Leaderboard · OpenRouter usage

The models developers actually route work through.

Name: OpenRouter routed-usage rankings retrieved July 22, 2026
Creator: Model Gauntlet
License: https://openrouter.ai/rankings

OpenRouter's routed token volume for 412 models over the platform's week view, retrieved July 22, 2026. This is the platform's own usage order. It is a demand signal, not a quality score, and it is never blended with the benchmark boards.

OpenRouter routed usage per model, week view retrieved July 22, 2026.
Rank	Model	Tokens routed	Requests	Share of top
01	Tencent: Hy3	10.9T	201,881,856	100.0%
02	Xiaomi: MiMo-V2.5	9.4T	140,528,738	86.7%
03	DeepSeek-V4-Flash	5.4T	546,571,250	49.4%
04	Z.ai: GLM 5.2	3.6T	74,644,988	33.4%
05	MiniMax: MiniMax M3	3.2T	51,139,830	29.7%
06	DeepSeek-V4-Pro	2.8T	86,168,748	25.8%
07	NVIDIA: Nemotron 3 Ultra	2.7T	26,144,925	24.9%
08	Claude Opus 4.7	1.9T	27,235,256	17.8%
09	Claude Opus 4.8	1.9T	22,654,380	17.5%
10	Anthropic: Claude Sonnet 5	1.1T	16,892,808	10.4%
11	Google: Gemini 3 Flash Preview	962.5B	132,142,507	8.9%
12	StepFun: Step 3.7 Flash	960.6B	16,102,926	8.8%
13	anthropic/claude-4.6-sonnet	876.8B	41,114,831	8.1%
14	MoonshotAI: Kimi K3	740.6B	9,146,489	6.8%
15	GPT-5.5	599.0B	15,114,586	5.5%
16	Google: Gemini 2.5 Flash	591.4B	176,812,716	5.4%
17	Poolside: Laguna M.1	583.5B	8,208,300	5.4%
18	Xiaomi: MiMo-V2.5-Pro	571.6B	10,987,711	5.3%
19	Google: Gemini 2.5 Flash Lite	570.4B	234,121,288	5.2%
20	Google: Gemini 3.1 Flash Lite	561.8B	111,905,748	5.2%
21	gpt-oss-120b	509.9B	113,938,416	4.7%
22	OpenAI: GPT-5.6 Sol	501.3B	9,997,708	4.6%
23	Google: Gemini 3.5 Flash	450.7B	24,488,495	4.1%
24	Claude Fable 5	449.9B	12,023,445	4.1%
25	GPT-5.4	415.2B	15,707,813	3.8%

Show the remaining 387 models

26	Google: Gemma 4 26B A4B	371.0B	74,117,483	3.4%
27	DeepSeek: DeepSeek V3.2	358.7B	50,466,675	3.3%
28	xAI: Grok 4.5	355.1B	7,387,103	3.3%
29	Google: Gemma 4 31B	346.1B	60,992,753	3.2%
30	Kimi K2.6	323.2B	13,503,514	3.0%
31	GPT-4o mini	303.5B	138,198,618	2.8%
32	NVIDIA: Nemotron 3 Super	294.4B	9,110,378	2.7%
33	OpenAI: GPT-5.6 Luna	294.3B	19,527,015	2.7%
34	Mistral: Mistral Nemo	279.3B	97,081,888	2.6%
35	Claude Haiku 4.5	247.8B	31,248,735	2.3%
36	anthropic/claude-4.6-opus	212.7B	5,158,462	2.0%
37	Google: Gemini 3.1 Pro Preview	174.6B	12,393,151	1.6%
38	Qwen: Qwen3.7 Max	172.9B	11,048,192	1.6%
39	OpenAI: GPT-5.4 Nano	169.5B	26,389,571	1.6%
40	OpenAI: GPT-5.4 Mini	167.6B	24,739,089	1.5%
41	GLM-5	167.4B	7,297,478	1.5%
42	moonshotai/kimi-k2.5-0127	158.8B	8,922,367	1.5%
43	openai/text-embedding-3-small	157.3B	78,723,347	1.4%
44	OpenAI: GPT-5.6 Terra	154.8B	13,145,908	1.4%
