Skip to content
RankShark

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 spa

ModelOpen sourceby Qwensince 2026
38.0

SharkScore

#151 in Models

Why it scores 38.0

Qwen3.5-122B-A10B has a SharkScore of 38.0/100, ranked #151 of 608 in Models (updated 2026-11-19).

Each part compares Qwen3.5-122B-A10B with other listings in Models. Evidence covers 87% of the score's weight.

Adoption
31 · 30%
User reviews
no data · 25%
Maintenance
11 · 20%
Trust & transparency
80 · 15%
Momentum
no data · 10%

Paying never changes this score. How ranking works · method v2026-11-18.2

RankShark review of Qwen3.5-122B-A10B

Automated evaluation by RankShark · 18 Nov 2026 · method v1.0 · How we review

We were not paid for this review.

As of 2026-11-18, Qwen3.5-122B-A10B is a vision-language model with a 262,144-token context; OpenRouter lists rates of $0.26 per million input tokens and $2.08 per million output tokens. [E2]

A 122-billion-parameter model with 10 billion parameters activated, designed to process text, images, and video and produce text. Its model repository provides weights and configuration files. [E1][E2]

Best for

  • Developers building applications that take text, image, or video input and return text. · OpenRouter
  • Workflows that use long context; the listed context window is 262,144 tokens. · model card, OpenRouter
  • Developers seeking model weights compatible with Transformers, vLLM, SGLang, or KTransformers. · model card

Not for

  • Applications that need the model to generate audio; the listing specifies text output. · OpenRouter

Key features

  • Vision-language inputs. The vendor listing specifies text, image, and video inputs, with text output. · OpenRouter
  • Long context. The vendor states a native context length of 262,144 tokens, extensible up to 1,010,000 tokens. The OpenRouter listing reports a 262,144-token context window. · model card, OpenRouter
  • Hybrid architecture. The vendor says the model combines Gated Delta Networks with sparse Mixture-of-Experts; the model overview also describes gated attention and MoE layers. · model card
  • Parameter count. The vendor lists 122B total parameters and 10B activated parameters. · model card
  • Language coverage. The vendor says Qwen3.5 supports 201 languages and dialects. · model card
  • OpenRouter token rates. The listing reports $0.26 per million input tokens and $2.08 per million output tokens. · OpenRouter

Pros

  • Accepts text, image, and video input. · OpenRouter
  • The listed context window is 262,144 tokens. · OpenRouter
  • The repository provides model weights and configuration files under an Apache-2.0 license. · model card
  • The repository says the artifacts are compatible with Transformers, vLLM, SGLang, and KTransformers. · model card

Cons

  • The listing specifies text output only, so it does not describe audio generation. · OpenRouter
  • The evidence gives token-based rates but does not state a monthly plan price. · OpenRouter
  • No public prices found on the pages we checked.
  • No free plan or free trial stated on the pages we checked.
  • Whether customer data is used for model training is not stated on the pages we checked.

Pricing

No public prices found on the pages we checked.

Checked 18 Nov 2026

Free plan
Not stated (checked 18 Nov 2026)
Free trial
Not stated (checked 18 Nov 2026)
Trains on customer data
Not stated (checked 18 Nov 2026)
Data retention
Not stated (checked 18 Nov 2026)
Data regions
Not stated (checked 18 Nov 2026)
Data processing agreement
Not stated (checked 18 Nov 2026)
AI models used
Qwen3.5-122B-A10B · model card, OpenRouter
API
OpenRouter lists chat completions, completions, messages, and responses endpoints. · OpenRouter
SDKs
Not stated (checked 18 Nov 2026)
Webhooks
Not stated (checked 18 Nov 2026)
Platforms
Hugging Face Transformers, vLLM, SGLang, and KTransformers. · model card
Security claims
No security certification stated (checked 18 Nov 2026)

What we measured

Context window (OpenRouter listing) · now
262,144 tokens
Price per million tokens (OpenRouter listing) · now
$0.26 in, $2.08 out
Package downloads · 30 days
775,084
How we tested · sources
  • Hourly uptime and response-time checks of the product's URL.
  • Repository, release and download data from GitHub, npm, PyPI and Hugging Face where they exist.
  • We did not sign up, pay, or use the product as a customer.
  • 18 Nov 2026: Plans or prices changed on the pricing page.

Something wrong? Report an error with a public link that shows it; corrections re-run the review.

Top alternatives to Qwen3.5-122B-A10B

See all
  • 67.1

    Qwen3.8 27B is an open-weight dense vision-language model from Qwen.

    ModelOpen source
  • 65.5

    Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per t

    ModelOpen source
  • 64.7

    Qwen3.8 Flash is a multimodal reasoning model from Alibaba.

    ModelOpen source
  • 64.3

    Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026.

    ModelOpen source