Leaderboard
Discover the top-performing models based on total token usage.
| Rank | Model | Input Tokens | Output Tokens | Total Tokens |
|---|---|---|---|---|
#1 馃 | swiss-ai/Apertus-8B-Instruct-2509-api-overhead-sglang-brachium-20260807-161911 34.7K requests 路 active today | 22.1M | 9.7M | 31.9M |
#2 馃 | CSCS-Inference/zai-org/GLM-5.2 288 requests 路 active today | 30.4M | 214.2K | 30.6M |
#3 馃 | SwissAI-Research/swiss-ai/Apertus-v1.5-70B 1.8K requests 路 active today | 2.3M | 350.3K | 2.6M |
#4 | SwissAI-Research/swiss-ai/Apertus-v1.5-70B-thinking 1.8K requests 路 active today | 2.2M | 349.9K | 2.6M |
#5 | CSCS-Inference/google/gemma-4-31B-it 310 requests 路 active today | 363.7K | 49.7K | 413.4K |
#6 | CSCS-Inference/swiss-ai/Apertus-v1.5-70B 127 requests 路 active today | 149.9K | 24.0K | 173.9K |
#7 | CSCS-Inference/swiss-ai/Apertus-v1.5-70B-thinking 70 requests 路 active today | 81.9K | 13.0K | 94.9K |
#8 | swiss-ai/Apertus-v1.5-70B 45 requests 路 active today | 46.0K | 12.0K | 58.0K |
#9 | SwissAI-Research/zai-org/GLM-4.7-Flash 78 requests 路 active today | 1.4K | 10.5K | 11.9K |
#10 | swiss-ai/Apertus-8B-Instruct-2509 24 requests 路 active today | 1.8K | 221 | 2.0K |
#11 | swiss-ai/Apertus-70B-Instruct-2509 24 requests 路 active today | 1.8K | 163 | 1.9K |
#12 | zai-org/GLM-4.7-Flash 13 requests 路 active today | 222 | 1.7K | 1.9K |
#13 | meta-llama/Llama-3.3-70B-Instruct 25 requests 路 active today | 1.2K | 50 | 1.3K |
#14 | SwissAI-Research/swiss-ai/Apertus-70B-Instruct-2509 5 requests 路 active today | 326 | 24 | 350 |
#15 | SwissAI-Research/meta-llama/Llama-3.3-70B-Instruct 4 requests 路 active today | 192 | 8 | 200 |
#16 | RCP-AIaaS/openai/gpt-oss-120b 2 requests 路 active today | 170 | 2 | 172 |
#17 | CSCS-Inference/swiss-ai/Apertus-v1.5-8B-thinking 2 requests 路 active today | 60 | 2 | 62 |
#18 | CSCS-Inference/swiss-ai/Apertus-v1.5-8B 2 requests 路 active today | 60 | 2 | 62 |
#19 | RCP-AIaaS/swiss-ai/Apertus-v1.5-70B 2 requests 路 active today | 60 | 2 | 62 |
#20 | RCP-AIaaS/swiss-ai/Apertus-70B-Instruct-2509 2 requests 路 active today | 60 | 2 | 62 |
#21 | CSCS-Inference/swiss-ai/Apertus-8B-Instruct-2509 2 requests 路 active today | 60 | 2 | 62 |
#22 | CSCS-Inference/swiss-ai/Apertus-70B-Instruct-2509 2 requests 路 active today | 60 | 2 | 62 |
#23 | RCP-AIaaS/swiss-ai/Apertus-8B-Instruct-2509 2 requests 路 active today | 60 | 2 | 62 |
#24 | CSCS-Inference/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16 2 requests 路 active today | 54 | 2 | 56 |
#25 | RCP-AIaaS/Qwen/Qwen3.6-35B-A3B 2 requests 路 active today | 52 | 2 | 54 |
#26 | RCP-AIaaS/OpenMeditron/meditron-CHUV-dpo 2 requests 路 active today | 52 | 2 | 54 |
#27 | RCP-AIaaS/OpenMeditron/Meditron3-70B 2 requests 路 active today | 52 | 2 | 54 |
#28 | RCP-AIaaS/Qwen/Qwen3.5-397B-A17B 2 requests 路 active today | 52 | 2 | 54 |
#29 | RCP-AIaaS/Qwen/Qwen3-VL-235B-A22B-Thinking 2 requests 路 active today | 52 | 2 | 54 |
#30 | RCP-AIaaS/Qwen/Qwen3-VL-30B-A3B-Instruct 2 requests 路 active today | 48 | 2 | 50 |
#31 | RCP-AIaaS/Qwen/Qwen3-30B-A3B-Instruct-2507 2 requests 路 active today | 48 | 2 | 50 |
#32 | CSCS-Inference/moonshotai/Kimi-K2.7-Code 2 requests 路 active today | 46 | 2 | 48 |
#33 | RCP-AIaaS/moonshotai/Kimi-K2.7-Code 2 requests 路 active today | 46 | 2 | 48 |
#34 | RCP-AIaaS/google/medgemma-27b-text-it 2 requests 路 active today | 42 | 2 | 44 |
#35 | RCP-AIaaS/mistralai/Mistral-Small-3.2-24B-Instruct-2506 2 requests 路 active today | 32 | 2 | 34 |
#36 | RCP-AIaaS/deepseek-ai/DeepSeek-V4-Flash-0731 2 requests 路 active today | 30 | 2 | 32 |
#37 | RCP-AIaaS/swiss-ai/Apertus-v1.5-8B 1 requests 路 active today | 30 | 1 | 31 |