45	openai/gpt-5-mini-2025-08-07	140.1B	19,137,454	1.3%
46	GPT-5.2	139.4B	13,212,502	1.3%
47	cohere/north-mini-code	138.3B	4,328,070	1.3%
48	gpt-oss-20b	133.7B	35,758,504	1.2%
49	Qwen: Qwen3.7 Plus	129.5B	18,315,419	1.2%
50	MoonshotAI: Kimi K2.7 Code	125.0B	2,559,373	1.1%
51	qwen/qwen3-embedding-8b	124.0B	72,293,168	1.1%
52	Google: Gemini 3.1 Flash Lite Preview	121.1B	23,453,593	1.1%
53	MiniMax: MiniMax M2.7	117.9B	5,674,734	1.1%
54	Poolside: Laguna XS 2.1	110.4B	2,685,482	1.0%
55	GLM-5.1	107.3B	6,087,132	1.0%
56	Claude Sonnet 4.5	91.5B	8,386,530	0.8%
57	xAI: Grok 4.3	91.5B	13,003,683	0.8%
58	Qwen: Qwen3.6 35B A3B	90.2B	6,675,368	0.8%
59	qwen/qwen3.5-flash	79.2B	23,087,577	0.7%
60	openai/gpt-4.1-mini-2025-04-14	76.1B	27,303,354	0.7%
61	openai/gpt-5-nano-2025-08-07	74.1B	17,294,344	0.7%
62	Google: Gemini 2.5 Pro	72.9B	6,700,016	0.7%
63	GLM-4.7	72.8B	5,553,420	0.7%
64	qwen/qwen3-235b-a22b-07-25	70.5B	20,675,152	0.6%
65	inclusionAI: Ling-2.6-flash	66.7B	26,487,051	0.6%
66	Nemotron 3-Nano-30B-A3B	58.2B	7,232,552	0.5%
67	Meta: Llama 3.1 8B Instruct	51.9B	51,954,809	0.5%
68	Google: Gemma 3 27B	51.6B	24,812,964	0.5%
69	openai/gpt-5-2025-08-07	49.0B	4,034,644	0.5%
70	qwen/qwen3.6-plus-04-02	48.1B	6,113,545	0.4%
71	MiniMax: MiniMax M2.5	46.9B	2,132,971	0.4%
72	Qwen: Qwen3.6 27B	46.7B	5,608,635	0.4%
73	Meta: Muse Spark 1.1	46.2B	975,213	0.4%
74	openai/gpt-4.1-2025-04-14	44.2B	12,495,110	0.4%
75	DeepSeek: DeepSeek V3.1	43.1B	10,941,569	0.4%
76	OpenAI: GPT-5.6 Sol Pro	42.9B	412,650	0.4%
77	Qwen: Qwen3.5-9B	42.0B	8,784,135	0.4%
78	OpenAI: GPT-5.6 Luna Pro	41.8B	520,710	0.4%
79	Z.ai: GLM 4.7 Flash	40.8B	5,623,664	0.4%
80	DeepSeek: DeepSeek V3.1 Terminus	40.1B	17,537,232	0.4%
81	Qwen: Qwen3.6 Flash	38.1B	3,591,712	0.4%
82	DeepSeek: DeepSeek V3 0324	38.0B	7,854,878	0.3%
83	mistralai/mistral-small-3.2-24b-instruct-2506	36.2B	13,282,148	0.3%
84	meta-llama/llama-4-maverick-17b-128e-instruct	36.0B	30,840,922	0.3%
85	Meta: Llama 3.3 70B Instruct	34.4B	17,590,578	0.3%
86	Grok 4.20	31.6B	3,870,403	0.3%
87	Poolside: Laguna S 2.1	31.4B	419,792	0.3%
88	Qwen: Qwen3.5-35B-A3B	29.8B	3,297,766	0.3%
89	Claude Sonnet 4	29.0B	2,987,693	0.3%
90	Qwen3.5 397B-A17B	28.8B	3,743,370	0.3%
91	GPT-5.3 Codex	28.3B	561,869	0.3%
92	Mistral: Mistral Small 4	27.3B	5,526,832	0.3%
93	Tencent: Hy3 preview	26.3B	1,765,249	0.2%
94	deepseek/deepseek-chat-v3	25.6B	12,026,562	0.2%
95	Qwen: Qwen3 30B A3B Instruct 2507	24.5B	7,977,635	0.2%
96	anthropic/claude-4.8-opus-fast	24.4B	307,119	0.2%
97	qwen/qwen3-next-80b-a3b-instruct-2509	24.2B	3,198,113	0.2%
98	GPT-5.1	23.8B	2,434,631	0.2%
99	openai/text-embedding-3-large	22.7B	11,333,268	0.2%
