Models/Alibaba Cloud/Qwen3.5 Plus

Qwen3.5 Plus

Alibaba Cloud 🧠 Language Model

397B MoE model with 17B active parameters, 1M token context, multimodal (text/image/video)

Specifications

ModalitiesInput: text, image, video  ·  Output: text
Context window1000K tokens
Max output8K tokens
Speed●●●○○ Average
FeaturesTools: No Streaming: Yes Vision: Yes
Capabilitiesreasoning

Pricing

$0.2013 / 1M input tokens  ·  $1.20 / 1M output tokens

Platform credit pricing — live rates on the Models page.

Use Qwen3.5 Plus on Zubnet →

More from Alibaba Cloud

Q
Qwen Flash
Ultra-fast model with 1M context. Best latency and cost efficiency for simple tasks.
🧠 Language Model
Q
Qwen Plus
Balanced flagship model with 1M context. Best performance/cost ratio for most tasks.
🧠 Language Model
Q
Qwen3 Max
Flagship 1T+ parameter model. State-of-the-art reasoning, coding, and agent capabilities.
🧠 Language Model
Q
Qwen VL Max
Premium vision-language model with 131K context. Best visual understanding and reasoning.
🧠 Language Model