Cerebrasapi.cerebras.ai |
| llama-3.3-70b |
0.25 s 最佳: 0.15最差: 0.32 |
1532.55t/s |
| 5 |
| 4 | Hugging Facerouter.huggingface.co | meta-llama/Llama-3.3-70B-Instruct | 0.26 s 最佳: 0.24最差: 0.28 | 416.19t/s | 5 |
| 5 | Hugging Facerouter.huggingface.co | meta-llama/Llama-3.3-70B-Instruct | 0.26 s 最佳: 0.24最差: 0.28 | 416.19t/s | 5 |
| 6 | Mistral AIapi.mistral.ai | mistral-small-latest | 0.33 s 最佳: 0.30最差: 0.37 | 74.79t/s | 5 |
| 7 | Mistral AIapi.mistral.ai | mistral-small-latest | 0.33 s 最佳: 0.30最差: 0.37 | 74.79t/s | 5 |
| 8 | Mistral AIapi.mistral.ai | mistral-medium | 0.35 s 最佳: 0.32最差: 0.37 | 99.70t/s | 5 |
| 9 | Mistral AIapi.mistral.ai | mistral-medium | 0.35 s 最佳: 0.32最差: 0.37 | 99.70t/s | 5 |
| 10 | Mistral AIapi.mistral.ai | mistral-medium-latest | 0.37 s 最佳: 0.34最差: 0.43 | 101.94t/s | 5 |
| 11 | Mistral AIapi.mistral.ai | mistral-medium-latest | 0.37 s 最佳: 0.34最差: 0.43 | 101.94t/s | 5 |
| 12 | Mistral AIapi.mistral.ai | mistral-tiny-latest | 0.38 s 最佳: 0.36最差: 0.42 | 155.43t/s | 5 |
| 13 | Mistral AIapi.mistral.ai | mistral-tiny-latest | 0.38 s 最佳: 0.36最差: 0.42 | 155.43t/s | 5 |
| 14 | Mistral AIapi.mistral.ai | magistral-small-latest | 0.39 s 最佳: 0.33最差: 0.56 | 189.91t/s | 5 |
| 15 | Mistral AIapi.mistral.ai | magistral-small-latest | 0.39 s 最佳: 0.33最差: 0.56 | 189.91t/s | 5 |
| 16 | Mistral AIapi.mistral.ai | open-mistral-nemo | 0.40 s 最佳: 0.34最差: 0.46 | 200.44t/s | 5 |
| 17 | Mistral AIapi.mistral.ai | open-mistral-nemo | 0.40 s 最佳: 0.34最差: 0.46 | 200.44t/s | 5 |
| 18 | R Realpicsrealpics.cn:2234 | qwen3-30b-a3b | 0.45 s 最佳: 0.39最差: 0.62 | 114.09t/s | 5 |
| 19 | r realpics.cn:2234realpics.cn:2234 | qwen3-30b-a3b | 0.45 s 最佳: 0.39最差: 0.62 | 114.09t/s | 5 |
| 20 | r realpics.cn:2234realpics.cn:2234 | qwen3-30b-a3b | 0.45 s 最佳: 0.39最差: 0.62 | 114.09t/s | 5 |
| 21 | Mistral AIapi.mistral.ai | ministral-14b-latest | 0.46 s 最佳: 0.31最差: 0.66 | 129.12t/s | 5 |
| 22 | Mistral AIapi.mistral.ai | ministral-14b-latest | 0.46 s 最佳: 0.31最差: 0.66 | 129.12t/s | 5 |
| 23 | Fireworks AIapi.fireworks.ai | accounts/fireworks/models/deepseek-v3p2 | 0.49 s 最佳: 0.45最差: 0.62 | 114.61t/s | 5 |
| 24 | Mistral AIapi.mistral.ai | ministral-3b-2410 | 0.50 s 最佳: 0.30最差: 0.70 | 332.18t/s | 5 |
| 25 | Mistral AIapi.mistral.ai | ministral-3b-2410 | 0.50 s 最佳: 0.30最差: 0.70 | 332.18t/s | 5 |
| 26 | DashScopedashscope.aliyuncs.com | qwen-flash | 0.50 s 最佳: 0.33最差: 1.10 | 137.25t/s | 15 |