100	nvidia/nemotron-3-nano-omni-30b-a3b-reasoning	21.6B	1,165,947	0.2%
101	Claude Opus 4.5	19.5B	1,097,981	0.2%
102	Qwen: Qwen3.5-27B	18.7B	3,210,980	0.2%
103	qwen/qwen3-coder-next-2025-02-03	18.6B	858,171	0.2%
104	IBM: Granite 4.0 Micro	17.7B	496,970	0.2%
105	openai/gpt-4.1-nano-2025-04-14	17.7B	8,218,010	0.2%
106	OpenAI: GPT-5.6 Terra Pro	17.7B	180,880	0.2%
107	qwen/qwen3-32b-04-28	17.5B	9,213,370	0.2%
108	DeepSeek: DeepSeek V3.2 Exp	17.2B	2,778,888	0.2%
109	Qwen: Qwen2.5 7B Instruct	17.2B	12,172,583	0.2%
110	Google: Gemma 3 12B	16.5B	6,500,770	0.2%
111	openai/o4-mini-2025-04-16	15.1B	1,619,214	0.1%
112	Qwen3.5-122B-A10B	14.6B	1,094,408	0.1%
113	Z.ai: GLM 4.6	14.2B	1,658,230	0.1%
114	baai/bge-m3	13.8B	13,152,178	0.1%
115	nvidia/llama-nemotron-rerank-vl-1b-v2	13.8B	1,666,119	0.1%
116	MoonshotAI: Kimi K2 0905	13.8B	3,787,234	0.1%
117	meta-llama/llama-4-scout-17b-16e-instruct	13.5B	5,684,144	0.1%
118	Qwen: Qwen3 VL 32B Instruct	13.4B	4,610,086	0.1%
119	google/gemini-embedding-2	13.3B	11,403,630	0.1%
120	nvidia/nemotron-nano-9b-v2	13.3B	913,229	0.1%
121	Amazon: Nova Micro 1.0	13.3B	5,569,321	0.1%
122	Thinking Machines: Inkling	13.2B	781,009	0.1%
123	qwen/qwen3-coder-480b-a35b-07-25	13.0B	822,573	0.1%
124	GPT-4o	12.7B	6,162,533	0.1%
125	Qwen: Qwen3 VL 235B A22B Instruct	10.9B	3,506,292	0.1%
126	perplexity/pplx-embed-v1-0.6B	10.8B	10,338,433	0.1%
127	Qwen: Qwen3 VL 8B Instruct	10.7B	9,851,408	0.1%
128	Mistral: Mistral Small 3	10.6B	4,296,164	0.1%
129	google/gemini-embedding-001	10.5B	11,336,218	0.1%
130	mistralai/mistral-embed-2312	10.5B	1,849,558	0.1%
131	Google: Gemini 3.6 Flash	10.5B	532,651	0.1%
132	DeepSeek: R1 0528	9.9B	934,051	0.1%
133	nvidia/nemotron-nano-12b-v2-vl	9.3B	755,381	0.1%
134	qwen/qwen3-embedding-4b	9.3B	5,517,610	0.1%
135	Z.ai: GLM 4.5 Air	8.9B	1,058,337	0.1%
136	Nex AGI: Nex-N2-Mini	8.3B	1,043,042	0.1%
137	Z.ai: GLM 5 Turbo	7.9B	284,853	0.1%
138	Qwen: Qwen3 VL 30B A3B Instruct	7.6B	5,482,287	0.1%
139	OpenAI: GPT-5.3 Chat	7.3B	980,116	0.1%
140	qwen/qwen3.5-plus	7.2B	631,482	0.1%
141	Meta: Llama 3.1 70B Instruct	6.8B	8,019,751	0.1%
142	Inception: Mercury 2	6.7B	1,612,719	0.1%
143	AionLabs: Aion-3.0	6.5B	330,282	0.1%
144	Mistral: Mistral Large 3 2512	6.4B	1,816,602	0.1%
145	Amazon: Nova Lite 1.0	6.2B	1,009,730	0.1%
146	Sao10K: Llama 3 8B Lunaris	6.1B	2,884,857	0.1%
147	OpenAI: gpt-oss-safeguard-20b	6.0B	2,869,631	0.1%
148	mistralai/mistral-medium-3.5	5.9B	398,048	0.1%
149	Z.ai: GLM 5V Turbo	5.6B	256,084	0.1%
150	OpenAI: GPT-4o-mini (2024-07-18)	5.4B	3,172,101	0.0%
151	Google: Gemma 3 4B	5.1B	3,516,394	0.0%
152	nvidia/llama-nemotron-embed-vl-1b-v2	5.1B	3,215,028	0.0%
