LogoLMSpeed
  • Home
  • Free
  • Providers
  • Docs
LogoLMSpeed
LogoLMSpeed

The best API speed test tool

GitHubGitHubTwitterX (Twitter)Email
Product
  • Features
  • Pricing
  • FAQ
Leaderboard
  • Overview
  • Speed Ranking
  • Latency Ranking
  • Health Ranking
Models
  • All Models
  • GPT
  • Claude
  • Gemini
  • DeepSeek
  • Llama
  • Qwen
Free Models
  • All Free Models
  • Free GPT
  • Free Claude
  • Free Gemini
  • Free DeepSeek
  • Free Llama
  • Free Qwen
Resources
  • Speed Test
  • Provider Directory
  • Documentation
Legal
  • Cookie Policy
  • Privacy Policy
  • Terms of Service
© 2026 LMSpeed All Rights Reserved.Made by Nexmoe with ❤️
首页交流 QQ 群:1034193296,欢迎中转站站长加入讨论 AI 最热话题、newapi、openclaw 等,获取最新测速动态与反馈支持。
阿里云百炼 DashScope logo

阿里云百炼 DashScope

Alibaba Cloud DashScope provides AI model APIs including Qwen LLMs, vision, audio, and embedding models.

Categories

官方 API
QwenQwen3.0QwenQwen3.1QwenQwen3.5 FlashQwenQwen3 Next InstructQwenQwen2.5 Instruct 1mQwenDeepSeek R1 Distill QwenQwenQwen3MinimaxMiniMax-M2.5QwenDeepSeek R1 Distill Qwen 1 5bQwenQwen2.5 Coder 0 5b InstructQwenQwen1.5QwenQwen3 Coder PlusChatGLMGLM-4.7QwenQwen3 ThinkingQwenQwen2.5 InstructDeepSeekDeepSeek V3.1ChatGLMGLM-4.5 AirQwenQwen3.6 PlusMoonshotAIKimi K2.5QwenQwen3 MaxQwenQwen3.5 PlusQwenQwen3 InstructDeepSeekDeepSeek V3QwenQwen3 VL InstructQwenQwen2.5 Coder InstructChatGLMGLM-5MoonshotAIKimi K2 ThinkingMinimaxMiniMax-M2.7DeepSeekDeepSeek V3.2DeepSeekDeepSeek R1MetaAIDeepSeek R1 Distill Llama

阿里云百炼 DashScope offers 66 LLM API models.

Speed benchmark average: 74 tok/s.

阿里云百炼 DashScope interface preview
Avg Speed74.02 tok/s
Latency5.78 s
Total Tests842
Models66
Updated4/16/2026
Created At8/13/2025
Website

API Endpoints

  • Historical / Unverified
    https://www.aliyun.com
  • Historical / Unverified
    https://dashscope.aliyuncs.com
  • Historical / Unverified
    https://coding.dashscope.aliyuncs.com

Supported Models

ModelSpeedLatencyTests
Qwenqwen-mt-turbo
4366.57 tok/s
0.60s
3
Qwenqwen3-0.6b
171.78 tok/s
2.49s
10
Qwenqwen3-vl-flash
147.58 tok/s
1.00s
5
Qwenqwen3-coder-next
147.13 tok/s
0.97s
5
Qwenqwen3-1.7b
140.08 tok/s
4.85s
10
Qwenqwen-flash
128.53 tok/s
0.63s
20
Qwenqwen3.5-flash
125.19 tok/s
7.31s
20
Qwenqwen3-next-80b-a3b-instruct
125.04 tok/s
3.99s
5
Qwenqwen-vl-plus-2025-07-10
112.44 tok/s
0.56s
65
Qwenqwen-vl-plus-2025-05-07
99.19 tok/s
0.88s
5
Qwenqwen2.5-7b-instruct-1m
92.57 tok/s
0.93s
10
Qwendeepseek-r1-distill-qwen-7b
92.17 tok/s
9.98s
5
Qwenqwen-flash-2025-07-28
91.82 tok/s
1.48s
5
Yitongyi-intent-detect-v3
87.54 tok/s
0.72s
10
Qwenqwen3-8b
80.48 tok/s
8.67s
10
MinimaxMiniMax-M2.5
76.33 tok/s
5.71s
10
Qwendeepseek-r1-distill-qwen-1.5b
73.65 tok/s
6.13s
5
Qwenqwen-vl-plus
69.83 tok/s
1.00s
15
Yitongyi-xiaomi-analysis-pro
65.76 tok/s
0.64s
5
Qwenqwen2.5-coder-0.5b-instruct
60.38 tok/s
0.75s
5
Showing 20 of 66 models.

Leaderboard Rankings

Speed
145.6 tokens/s#17/100
Latency
1.08 s#33/100
OverviewPerformance66PricingTests842HealthEmbed