LLM Reference
Alibaba Cloud PAI-EAS

Using Qwen3.5-397B-A17B on Alibaba Cloud PAI-EAS

Implementation guide · Qwen3.5 · Alibaba

ServerlessOpen Source

Alibaba Cloud PAI-EAS exposes Qwen3.5-397B-A17B through model ID qwen3.5-397b-a17b. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-04. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Alibaba Cloud PAI-EAS and generate an API key.
  2. 2
    Use the Alibaba Cloud PAI-EAS SDK or REST API to call qwen3.5-397b-a17b — see the documentation for request format.
  3. 3
    You'll be billed $0.39/1M input, $2.34/1M output tokens. See full pricing.

Code Examples

See Alibaba Cloud PAI-EAS documentation for integration details.

Pricing on Alibaba Cloud PAI-EAS

TypePrice (per 1M)
Input tokens$0.39
Output tokens$2.34

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured Outputs

About Qwen3.5-397B-A17B

Alibaba's largest Qwen3.5 model, featuring a Mixture-of-Experts architecture with 397B total parameters and 17B active per token (using 512 total experts with 10 routed + 1 shared active). Supports 201 languages with a native 262K token context window extensible to 1M tokens via YaRN. Includes a thinking/reasoning mode, tool calling with MCP integration, and unified vision-language capabilities through early fusion training.

Model Specs

Released2026-02-16
Parameters397B
Context262k
ArchitectureMixture of Experts

Provider

Alibaba Cloud PAI-EAS
Alibaba Cloud PAI-EAS

Alibaba Cloud

Hangzhou, Zhejiang, China