153	Mistral: Ministral 3 8B 2512	4.8B	3,047,989	0.0%
154	Qwen: Qwen3 Coder 30B A3B Instruct	4.5B	661,525	0.0%
155	Amazon: Nova 2 Lite	4.5B	1,202,990	0.0%
156	Google: Nano Banana (Gemini 2.5 Flash Image)	4.4B	1,688,962	0.0%
157	Qwen: Qwen3 235B A22B Thinking 2507	4.3B	372,205	0.0%
158	Meituan: LongCat 2.0	4.3B	65,122	0.0%
159	Qwen: Qwen2.5 VL 72B Instruct	4.3B	2,363,941	0.0%
160	google/gemini-embedding-2-preview	4.1B	5,705,754	0.0%
161	inclusionAI: Ling-2.6-1T	4.1B	101,474	0.0%
162	Nex AGI: Nex-N2-Pro	4.0B	133,625	0.0%
163	perplexity/pplx-embed-v1-4B	3.9B	5,115,257	0.0%
164	OpenAI: GPT-5.1-Codex-Mini	3.7B	180,477	0.0%
165	ByteDance Seed: Seed-2.0-Lite	3.6B	229,931	0.0%
166	qwen/qwen3-8b-04-28	3.6B	2,299,437	0.0%
167	Kwaipilot: KAT-Coder-Air V2.5	3.5B	209,338	0.0%
168	Perceptron: Perceptron Mk1	3.4B	312,375	0.0%
169	IBM: Granite 4.1 8B	3.4B	1,484,249	0.0%
170	inclusionAI: Ring-2.6-1T	3.4B	110,525	0.0%
171	xAI: Grok Build 0.1	3.3B	172,857	0.0%
172	Kimi K2	3.3B	497,004	0.0%
173	Google: Gemini 3.1 Pro Preview Custom Tools	3.2B	110,826	0.0%
174	Mistral: Devstral 2 2512	3.2B	594,941	0.0%
175	DeepSeek-R1	3.2B	502,496	0.0%
176	Google: Nano Banana 2 (Gemini 3.1 Flash Image)	3.1B	1,003,216	0.0%
177	Google: Gemini 3.5 Flash-Lite	3.0B	396,163	0.0%
178	StepFun: Step 3.5 Flash	3.0B	271,953	0.0%
179	Meta: Llama Guard 4 12B	2.9B	4,530,147	0.0%
180	mistralai/codestral-embed-2505	2.8B	250,985	0.0%
181	Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)	2.8B	603,046	0.0%
182	Kimi K2 Thinking	2.7B	211,934	0.0%
183	AionLabs: Aion-2.0	2.6B	237,604	0.0%
184	Sakana: Fugu Ultra	2.5B	29,562	0.0%
185	Anthropic: Claude 3 Haiku	2.5B	1,113,863	0.0%
186	OpenAI: GPT-5.1 Chat	2.5B	688,781	0.0%
187	Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview)	2.5B	974,328	0.0%
188	AionLabs: Aion-3.0-Mini	2.5B	191,989	0.0%
189	Mistral: Mistral Medium 3.1	2.4B	338,773	0.0%
190	bytedance-seed/seedream-4.5	2.4B	111,541	0.0%
191	xAI: Grok 4.20 Multi-Agent	2.3B	36,119	0.0%
192	OpenAI: GPT-5.2 Chat	2.3B	461,896	0.0%
193	qwen/qwen3-30b-a3b-04-28	2.3B	616,531	0.0%
194	OpenAI: GPT-4o (2024-11-20)	2.3B	362,248	0.0%
195	qwen/qwen3-14b-04-28	2.3B	1,774,403	0.0%
196	Nous: Hermes 4 70B	2.3B	841,686	0.0%
197	Perplexity: Sonar	2.2B	1,640,844	0.0%
198	Kwaipilot: KAT-Coder-Pro V2.5	2.2B	53,819	0.0%
199	intfloat/multilingual-e5-large	2.2B	2,399,237	0.0%
200	ByteDance Seed: Seed-2.0-Mini	2.2B	1,649,686	0.0%
201	Qwen2.5 72B Instruct	2.2B	1,611,739	0.0%
202	Mistral: Ministral 3 3B 2512	2.1B	1,802,305	0.0%
203	ByteDance Seed: Seed 1.6 Flash	2.0B	1,358,888	0.0%
204	Qwen: Qwen3 Coder Flash	2.0B	191,063	0.0%
