DashScope提供AI模型和API，主要用于自然语言处理和计算机视觉应用。
DashScope提供一系列AI模型和API，主要专注于自然语言处理和计算机视觉任务。核心能力包括文本生成、图像分析和多模态理解。该平台以与阿里云服务的集成而闻名，为开发者和企业提供可扩展的解决方案。典型用例涉及聊天机器人、内容创作和自动化图像处理。可用内容中未提供具体模型、端点、延迟、速度或定价的详细信息。
Performance Stats
Avg Speed
131.72t/s
Latency
7.61s
Total Tests
387
Models
59
About DashScope
Supported Models
| Model | Speed | Latency | Tests |
|---|---|---|---|
| qwen-mt-turbo | 5403.35 t/s | 1.02s | 5 |
| qwen3-0.6b | 252.65 t/s | 2.49s | 10 |
| qwen3-1.7b | 155.43 t/s | 4.85s | 10 |
| qwen3-next-80b-a3b-instruct | 153.69 t/s | 3.99s | 5 |
| qwen3-next-80b-a3b-instruct | 153.69 t/s | 3.99s | 5 |
| qwen3-vl-flash | 147.58 t/s | 1.00s | 5 |
| qwen3-vl-flash | 147.58 t/s | 1.00s | 5 |
| deepseek-r1-distill-qwen-1.5b | 135.25 t/s | 6.13s | 5 |
| qwen-flash | 102.36 t/s | 1.04s | 5 |
| qwen2.5-7b-instruct-1m | 92.57 t/s | 0.93s | 10 |
| qwen2.5-7b-instruct-1m | 92.57 t/s | 0.93s | 10 |
| deepseek-r1-distill-qwen-7b | 92.17 t/s | 9.98s | 5 |
| qwen-flash-2025-07-28 | 91.82 t/s | 1.48s | 5 |
| tongyi-intent-detect-v3 | 91.73 t/s | 0.86s | 5 |
| qwen3-8b | 91.25 t/s | 8.67s | 10 |
| qwen-vl-plus | 69.83 t/s | 1.00s | 15 |
| qwen2.5-coder-0.5b-instruct | 60.38 t/s | 0.75s | 5 |
| qwen2.5-coder-0.5b-instruct | 60.38 t/s | 0.75s | 5 |
| qwen2.5-coder-0.5b-instruct | 60.38 t/s | 0.75s | 5 |
| qwen1.5-7b-chat | 59.96 t/s | 0.89s | 10 |
| qwen-turbo-latest | 59.77 t/s | 1.00s | 15 |
| qwen3-30b-a3b | 55.50 t/s | 12.29s | 15 |
| qwen3-coder-plus | 54.19 t/s | 1.08s | 10 |
| qwen3-coder-plus | 54.19 t/s | 1.08s | 10 |
| qwen-coder-plus-latest | 53.02 t/s | 0.96s | 5 |
| qwen2.5-14b-instruct-1m | 51.72 t/s | 1.37s | 5 |
| qwen2.5-14b-instruct-1m | 51.72 t/s | 1.37s | 5 |
| qwen-14b-chat | 50.69 t/s | 0.90s | 5 |
| qwen2.5-14b-instruct | 49.95 t/s | 0.96s | 5 |
| qwen2.5-14b-instruct | 49.95 t/s | 0.96s | 5 |
| deepseek-v3.1 | 49.55 t/s | 1.34s | 15 |
| deepseek-v3.1 | 49.55 t/s | 1.34s | 15 |
| glm-4.5-air | 48.65 t/s | 13.21s | 10 |
| glm-4.5-air | 48.65 t/s | 13.21s | 10 |
| qwen3-vl-235b-a22b-instruct | 41.54 t/s | 3.23s | 5 |
| qwen3-vl-235b-a22b-instruct | 41.54 t/s | 3.23s | 5 |
| qwen2.5-coder-3b-instruct | 38.45 t/s | 1.00s | 5 |
| qwen2.5-coder-3b-instruct | 38.45 t/s | 1.00s | 5 |
| qwen2.5-coder-3b-instruct | 38.45 t/s | 1.00s | 5 |
| qwq-32b | 38.05 t/s | 17.85s | 5 |
| qwen3-235b-a22b | 37.79 t/s | 21.21s | 25 |
| qwen3-235b-a22b-thinking-2507 | 37.24 t/s | 18.95s | 10 |
| deepseek-r1-distill-qwen-32b | 35.81 t/s | 86.57s | 5 |
| qwen-plus | 30.71 t/s | 0.93s | 20 |
| qwen-plus-latest | 29.51 t/s | 0.92s | 25 |
| qwen2.5-72b-instruct | 28.17 t/s | 0.97s | 5 |
| qwen2.5-72b-instruct | 28.17 t/s | 0.97s | 5 |
| qwen2.5-coder-32b-instruct | 28.02 t/s | 1.02s | 5 |
| qwen2.5-coder-32b-instruct | 28.02 t/s | 1.02s | 5 |
| qwen2.5-coder-32b-instruct | 28.02 t/s | 1.02s | 5 |
| deepseek-r1-distill-llama-70b | 27.80 t/s | 23.28s | 15 |
| qwen-vl-max | 26.48 t/s | 1.12s | 5 |
| qwen3-235b-a22b-instruct-2507 | 24.80 t/s | 1.15s | 5 |
| qwen3-max-2025-09-23 | 24.49 t/s | 1.14s | 5 |
| qwen-max | 24.47 t/s | 0.98s | 10 |
| kimi-k2-thinking | 23.73 t/s | 17.54s | 5 |
| qwen-max-latest | 22.05 t/s | 1.21s | 10 |
| qwen-max-0428 | 16.86 t/s | 0.97s | 5 |
| deepseek-r1 | 13.61 t/s | 62.81s | 5 |
Recent Test Records
| Time | Model | Speed | Latency |
|---|---|---|---|
| Dec 9, 06:45 AM | Unknown | - | -s |
| Nov 26, 01:15 AM | kimi-k2-thinking | 23.73 t/s | 17.54s |
| Nov 26, 01:10 AM | qwen-mt-turbo | 5403.35 t/s | 1.02s |
| Nov 21, 02:51 AM | qwen3-1.7b | 175.64 t/s | 4.38s |
| Nov 21, 02:50 AM | qwen3-0.6b | 243.65 t/s | 2.38s |
| Oct 17, 06:48 AM | qwen3-max-2025-09-23 | 24.49 t/s | 1.14s |
| Oct 17, 06:44 AM | qwen3-vl-235b-a22b-instruct | 41.54 t/s | 3.23s |
| Oct 17, 06:41 AM | deepseek-v3.1 | 45.16 t/s | 1.42s |
| Oct 17, 06:33 AM | qwen3-next-80b-a3b-instruct | 153.69 t/s | 3.99s |
| Oct 17, 06:31 AM | qwen3-235b-a22b-instruct-2507 | 24.80 t/s | 1.15s |