gateway	alibaba/qwen3.5-122b-a10b	262,144	65,536	$0.40 / $3.20	Yes	Yes	No	View
Merge Gateway	qwen/qwen3.5-122b-a10b	131,072	32,768	$0.115 / $0.917	Yes	Yes	Yes	View
NanoGPT	qwen/qwen3.5-122b-a10b:thinking	131,072	32,768	$0.437 / $3.496	Yes	Yes	Yes	View
NanoGPT	qwen/qwen3.5-122b-a10b	131,072	32,768	$0.437 / $3.496	No	Yes	Yes	View
Neon	qwen35-122b-a10b	262,144	25,000	$0.22 / $2.20	Yes	Yes	Yes	View
Ofox	qwen/qwen3.5-122b-a10b	256,000	64,000	$0.29 / $2.29	Yes	Yes	Yes	View
Ofox	bailian/qwen3.5-122b-a10b	256,000	64,000	$0.29 / $2.29	Yes	Yes	Yes	View
Alibabavia OpenRouter	qwen/qwen3.5-122b-a10b unknown	262,144	65,536	$0.26 / $2.08	Yes	Yes	Yes	View
AtlasCloudvia OpenRouter	qwen/qwen3.5-122b-a10b fp8	262,144	65,536	$0.30 / $2.40	Yes	Yes	Yes	View
Novitavia OpenRouter	qwen/qwen3.5-122b-a10b bf16	262,144	65,536	$0.40 / $3.20	Yes	Yes	No	View
SiliconFlowvia OpenRouter	qwen/qwen3.5-122b-a10b fp8	262,144	235,929	$0.26 / $2.08	Yes	No	Yes	View
OrcaRouter	qwen/qwen3.5-122b-a10b	262,144	65,536	$0.115 / $0.917	Yes	Yes	Yes	View
SiliconFlow	Qwen/Qwen3.5-122B-A10B	262,144	262,144	$0.26 / $2.08	No	Yes	Yes	View
TensorX	qwen/qwen3.5-122b-a10b	262,144	262,144	$0.50 / $3.50	Yes	Yes	Yes	View

Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.

Pricing

Compare token rates and cache charges across available routes and hosting configurations.

USD per million tokens

Input from$0.1126Per 1M input tokens

Output from$0.9008Per 1M output tokens

Available offers24Across 18 providers

Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.

Endpoint price comparisonLatest observed snapshot · 4 lowest-priced configurations

InputOutput

Alibabaalibaba

$0.26$2.08

SiliconFlowsiliconflow/fp8

$0.26$2.08

AtlasCloudatlas-cloud/fp8

$0.30$2.40

Novitanovita/bf16

$0.40$3.20

qwen/qwen3.5-122b-a10bObserved Oct 4, 2026, 11:31 AM UTC

Input: $0.26
Output: $2.08

Hosting prices through OpenRouter All endpoints and cache rates

Endpoint	Input / 1M	Output / 1M	Cache read / 1M	Cache write / 1M
Alibabaalibaba	$0.26	$2.08	—	—
AtlasCloudatlas-cloud/fp8	$0.30	$2.40	$0.30	—
Novitanovita/bf16	$0.40	$3.20	—	—
SiliconFlowsiliconflow/fp8	$0.26	$2.08	—	—

Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.

Performance

Review reported latency and output-throughput percentiles from the latest observed rolling window.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 4 endpoints

P50P75P90P99

Alibabaalibaba

492–4,264.16 ms

AtlasCloudatlas-cloud/fp8

970–9,662.1 ms

Novitanovita/bf16

907–1,768.1 ms

SiliconFlowsiliconflow/fp8

1,151–4,364.99 ms

All latency percentiles 4 endpoints

Endpoint	P50	P75	P90	P99
Alibabaalibaba	492 ms	661.5 ms	1,151.6 ms	4,264.16 ms
AtlasCloudatlas-cloud/fp8	970 ms	1,292 ms	6,539.8 ms	9,662.1 ms
Novitanovita/bf16	907 ms	1,021 ms	1,248.1 ms	1,768.1 ms
SiliconFlowsiliconflow/fp8	1,151 ms	1,207.25 ms	1,309 ms	4,364.99 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 4 endpoints