205	OpenAI: GPT-4o (2024-08-06)	2.0B	1,365,882	0.0%
206	Mistral: Ministral 3 14B 2512	2.0B	1,293,188	0.0%
207	qwen/qwen3-235b-a22b-04-28	1.9B	391,593	0.0%
208	Qwen: Qwen3 Coder Plus	1.8B	91,363	0.0%
209	GPT Image 2	1.8B	643,537	0.0%
210	OpenAI: GPT-5.4 Image 2	1.8B	196,338	0.0%
211	Kwaipilot: KAT-Coder-Pro V2	1.7B	93,049	0.0%
212	Qwen3-Max	1.7B	367,684	0.0%
213	openai/gpt-5-chat-2025-08-07	1.6B	603,434	0.0%
214	nvidia/nemotron-3.5-content-safety	1.5B	581,116	0.0%
215	Google: Nano Banana Pro (Gemini 3 Pro Image Preview)	1.5B	592,413	0.0%
216	Google: Gemma 3n 4B	1.5B	2,424,388	0.0%
217	Mistral: Mistral Medium 3	1.4B	5,221,909	0.0%
218	anthropic/claude-4.7-opus-fast	1.4B	43,419	0.0%
219	OpenAI: GPT Chat Latest	1.3B	120,479	0.0%
220	MiniMax-M2.1	1.3B	113,866	0.0%
221	qwen/qwen-plus-2025-01-25	1.2B	324,464	0.0%
222	Mistral Large	1.2B	361,264	0.0%
223	MiniMax-M2	1.2B	88,433	0.0%
224	TheDrummer: Cydonia 24B V4.1	1.2B	338,280	0.0%
225	x-ai/grok-imagine-image-quality	1.2B	241,848	0.0%
226	baai/bge-base-en-v1.5	1.2B	2,667,317	0.0%
227	openai/text-embedding-ada-002	1.2B	3,252,558	0.0%
228	sentence-transformers/all-minilm-l6-v2	1.2B	991,286	0.0%
229	Arcee AI: Trinity Large Thinking	1.2B	88,528	0.0%
230	Claude Opus 4	1.1B	132,679	0.0%
231	OpenAI: GPT-5 Codex	1.1B	35,747	0.0%
232	Perplexity: Sonar Pro	1.1B	657,179	0.0%
233	Gemini 3 Pro Image (Nano Banana Pro)	1.1B	391,649	0.0%
234	Z.ai: GLM 4.5	1.0B	97,811	0.0%
235	GPT-5.2 Codex	1.0B	42,270	0.0%
236	Qwen: Qwen3.6 Max Preview	1.0B	121,542	0.0%
237	WizardLM-2 8x22B	986.1M	139,786	0.0%
238	openai/o3-mini-2025-01-31	961.2M	263,232	0.0%
239	Microsoft: Phi 4	906.3M	553,985	0.0%
240	MythoMax 13B	883.3M	753,802	0.0%
241	Meta: Llama 3.2 3B Instruct	879.7M	768,801	0.0%
242	openai/o3-2025-04-16	858.4M	170,261	0.0%
243	nvidia/nemotron-3-embed-1b	838.2M	628,410	0.0%
244	Meta: Llama 3.2 1B Instruct	781.3M	414,610	0.0%
245	GPT-5.1-Codex	685.3M	33,300	0.0%
246	GPT-5.5 Pro	628.6M	48,125	0.0%
247	Nous: Hermes 3 405B Instruct	598.1M	206,640	0.0%
248	Mistral: Codestral 2508	596.6M	197,344	0.0%
249	GPT-3.5 Turbo	548.4M	553,494	0.0%
250	TheDrummer: UnslopNemo 12B	544.6M	147,739	0.0%
251	black-forest-labs/flux.2-pro	520.4M	55,420	0.0%
252	mistralai/mistral-small-3.1-24b-instruct-2503	507.3M	367,212	0.0%
253	Nous: Hermes 4 405B	477.3M	115,406	0.0%
254	Qwen: Qwen3 30B A3B Thinking 2507	468.8M	96,933	0.0%
255	Qwen3-Max-Thinking	457.2M	114,654	0.0%
256	Claude Opus 4.1	430.1M	69,694	0.0%
257	qwen/qwen3-next-80b-a3b-thinking-2509	428.8M	77,377	0.0%
258	Perplexity: Sonar Pro Search	416.3M	152,276	0.0%
259	Qwen: Qwen3 VL 235B A22B Thinking	399.2M	63,060	0.0%
