Using Qwen3-Coder-Flash on Alibaba Cloud PAI-EAS
Implementation guide · Qwen3-Coder · Alibaba
Alibaba Cloud PAI-EAS exposes Qwen3-Coder-Flash through model ID qwen3-coder-flash. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-06-19. Next refresh: weekly.
Quick Start
- 1
- 2Use the Alibaba Cloud PAI-EAS SDK or REST API to call
qwen3-coder-flash— see the documentation for request format. - 3
Code Examples
Pricing on Alibaba Cloud PAI-EAS
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.30 |
| Output tokens | $1.50 |
Capabilities
About Qwen3-Coder-Flash
Qwen3-Coder-Flash is Alibaba's fast API-only code generation model in the Qwen3-Coder family, released July 28, 2025 via DashScope (Alibaba Cloud Model Studio). It is not an open-weight model. Supports 1 million token context with up to 65,536 output tokens. Inherits Qwen3-Coder-Plus capabilities with support for multi-turn tool interaction, optimized for repository-level understanding, and enhanced tool-calling stability at lower cost. Pricing is tiered by context length: input $0.30-$1.60 per 1M tokens, output $1.50-$9.60 per 1M tokens. Available via DashScope API (qwen3-coder-flash or versioned alias qwen3-coder-flash-2025-07-28) and Vercel AI Gateway (alibaba/qwen3-coder-flash coming soon).