🥇
gpt-5.6-lunaopenai/gpt-5.6-luna
17.32T
份额 14.8% · 请求 546.0M
热门模型用量榜
按当日总 Tokens（输入+输出）降序；份额=该模型占当日榜内总量。反映路由平台流量，≠全球份额。 对标 openrouter.ai/rankings。能力验真 → 模型天梯 · 模型目录 · Providers · 实验室 · 官方 API。
数据状态
OpenRouter 用量榜 · 2026-09-16 00:00:00 · source=openrouter · 2026-09-17T03:27:42.856Z
热门模型用量榜 · 2026-09-16
按当日总 Tokens（输入+输出）降序；份额=该模型占当日榜内总量。反映路由平台流量，≠全球份额。
Top 50总量 116.87T
🥈
hy4-previewtencent/hy4-preview
11.96T
份额 10.2% · 请求 101.8M
🥉
glm-5.3-flashz-ai/glm-5.3-flash
11.27T
份额 9.6% · 请求 297.7M
| # | 模型 | 变体 | Tokens | 份额 | 相对热度 | 请求 | 工具调用 |
|---|---|---|---|---|---|---|---|
| 🥇 | gpt-5.6-luna openai/gpt-5.6-luna | standard | 17.32T in 17.00T · out 318.94B | 14.8% | 546.0M | 0 | |
| 🥈 | hy4-preview tencent/hy4-preview | standard | 11.96T in 11.85T · out 104.67B | 10.2% | 101.8M | 0 | |
| 🥉 | glm-5.3-flash z-ai/glm-5.3-flash | standard | 11.27T in 10.97T · out 302.10B | 9.6% | 297.7M | 0 | |
| 4 | deepseek-v4-flash deepseek/deepseek-v4-flash | standard | 11.24T in 10.86T · out 383.45B | 9.6% | 511.8M | 0 | |
| 5 | deepseek-v4.1-flash deepseek/deepseek-v4.1-flash | standard | 10.27T in 10.09T · out 176.38B | 8.8% | 166.6M | 0 | |
| 6 | mimo-v2.5 xiaomi/mimo-v2.5 | standard | 7.83T in 7.77T · out 68.75B | 6.7% | 105.6M | 0 | |
| 7 | hy3 tencent/hy3 | standard | 4.47T in 4.40T · out 71.39B | 3.8% | 70.8M | 0 | |
| 8 | deepseek-v4-flash deepseek/deepseek-v4-flash | standard | 4.24T in 4.02T · out 221.40B | 3.6% | 447.4M | 0 | |
| 9 | nemotron-3-ultra-550b-a55b nvidia/nemotron-3-ultra-550b-a55b | free | 3.49T in 3.47T · out 19.02B | 3.0% | 27.8M | 0 | |
| 10 | glm-5.3 z-ai/glm-5.3 | standard | 2.46T in 2.42T · out 38.72B | 2.1% | 31.4M | 0 | |
| 11 | gemini-3.8-flash google/gemini-3.8-flash | standard | 2.16T in 2.12T · out 47.73B | 1.9% | 55.4M | 0 | |
| 12 | muse-spark-1.3-contributor meta/muse-spark-1.3-contributor | standard | 1.97T in 1.94T · out 30.36B | 1.7% | 26.8M | 0 | |
| 13 | gpt-5.6-sol openai/gpt-5.6-sol | standard | 1.85T in 1.83T · out 21.76B | 1.6% | 31.7M | 0 | |
| 14 | solar-pro4 upstage/solar-pro4 | standard | 1.67T in 1.65T · out 18.03B | 1.4% | 21.8M | 0 | |
| 15 | claude-sonnet-5 anthropic/claude-sonnet-5 | standard | 1.52T in 1.50T · out 21.86B | 1.3% | 28.5M | 0 | |
| 16 | glm-5.2 z-ai/glm-5.2 | standard | 1.48T in 1.44T · out 40.08B | 1.3% | 43.9M | 0 | |
| 17 | minimax-m3 minimax/minimax-m3 | standard | 1.46T in 1.43T · out 27.97B | 1.2% | 29.3M | 0 | |
| 18 | deepseek-v4-pro deepseek/deepseek-v4-pro | standard | 1.43T in 1.33T · out 100.89B | 1.2% | 58.6M | 0 | |
| 19 | kimi-k3 moonshotai/kimi-k3 | standard | 1.37T in 1.34T · out 27.42B | 1.2% | 25.5M | 0 | |
| 20 | laguna-s-2.1 poolside/laguna-s-2.1 | free | 1.16T in 1.15T · out 9.21B | 1.0% | 13.4M | 0 | |
| 21 | claude-opus-5 anthropic/claude-opus-5 | standard | 1.10T in 1.08T · out 19.52B | 0.9% | 13.9M | 0 | |
| 22 | deepseek-v4-pro deepseek/deepseek-v4-pro | standard | 1.03T in 1.01T · out 24.36B | 0.9% | 35.1M | 0 | |
| 23 | ling-3.0-flash-fin inclusionai/ling-3.0-flash-fin | free | 1.00T in 985.26B · out 17.45B | 0.9% | 15.7M | 0 | |
| 24 | gpt-6-astra openai/gpt-6-astra | standard | 818.99B in 810.92B · out 8.07B | 0.7% | 11.4M | 0 | |
| 25 | gemini-3-flash-preview google/gemini-3-flash-preview | standard | 808.90B in 772.73B · out 36.18B | 0.7% | 99.5M | 0 | |