260	Nous: Hermes 3 70B Instruct	392.0M	160,854	0.0%
261	sao10k/l3.3-euryale-70b-v2.3	359.6M	169,762	0.0%
262	venice/uncensored	353.5M	125,683	0.0%
263	TheDrummer: Rocinante 12B	352.1M	131,060	0.0%
264	Qwen: Qwen3 VL 30B A3B Thinking	348.9M	57,561	0.0%
265	black-forest-labs/flux.2-klein-4b	344.9M	62,941	0.0%
266	GPT-5.1-Codex-Max	337.4M	20,041	0.0%
267	Upstage: Solar Pro 3	321.9M	46,397	0.0%
268	baai/bge-large-en-v1.5	318.1M	112,131	0.0%
269	Sao10K: Llama 3.1 Euryale 70B v2.2	307.1M	97,739	0.0%
270	Qwen: Qwen Plus 0728	277.0M	78,935	0.0%
271	Morph: Morph V3 Large	259.3M	24,744	0.0%
272	meta-llama/llama-3.2-11b-vision-instruct	244.1M	95,359	0.0%
273	sentence-transformers/all-mpnet-base-v2	243.4M	35,620	0.0%
274	MiniMax: MiniMax-01	238.1M	94,887	0.0%
275	ByteDance: UI-TARS 7B	229.9M	107,545	0.0%
276	OpenAI: GPT Audio Mini	229.2M	343,523	0.0%
277	MiniMax: MiniMax M2-her	227.5M	77,783	0.0%
278	thenlper/gte-base	205.7M	155,085	0.0%
279	OpenAI: GPT-5 Image Mini	202.8M	31,290	0.0%
280	Amazon: Nova Pro 1.0	199.8M	76,292	0.0%
281	google/gemini-3.1-flash-tts-preview	176.6M	390,011	0.0%
282	Mistral: Mixtral 8x22B Instruct	173.9M	49,091	0.0%
283	Mistral: Voxtral Small 24B 2507	172.3M	246,628	0.0%
284	Mistral Large 2407	168.5M	98,009	0.0%
285	TheDrummer: Skyfall 36B V2	163.9M	93,801	0.0%
286	Cohere: Command R (08-2024)	158.7M	163,590	0.0%
287	sentence-transformers/all-minilm-l12-v2	152.0M	1,276,487	0.0%
288	openai/gpt-4o-mini-transcribe	149.4M	565,470	0.0%
289	Google: Gemma 2 27B	144.8M	222,400	0.0%
290	OpenAI: GPT-4 Turbo	142.4M	215,996	0.0%
291	OpenAI: GPT-4o (2024-05-13)	139.4M	74,980	0.0%
292	Morph: Morph V3 Fast	135.5M	15,297	0.0%
293	Qwen: Qwen3 VL 8B Thinking	135.1M	34,995	0.0%
294	ByteDance Seed: Seed 1.6	128.5M	33,409	0.0%
295	MiniMax: MiniMax M1	128.5M	26,598	0.0%
296	ReMM SLERP 13B	128.5M	70,844	0.0%
297	Tencent: Hunyuan A13B Instruct	113.1M	27,456	0.0%
298	Perplexity: Sonar Deep Research	110.1M	17,190	0.0%
299	openai/o1-2024-12-17	108.4M	45,394	0.0%
300	Deep Cogito: Cogito v2.1 671B	105.6M	40,147	0.0%
301	intfloat/e5-large-v2	104.7M	371,522	0.0%
302	AI21: Jamba Large 1.7	101.5M	95,705	0.0%
303	Perplexity: Sonar Reasoning Pro	101.1M	40,666	0.0%
304	OpenAI: GPT-5 Image	96.6M	16,622	0.0%
305	Cohere: Command R+ (08-2024)	95.7M	113,204	0.0%
306	black-forest-labs/flux.2-max	91.6M	6,653	0.0%
307	Cohere: Command R7B (12-2024)	82.2M	56,460	0.0%
308	DeepSeek: R1 Distill Llama 70B	80.0M	41,296	0.0%
309	openai/o4-mini-high-2025-04-16	78.8M	29,634	0.0%
310	Google: Lyria 3 Pro Preview	71.9M	121,262	0.0%
311	Z.ai: GLM 4.5V	67.8M	35,468	0.0%
312	nvidia/llama-3.3-nemotron-super-49b-v1.5	66.6M	42,664	0.0%
