Qwen2.5-Plus
General language model Generally availableAlibaba Cloud's hosted flagship language model providing a 128k context window, advanced reasoning, and enterprise API capabilities.
Overview
Qwen2.5-Plus is a proprietary hosted language model in Alibaba Cloud's Qwen2.5 family, introduced in September 2024. Designed as a high-performance general-purpose AI tier, Qwen2.5-Plus rivals leading global commercial models across language processing, complex instruction following, code generation, and tabular data synthesis.
The model features a 131,072-token (128k) context window and supports up to 8,192 output tokens. It is optimized for high-concurrency enterprise deployments on Alibaba Cloud Model Studio (`qwen-plus` / `qwen2.5-plus` API endpoints at $0.40 / 1M input tokens, $1.20 / 1M output tokens).
As a proprietary hosted model, parameter counts are undisclosed and local execution is not supported.
Technical Specifications
Context Window
131,072 tokens
Max Input Tokens
128,000
Max Output Tokens
8,192
Released
2024-09-19
Modalities
Text → Text (Both)
Image → Text (Input)
Text + Image → Text (Input)
Capabilities
Text Generation
Code Generation
Structured Output
Image Understanding
Function Calling
Long Context
Multilingual Support
Use Cases
Content Creation
Coding Assistance
Data Analysis
Languages
English (en)
Chinese (zh)
Japanese (ja)
Korean (ko)
Access Routes
| Route | Type | Protocol | Region / Scope | Provider | Status |
|---|---|---|---|---|---|
| Alibaba Cloud | Hosted API (Direct provider) | OpenAI-compatible REST API | Global | Alibaba Cloud | Available |
Identifiers
- qwen2.5-plus Canonical identifier Default
- qwen-plus Canonical identifier Default