| 26 | gemini-2.5-flash-lite google/gemini-2.5-flash-lite | standard | 723.80B in 666.49B · out 57.31B | 0.6% | 240.3M | 0 | |
| 27 | gpt-oss-120b openai/gpt-oss-120b | standard | 695.88B in 612.24B · out 83.64B | 0.6% | 166.2M | 0 | |
| 28 | nemotron-3.5-lightning nvidia/nemotron-3.5-lightning | free | 694.41B in 685.29B · out 9.12B | 0.6% | 11.1M | 0 | |
| 29 | gemini-3.7-flash google/gemini-3.7-flash | standard | 672.79B in 641.64B · out 31.15B | 0.6% | 37.9M | 0 | |
| 30 | dots-3-note-preview dots-studio/dots-3-note-preview | free | 649.05B in 638.86B · out 10.19B | 0.6% | 10.5M | 0 | |
| 31 | gpt-5.6-terra openai/gpt-5.6-terra | standard | 540.03B in 533.59B · out 6.44B | 0.5% | 14.4M | 0 | |
| 32 | nex-n2.5-pro nex-agi/nex-n2.5-pro | free | 513.65B in 502.83B · out 10.82B | 0.4% | 7.8M | 0 | |
| 33 | gemini-2.5-flash google/gemini-2.5-flash | standard | 478.03B in 446.78B · out 31.25B | 0.4% | 123.9M | 0 | |
| 34 | gemini-3.1-flash-lite google/gemini-3.1-flash-lite | standard | 472.79B in 448.43B · out 24.36B | 0.4% | 105.8M | 0 | |
| 35 | claude-4.8-opus anthropic/claude-4.8-opus | standard | 472.63B in 463.70B · out 8.92B | 0.4% | 8.4M | 0 | |
| 36 | ling-3.0-flash-vl inclusionai/ling-3.0-flash-vl | free | 448.26B in 442.11B · out 6.15B | 0.4% | 6.8M | 0 | |
| 37 | claude-fable-5.1 anthropic/claude-fable-5.1 | standard | 443.10B in 438.50B · out 4.59B | 0.4% | 3.7M | 0 | |
| 38 | qwen3.8-flash qwen/qwen3.8-flash | standard | 427.65B in 415.73B · out 11.93B | 0.4% | 10.6M | 0 | |
| 39 | deepseek-v3.2 deepseek/deepseek-v3.2 | standard | 420.66B in 401.75B · out 18.91B | 0.4% | 65.9M | 0 | |
| 40 | claude-4.6-sonnet anthropic/claude-4.6-sonnet | standard | 405.00B in 393.08B · out 11.93B | 0.3% | 22.7M | 0 | |
| 41 | grok-4.6 x-ai/grok-4.6 | standard | 383.07B in 372.84B · out 10.23B | 0.3% | 6.8M | 0 | |
| 42 | gemma-4-31b-it google/gemma-4-31b-it | standard | 378.31B in 343.54B · out 34.77B | 0.3% | 88.2M | 0 | |
| 43 | qwen3.8-max qwen/qwen3.8-max | standard | 368.64B in 358.50B · out 10.14B | 0.3% | 5.1M | 0 | |
| 44 | inkling thinkingmachines/inkling | free | 359.45B in 354.84B · out 4.60B | 0.3% | 4.8M | 0 | |
| 45 | nemotron-3-super-120b-a12b nvidia/nemotron-3-super-120b-a12b | free | 356.87B in 344.55B · out 12.33B | 0.3% | 10.6M | 0 | |
| 46 | qwen3.7-flash qwen/qwen3.7-flash | standard | 343.93B in 307.55B · out 36.38B | 0.3% | 93.6M | 0 | |
| 47 | deepseek-v4-flash-vision-exp deepseek/deepseek-v4-flash-vision-exp | standard | 317.93B in 312.94B · out 4.98B | 0.3% | 6.3M | 0 | |
| 48 | ling-3.0-flash-sante inclusionai/ling-3.0-flash-sante | free | 316.31B in 310.29B · out 6.02B | 0.3% | 5.7M | 0 | |
| 49 | gpt-5.6-luna-pro openai/gpt-5.6-luna-pro | standard | 309.57B in 299.76B · out 9.81B | 0.3% | 3.8M | 0 | |
| 50 | gemma-4-26b-a4b-it google/gemma-4-26b-a4b-it | standard | 294.21B in 275.67B · out 18.54B | 0.3% | 98.0M | 0 |
数据来源 OpenRouter 公开 Rankings API（约小时级缓存）。用量/份额反映路由平台流量，不等于全球真实份额； 智力指数来自 Artificial Analysis 透出字段。选型请结合 天梯、目录与自有压测。
站內推薦
同系工具：Clavue CLI / imux IDE / clavue-2.1
Clavue · CLI 与 Agent 平台
CLI / GUI Agent 运行时、设备登录、会员额度与 OpenAI 兼容 API（api.clavue.com）。开发脚本、CI 与本地工具一条链路。
打开 Clavue ↗imux · 原生 macOS AI IDE
Clavue 平台的原生 IDE：多 Agent 分屏、Ghostty 级终端、Agent Chat、浏览器自动化与 Supervisor——不是又一个 Electron 壳。
了解 imux ↗Clavue 2.1 · 产品级大模型
旗舰模型 clavue-2.1（及 fast / pro / rev）：适合复杂推理与长程 Agent 循环。Chat、imux、API 共用会员额度。
查看模型 ↗