313	hexgrad/kokoro-82m	66.1M	387,877	0.0%
314	MAI-Image-2.5	65.8M	39,444	0.0%
315	OpenAI: GPT-4	62.0M	77,936	0.0%
316	Magnum v4 72B	61.9M	26,411	0.0%
317	openai/gpt-4o-transcribe	61.4M	125,375	0.0%
318	black-forest-labs/flux.2-flex	58.5M	6,676	0.0%
319	Amazon: Nova Premier 1.0	52.5M	26,586	0.0%
320	sourceful/riverflow-v2.5-fast	46.6M	10,907	0.0%
321	OpenAI: GPT Audio	45.1M	107,316	0.0%
322	cohere/command-a-03-2025	44.5M	45,111	0.0%
323	Baidu: ERNIE 4.5 VL 424B A47B	44.5M	32,880	0.0%
324	openai/gpt-4o-mini-search-preview-2025-03-11	43.6M	41,900	0.0%
325	sourceful/riverflow-v2-fast	42.3M	9,701	0.0%
326	Writer: Palmyra X5	41.2M	20,116	0.0%
327	openai/gpt-4o-search-preview-2025-03-11	40.4M	58,109	0.0%
328	GPT-5.4 Pro	33.1M	18,569	0.0%
329	Reka Flash 3	32.1M	13,082	0.0%
330	mistralai/mistral-saba-2502	30.4M	20,585	0.0%
331	openai/o4-mini-deep-research-2025-06-26	28.6M	1,908	0.0%
332	gpt-image-1	28.1M	11,516	0.0%
333	Qwen2.5 Coder 32B Instruct	27.8M	44,551	0.0%
334	openai/o3-deep-research-2025-06-26	26.9M	1,735	0.0%
335	GPT-5.2 Pro	24.8M	15,224	0.0%
336	sentence-transformers/paraphrase-minilm-l6-v2	23.3M	9,727	0.0%
337	Relace: Relace Apply 3	22.8M	2,980	0.0%
338	thenlper/gte-large	22.0M	39,419	0.0%
339	openai/o3-mini-high-2025-01-31	21.1M	9,071	0.0%
340	openai/gpt-image-1-mini	17.7M	7,571	0.0%
341	rekaai/reka-edge-2603	13.1M	14,793	0.0%
342	sourceful/riverflow-v2.5-pro	12.9M	2,831	0.0%
343	AionLabs: Aion-RP 1.0 (8B)	12.4M	12,883	0.0%
344	recraft/recraft-v4.1	11.9M	2,623	0.0%
345	OpenAI: GPT-3.5 Turbo (older v0613)	11.9M	31,394	0.0%
346	krea/krea-2-medium-turbo	11.1M	2,663	0.0%
347	openai/gpt-5-pro-2025-10-06	10.6M	5,227	0.0%
348	mistralai/voxtral-mini-transcribe-2602	9.9M	167,243	0.0%
349	recraft/recraft-v4	9.3M	2,152	0.0%
350	recraft/recraft-v4.1-utility	8.5M	1,846	0.0%
351	recraft/recraft-v4.1-vector	8.4M	1,953	0.0%
352	Relace: Relace Search	8.1M	10,074	0.0%
353	Google: Lyria 3 Clip Preview	7.6M	5,351	0.0%
354	openai/o3-pro-2025-06-10	6.3M	4,484	0.0%
355	sourceful/riverflow-v2-pro	5.9M	867	0.0%
356	x-ai/grok-voice-tts-1.0	5.8M	172,616	0.0%
357	GPT-3.5 Turbo Instruct	5.4M	18,842	0.0%
358	Mancer: Weaver (alpha)	5.2M	9,565	0.0%
359	krea/krea-2-large	5.1M	1,226	0.0%
360	OpenAI: GPT-3.5 Turbo 16k	5.1M	12,682	0.0%
361	recraft/recraft-v4.1-pro-vector	4.0M	924	0.0%
362	intfloat/e5-base-v2	2.4M	7,751	0.0%
363	recraft/recraft-v4-pro	2.3M	497	0.0%
364	microsoft/mai-voice-2	2.3M	28,002	0.0%
365	recraft/recraft-v3	2.3M	512	0.0%
366	krea/krea-2-medium	2.1M	509	0.0%
367	recraft/recraft-v4.1-pro	2.1M	474	0.0%
368	o1-pro	1.7M	5,954	0.0%
369	recraft/recraft-v4.1-utility-pro	1.3M	308	0.0%
