OpenRouter Live Rankings · SEO 分 Tab

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。

智能指数天梯AA / Arena / free 池实测 模型目录价格 · 上下文 · AA 分 热门用量真实 Tokens 热度 智力指数AA 客观能力 任务消费场景选型参考

数据状态

OpenRouter 用量榜 · 2026-11-01 00:00:00 · source=openrouter · 2026-11-02T10:58:57.075Z

热门模型用量榜 · 2026-11-01

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 181.07T

🥇

deepseek-v4.1-flash

deepseek/deepseek-v4.1-flash

48.08T

份额 26.6% · 请求 770.6M

🥈

glm-5.3-flash

z-ai/glm-5.3-flash

15.01T

份额 8.3% · 请求 699.6M

🥉

deepseek-v4.1-flash

deepseek/deepseek-v4.1-flash

14.87T

份额 8.2% · 请求 473.0M

#	模型	变体	Tokens	份额	请求
🥇	deepseek-v4.1-flash deepseek/deepseek-v4.1-flash	standard	48.08T in 47.44T · out 646.73B	26.6%	770.6M
🥈	glm-5.3-flash z-ai/glm-5.3-flash	standard	15.01T in 14.47T · out 532.49B	8.3%	699.6M
🥉	deepseek-v4.1-flash deepseek/deepseek-v4.1-flash	standard	14.87T in 14.56T · out 310.70B	8.2%	473.0M
4	gpt-6-luna openai/gpt-6-luna	standard	9.62T in 9.35T · out 262.71B	5.3%	523.0M
5	hy4-preview tencent/hy4-preview	standard	9.07T in 8.98T · out 86.76B	5.0%	88.0M
6	claude-opus-5.5 anthropic/claude-opus-5.5	standard	6.73T in 6.67T · out 60.15B	3.7%	57.3M
7	step-5-preview stepfun/step-5-preview	standard	6.25T in 6.22T · out 28.89B	3.5%	24.3M
8	minimax-m3.1-flash minimax/minimax-m3.1-flash	standard	6.23T in 6.14T · out 90.55B	3.4%	69.4M
9	gpt-5.6-luna openai/gpt-5.6-luna	standard	4.33T in 4.23T · out 95.49B	2.4%	176.4M
10	glm-5.3 z-ai/glm-5.3	standard	4.23T in 4.16T · out 66.12B	2.3%	66.5M
11	deepseek-v4-flash deepseek/deepseek-v4-flash	standard	3.94T in 3.77T · out 172.99B	2.2%	329.7M
12	gpt-6.1-sol openai/gpt-6.1-sol	standard	3.75T in 3.69T · out 57.60B	2.1%	105.2M
13	jev-1.13 typesafe/jev-1.13	standard	3.14T in 2.91T · out 224.54B	1.7%	991.1M
14	hy3 tencent/hy3	standard	3.07T in 3.02T · out 49.81B	1.7%	38.5M
15	mimo-v2.6-flash xiaomi/mimo-v2.6-flash	standard	3.02T in 2.97T · out 42.72B	1.7%	58.1M
16	nemotron-3-ultra-550b-a55b nvidia/nemotron-3-ultra-550b-a55b	free	2.99T in 2.96T · out 30.99B	1.7%	32.4M
17	claude-haiku-5.5 anthropic/claude-haiku-5.5	standard	2.79T in 2.66T · out 134.47B	1.5%	183.7M
18	deepseek-v4-flash deepseek/deepseek-v4-flash	standard	2.69T in 2.53T · out 158.18B	1.5%	338.3M
19	claude-sonnet-5.5 anthropic/claude-sonnet-5.5	standard	2.60T in 2.54T · out 54.90B	1.4%	52.6M
20	muse-spark-1.3-contributor meta/muse-spark-1.3-contributor	standard	2.59T in 2.56T · out 34.96B	1.4%	35.8M
21	nemotron-3.5-super-vl nvidia/nemotron-3.5-super-vl	free	2.37T in 2.34T · out 28.12B	1.3%	21.4M
22	kimi-k3.1-pro moonshotai/kimi-k3.1-pro	standard	2.29T in 2.27T · out 19.74B	1.3%	18.5M
23	jev-1.14 typesafe/jev-1.14	standard	1.74T in 1.59T · out 150.62B	1.0%	474.0M
