LLM Reference
Alibaba Cloud PAI-EAS

Using Qwen3.8-Omni-Flash on Alibaba Cloud PAI-EAS

Implementation guide · Qwen3.8 · Alibaba

Serverless

Alibaba Cloud PAI-EAS exposes Qwen3.8-Omni-Flash through model ID qwen3.8-omni-flash. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-09-17. 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 qwen3.8-omni-flash — see the documentation for request format.
  3. 3
    You'll be billed $0.15/1M input, $0.47/1M 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$0.15
Output tokens$0.47

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured OutputsPrompt CachingAudio

About Qwen3.8-Omni-Flash

Qwen3.8-Omni-Flash is Alibaba Qwen's first omni-modal model built around agentic capabilities, announced 2026-09-18 (MCP-verified @Alibaba_Qwen tip 2100785962414702599 + first-party QwenCloud / Model Studio Qwen-Omni docs). Native text, image, audio, and video input with text-only output (do not set audio modalities). 1M-token context; QwenCloud lists max input 991K / max output 131K (thinking: max input 983K / max output 131K / max reasoning 262K). Tip + QwenCloud: audio-video understanding with reasoning and tool use for agentic workflows (vlog auto-edit, short-video translate, movie recaps); two-/four-channel spatial audio; DashScope + OpenAI-compatible protocols; companion open-source Qwen-MM-Plugins (Qwen-Live Harness coming soon).

Model Specs

Released2026-09-18
Context1m

Provider

Alibaba Cloud PAI-EAS
Alibaba Cloud PAI-EAS

Alibaba Cloud

Hangzhou, Zhejiang, China