370	recraft/recraft-v4-vector	777,355	181	0.0%
371	recraft/recraft-v4-pro-vector	454,115	102	0.0%
372	deepgram/aura-2	427,114	8,661	0.0%
373	sentence-transformers/multi-qa-mpnet-base-dot-v1	416,299	515	0.0%
374	perplexity/pplx-embed-v1-0.6b	347,847	1,406	0.0%
375	mistralai/voxtral-mini-tts-2603	303,057	4,562	0.0%
376	Qwen/Qwen3-Embedding-8B	166,891	3,509	0.0%
377	minimax/speech-2.8-hd	155,940	3,321	0.0%
378	minimax/speech-2.8-turbo	107,595	4,202	0.0%
379	canopylabs/orpheus-3b-0.1-ft	56,514	1,673	0.0%
380	sesame/csm-1b	17,921	580	0.0%
381	zyphra/zonos-v0.1-hybrid	5,526	261	0.0%
382	zyphra/zonos-v0.1-transformer	4,042	131	0.0%
383	BAAI/bge-base-en-v1.5	945	46	0.0%
384	alibaba/happyhorse-1.0	0	195	0.0%
385	alibaba/happyhorse-1.1	0	5,370	0.0%
386	alibaba/wan-2.6	0	669	0.0%
387	alibaba/wan-2.7	0	2,448	0.0%
388	bytedance/seedance-1-5-pro	0	5,928	0.0%
389	Seedance 2.0	0	22,873	0.0%
390	bytedance/seedance-2.0-fast	0	8,829	0.0%
391	cohere/rerank-4-fast	0	475,888	0.0%
392	cohere/rerank-4-pro	0	316,947	0.0%
393	cohere/rerank-v3.5	0	658,689	0.0%
394	deepgram/nova-3	0	5,280	0.0%
395	google/chirp-3	0	47,867	0.0%
396	Veo 3.1	0	16,177	0.0%
397	google/veo-3.1-fast	0	39,339	0.0%
398	google/veo-3.1-lite	0	15,658	0.0%
399	kwaivgi/kling-v3.0-pro	0	4,211	0.0%
400	kwaivgi/kling-v3.0-std	0	4,605	0.0%
401	kwaivgi/kling-video-o1	0	302	0.0%
402	microsoft/mai-transcribe-1.5	0	66,367	0.0%
403	minimax/hailuo-2.3	0	291	0.0%
404	nvidia/parakeet-tdt-0.6b-v3	0	334,726	0.0%
405	openai/sora-2-pro	0	191	0.0%
406	openai/whisper-1	0	152,137	0.0%
407	openai/whisper-large-v3	0	2,271,088	0.0%
408	openai/whisper-large-v3-turbo	0	1,006,138	0.0%
409	Body Builder (beta)	0	6,352	0.0%
410	qwen/qwen3-asr-flash-2026-02-10	0	224,932	0.0%
411	x-ai/grok-imagine-video	0	7,837	0.0%
412	x-ai/grok-imagine-video-1.5	0	807	0.0%

Usage board questions

What does this board measure?

OpenRouter's own weekly routed token volume per model: the prompt and completion tokens of traffic developers routed through the platform, summed across a model's listing variants. It measures where routed work goes on one platform, not how good a model is.

Why lead with usage instead of a benchmark?

Usage is a live demand signal. A model nobody routes work through falls off this board on its own, while benchmark boards can keep retired models near the top for months. Model Gauntlet publishes both views side by side and never blends them.

Why is a model missing or unlinked?

Only models OpenRouter's week view lists appear, retrieved July 22, 2026. Rows without a reviewed identity match stay under the platform's own listing name without a profile link rather than being guessed.