24	kimi-k3 moonshotai/kimi-k3	standard	1.71T in 1.68T · out 25.84B	0.9%	33.3M
25	gemini-3.8-flash google/gemini-3.8-flash	standard	1.52T in 1.45T · out 70.64B	0.8%	83.7M
26	solar-mini4 upstage/solar-mini4	standard	1.39T in 1.37T · out 12.52B	0.8%	13.7M
27	mimo-v2.6-pro xiaomi/mimo-v2.6-pro	standard	1.30T in 1.28T · out 23.28B	0.7%	19.1M
28	gemini-4-argon google/gemini-4-argon	standard	1.16T in 1.13T · out 28.68B	0.6%	24.1M
29	nemotron-3.5-lightning nvidia/nemotron-3.5-lightning	free	989.15B in 976.94B · out 12.21B	0.5%	14.0M
30	glm-5.2 z-ai/glm-5.2	standard	920.79B in 893.39B · out 27.40B	0.5%	31.3M
31	deepseek-v4-pro deepseek/deepseek-v4-pro	standard	794.29B in 769.02B · out 25.27B	0.4%	44.8M
32	dots-3-note-preview dots-studio/dots-3-note-preview	free	731.19B in 713.14B · out 18.04B	0.4%	14.8M
33	gpt-6.1-terra openai/gpt-6.1-terra	standard	645.20B in 638.79B · out 6.42B	0.4%	13.5M
34	gemini-3-flash-preview google/gemini-3-flash-preview	standard	620.29B in 592.38B · out 27.91B	0.3%	71.2M
35	gemini-3.1-flash-lite google/gemini-3.1-flash-lite	standard	616.15B in 580.69B · out 35.46B	0.3%	146.8M
36	minimax-m3 minimax/minimax-m3	standard	612.17B in 597.95B · out 14.22B	0.3%	9.9M
37	gpt-6-luna-pro openai/gpt-6-luna-pro	standard	606.60B in 583.52B · out 23.07B	0.3%	9.4M
38	qwen3.8-flash qwen/qwen3.8-flash	standard	600.12B in 568.93B · out 31.19B	0.3%	21.0M
39	qwen3.8-27b qwen/qwen3.8-27b	standard	598.37B in 572.22B · out 26.15B	0.3%	37.1M
40	deepseek-v4-pro deepseek/deepseek-v4-pro	standard	573.13B in 554.85B · out 18.28B	0.3%	23.1M
41	claude-sonnet-5 anthropic/claude-sonnet-5	standard	516.56B in 507.80B · out 8.77B	0.3%	12.8M
42	step-3.7-flash stepfun/step-3.7-flash	standard	499.87B in 492.64B · out 7.23B	0.3%	7.0M
43	gemma-4-31b-it google/gemma-4-31b-it	standard	494.10B in 461.27B · out 32.83B	0.3%	101.0M
44	gpt-6-astra openai/gpt-6-astra	standard	444.57B in 438.05B · out 6.52B	0.2%	15.0M
45	qwen3.7-flash qwen/qwen3.7-flash	standard	441.53B in 404.97B · out 36.56B	0.2%	138.0M
46	solar-pro4 upstage/solar-pro4	standard	396.83B in 394.03B · out 2.79B	0.2%	5.3M
47	gemini-3.7-flash google/gemini-3.7-flash	standard	393.44B in 367.31B · out 26.13B	0.2%	26.5M
48	gpt-oss-120b openai/gpt-oss-120b	standard	385.09B in 336.25B · out 48.84B	0.2%	94.4M
49	inkling thinkingmachines/inkling	free	371.01B in 364.15B · out 6.87B	0.2%	5.1M
50	gemma-4-26b-a4b-it google/gemma-4-26b-a4b-it	standard	368.18B in 342.03B · out 26.15B	0.2%	131.8M

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 平台 ↗

Clavue · CLI 与 Agent 平台

CLI / GUI Agent 运行时、设备登录、会员额度与通用对话 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 ↗