| 27 | a api.n1n.aiapi.n1n.ai | gemini-2.5-flash-lite | 0.52 s 最佳: 0.44最差: 0.64 | 297.64t/s | 5 |
| 28 | Cerebrasapi.cerebras.ai | gpt-oss-120b | 0.54 s 最佳: 0.25最差: 1.05 | 1920.13t/s | 5 |
| 29 | a api.vectorengine.aiapi.vectorengine.ai | gemini-2.0-flash | 0.56 s 最佳: 0.50最差: 0.63 | 175.01t/s | 5 |
| 30 | DashScopedashscope.aliyuncs.com | qwen-vl-plus-2025-07-10 | 0.56 s 最佳: 0.37最差: 1.20 | 112.44t/s | 65 |
| 31 | N N1Nhk.n1n.ai | qwen3-vl-flash | 0.56 s 最佳: 0.49最差: 0.66 | 85.94t/s | 5 |
| 32 | g gpt.cosmoplat.comgpt.cosmoplat.com | qwen3-235b-fp8 | 0.56 s 最佳: 0.27最差: 1.24 | 94.11t/s | 5 |
| 33 | DashScopedashscope.aliyuncs.com | qwen-plus-2025-04-28 | 0.57 s 最佳: 0.41最差: 1.06 | 43.49t/s | 10 |
| 34 | a ai-hub.square-llm.comai-hub.square-llm.com | anthropic/claude-haiku-4.5 | 0.57 s 最佳: 0.44最差: 0.72 | 98.63t/s | 5 |
| 35 | DashScopedashscope.aliyuncs.com | tongyi-intent-detect-v3 | 0.57 s 最佳: 0.43最差: 1.05 | 83.35t/s | 5 |
| 36 | Mistral AIapi.mistral.ai | mistral-large-2411 | 0.58 s 最佳: 0.38最差: 1.31 | 45.26t/s | 5 |
| 37 | Mistral AIapi.mistral.ai | mistral-large-2411 | 0.58 s 最佳: 0.38最差: 1.31 | 45.26t/s | 5 |
| 38 | N N1Nhk.n1n.ai | qwen-flash | 0.63 s 最佳: 0.44最差: 1.10 | 128.54t/s | 5 |
| 39 | a api.vectorengine.aiapi.vectorengine.ai | gemini-2.0-flash-lite | 0.64 s 最佳: 0.33最差: 2.46 | 135.07t/s | 10 |
| 40 | DashScopedashscope.aliyuncs.com | tongyi-xiaomi-analysis-pro | 0.64 s 最佳: 0.46最差: 1.12 | 65.76t/s | 5 |
| 41 | DashScopedashscope.aliyuncs.com | qwen-plus | 0.66 s 最佳: 0.46最差: 1.07 | 57.34t/s | 5 |
| 42 | DashScopedashscope.aliyuncs.com | qwen-plus-latest | 0.69 s 最佳: 0.52最差: 1.16 | 57.95t/s | 5 |
| 43 | N New APIapi.seosycy.com | deepseek-v3.2 | 0.71 s 最佳: 0.51最差: 1.29 | 27.18t/s | 10 |
| 44 | DashScopedashscope.aliyuncs.com | qwen3-max-preview | 0.77 s 最佳: 0.55最差: 1.56 | 44.58t/s | 5 |
| 45 | SiliconFlowapi.siliconflow.cn | Qwen/Qwen3-Coder-30B-A3B-Instruct | 0.78 s 最佳: 0.57最差: 1.27 | 38.23t/s | 5 |
| 46 | DashScopedashscope.aliyuncs.com | qwen-max-latest | 0.79 s 最佳: 0.48最差: 1.47 | 37.07t/s | 5 |
| 47 | Fireworks AIapi.fireworks.ai | accounts/fireworks/models/gpt-oss-120b | 0.79 s 最佳: 0.60最差: 1.00 | 144.71t/s | 10 |
| 48 | DashScopedashscope.aliyuncs.com | qwen-plus-2025-12-01 | 0.80 s 最佳: 0.49最差: 1.23 | 54.28t/s | 10 |
| 49 | ChatGTPwww.chatgtp.cn | gpt-4.1-nano-2025-04-14 | 0.80 s 最佳: 0.71最差: 0.91 | 222.46t/s | 5 |
| 50 | 1 123.54.215.139:8008123.54.215.139:8008 | qwen3-32b | 0.81 s 最佳: 0.29最差: 2.11 | 22.93t/s | 5 |