P50P75P90P99

Alibabaalibaba

82–144 t/s

AtlasCloudatlas-cloud/fp8

49–98 t/s

Novitanovita/bf16

54–142.08 t/s

SiliconFlowsiliconflow/fp8

32–60 t/s

All throughput percentiles 4 endpoints

Endpoint	P50	P75	P90	P99
Alibabaalibaba	82 t/s	98.5 t/s	118 t/s	144 t/s
AtlasCloudatlas-cloud/fp8	49 t/s	56 t/s	66 t/s	98 t/s
Novitanovita/bf16	54 t/s	69 t/s	95 t/s	142.08 t/s
SiliconFlowsiliconflow/fp8	32 t/s	38 t/s	45 t/s	60 t/s

Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.

Uptime

Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.

Successful requests by window

Availability by endpointCurrent overlapping windows · 4 endpoints

Endpoint5 minutes30 minutes24 hours

AlibabaalibabaObserved Oct 4, 2026, 11:31 AM UTC

100%

99.95%

99.6%

AtlasCloudatlas-cloud/fp8Observed Oct 4, 2026, 11:31 AM UTC

100%

99.77%

94.67%

Novitanovita/bf16Observed Oct 4, 2026, 11:31 AM UTC

100%

98.58%

SiliconFlowsiliconflow/fp8Observed Oct 4, 2026, 11:31 AM UTC

100%

86.77%

Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.

Benchmarks

Review attributed evaluation results on each source's original scale.

External evaluations

qwen/qwen3.5-122b-a10bObserved Oct 4, 2026, 11:31 AM UTC

Benchmark profileArtificial Analysis · shared source scale from 0 to 50

Coding

45.7

Agentic

7.6

Intelligence

15.6

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better

tau bench verified airlineQwen: Qwen3.5-122B-A10B

76.061%

gpqa diamondQwen: Qwen3.5-122B-A10B

83.319%

Evaluation	Configuration	Source	Results	Details
tau bench verified airline	Qwen: Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10b-20260224	OpenRouter	76.061%	Details
Composite indices	Qwen3.5 122B A10B (Reasoning)qwen/qwen3.5-122b-a10b-20260224	Artificial Analysis	Intelligence 15.6 · Coding 45.7 · Agentic 7.6	Details
gpqa diamond	Qwen: Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10b-20260224	OpenRouter	83.319%	Details

Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.

Technical details & API

Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.

Current route specifications

qwen/qwen3.5-122b-a10bObserved Oct 4, 2026, 11:31 AM UTC

Context: 262,144
Maximum output: 65,536
Tokenizer: Qwen3
Input: text, image, video
Output: text
Moderation: No
Added to OpenRouter: 2026-02-25

Base URLhttps://openrouter.ai/api/v1

Model IDqwen/qwen3.5-122b-a10b

Version IDqwen/qwen3.5-122b-a10b-20260224

Weights IDQwen/Qwen3.5-122B-A10B

Reasoning

Required: No
Enabled by default: Not reported
Default effort: —
Supported efforts: —

Supported parameters

frequency_penalty
include_reasoning
logit_bias
logprobs
max_tokens
min_p
presence_penalty
reasoning
repetition_penalty
response_format
seed
stop
structured_outputs
temperature
tool_choice
tools
top_k
top_logprobs
top_p

Default parameters

top k: 20
top p: 0.95
temperature: 0.6

Frequently asked questions

Answers based on the model metadata and serving offers currently in the catalog.

How much does Qwen3.5 122B-A10B cost?

Listed rates start at $0.1126 per million input tokens and $0.9008 per million output tokens. Prices vary by provider and configuration; see Pricing for details.

Which providers offer Qwen3.5 122B-A10B?

There are 24 cataloged offers across 18 providers. Compare model IDs, prices and limits in Providers.

What is the context window?

The cataloged model context is 262,144 tokens. Each serving endpoint may apply a different limit.

Does it support tools and structured output?

Tool calling: Yes. Structured output: Yes. Support can vary by endpoint.

Resources

Hugging Face ↗

Catalog history · 2 recorded revisions

Metadata observations since this model was first cataloged. These are not model release versions.

Sep 14, 2026 · 7cc0c1b18ed5
Sep 12, 2026 · 76b9fbfff120