What is the most used AI model for coding?

Measured by real token burn from developers' machines on whoburnedmore, the top-ranked model on this page currently leads real coding usage. Unlike benchmark leaderboards, this ranking reflects what developers actually run in Claude Code, Codex, Cursor, Gemini CLI and other coding agents.

How is this different from OpenRouter's model rankings?

OpenRouter ranks models by API traffic routed through its gateway. This page measures usage that never touches an API gateway — subscription products like Claude Code Max plans, Cursor and Codex — read directly from the local usage logs those tools keep, via the open-source whoburnedmore CLI.

Where does this data come from?

From developers who run npx whoburnedmore and choose to be listed publicly. The CLI reads each coding agent's own local logs and submits daily aggregate token totals per tool and model — never prompts, code, or file names.

AI Model Usage Rankings — Real Coding Data, Not Benchmarks

#	Model	Devs	Tokens	Share	Input	Output	Cache	Est cost
01	gpt-5.6-solCodex CLI · Hermes · OpenCode +3	133	821.67B	24%	23.73B	2.42B	97%	$520,710
02	claude-opus-5Claude Code · Hermes · Cline +3	149	512.25B	15%	361.4M	1.90B	100%	$367,202
03	claude-opus-4-8Claude Code · OpenCode · Hermes +3	184	411.19B	12%	5.63B	2.91B	99%	$427,118
04	gpt-5.5Codex CLI · OpenCode · Hermes +2	207	287.75B	8.3%	15.36B	1.01B	95%	$322,039
05	claude-sonnet-5Claude Code · Hermes	156	183.60B	5.3%	94.1M	723.0M	100%	$54,809
06	claude-fable-5Claude Code · OpenCode · Cline	144	142.15B	4.1%	2.66B	1.02B	98%	$248,149
07	claude-opus-4-7Claude Code · OpenCode · Anthropic Api +1	95	116.40B	3.3%	144.1M	391.6M	100%	$97,140
08	gpt-6-astraCodex CLI · Hermes · OpenCode +1	104	89.00B	2.6%	2.58B	315.1M	97%	$9,142
09	claude-opus-5-5Claude Code	77	67.92B	1.9%	599.2K	219.2M	100%	$25,747
10	defaultCursor · OpenCode	117	65.48B	1.9%	3.98B	395.9M	94%	$30,944
11	gpt-5.4Codex CLI · OpenCode · Hermes +1	132	54.01B	1.5%	6.02B	270.1M	89%	$42,628
12	gpt-5.6-terraCodex CLI · Hermes · Claude Code +2	143	53.54B	1.5%	2.11B	187.2M	96%	$26,855
13	gpt-5.6-lunaCodex CLI · Claude Code · Hermes +3	118	52.92B	1.5%	2.70B	177.2M	95%	$13,298
14	claude-sonnet-4-6Claude Code · Cursor · OpenCode +4	141	35.60B	1.0%	571.3M	436.0M	98%	$24,781
15	claude-fable-5-1Claude Code · Hermes	66	34.97B	1.0%	17.9M	173.1M	100%	$30,952
16	unreportedFactory Droid · OpenCode · Openclaw +9	87	29.42B	0.8%	8.00B	116.3M	72%	$12,336
17	gpt-5.3-codexCodex CLI · OpenCode · Cursor +2	109	29.11B	0.8%	2.18B	266.3M	92%	$12,963
18	claude-opus-4-6Claude Code · OpenCode · Amp +2	53	28.44B	0.8%	311.3M	217.2M	99%	$37,368
19	claude-opus-4-8-thinkingOpenCode · Claude Code	1	18.62B	0.5%	12.9M	25.7M	100%	$12,781
20	claude-haiku-4-5-20251001Claude Code · Anthropic Api · Amp +1	183	17.45B	0.5%	67.3M	143.0M	100%	$3,971
21	gpt-6-solCodex CLI · OpenCode · Hermes	33	16.10B	0.5%	234.1M	32.4M	99%	$1,046
22	gpt-5Codex CLI · Cursor · OpenCode	78	14.09B	0.4%	568.7M	44.9M	96%	$1,587
23	composer-2.5-fastCursor · OpenCode	79	12.66B	0.4%	793.0M	86.0M	94%	$9,454
24	deepseek-v4-flashOpenCode · Hermes · Claude Code +2	44	11.29B	0.3%	540.1M	36.0M	95%	$108
25	deepseek-v4-flash-freeOpenCode · Hermes · Claude Code	50	11.28B	0.3%	425.7M	53.2M	96%	$1.2
26	gpt-daybreak-blue-latestCodex CLI	8	11.24B	0.3%	320.6M	41.0M	97%	$1,738
27	claude-4.6-sonnet-medium-thinkingCursor	41	10.90B	0.3%	73.7M	81.4M	99%	$6,754
28	gpt-5-codexCodex CLI · Cursor	31	10.58B	0.3%	413.3M	51.5M	96%	$2,815
29	claude-4.6-opus-high-thinkingCursor	44	10.15B	0.3%	100.1M	56.0M	99%	$9,410
30	cursor-grok-4.6-high-fastCursor	37	9.96B	0.3%	730.0M	64.1M	93%	$12,700
31	gemini-3.7-flashClaude Code · OpenCode	3	8.90B	0.3%	7.99B	3.6M	10%	$6,010
32	codex-auto-reviewCodex CLI	47	8.73B	0.3%	468.9M	22.1M	95%	$1,040
33	x-preview-f-freeOpenCode · Hermes	36	7.87B	0.2%	387.9M	21.9M	95%	$0
34	gpt-5.2-codexCodex CLI · OpenCode · Cursor +1	64	6.92B	0.2%	381.8M	47.0M	94%	$2,581
35	cursor-grok-4.6-highCursor	32	6.58B	0.2%	496.9M	38.8M	92%	$4,244
36	gpt-5.5-mediumCursor	37	6.46B	0.2%	441.5M	14.3M	93%	$6,941
37	grok-bot-defaultCursor	27	6.32B	0.2%	856.3M	38.9M	86%	$9,461
38	cursor-grok-4.5-high-fastCursor	36	6.28B	0.2%	529.8M	47.5M	92%	$8,545
39	claude-4.5-opus-high-thinkingCursor	38	5.98B	0.2%	55.6M	40.5M	99%	$5,472
40	composer-2.5Cursor	36	5.73B	0.2%	356.9M	42.1M	94%	$1,369
41	claude-opus-4-8-thinking-highCursor	36	5.69B	0.2%	25.6M	29.6M	100%	$5,254
42	gpt-realtime-1.5Openai Api	1	5.38B	0.2%	2.89B	10.1M	46%	$465
43	claude-4.5-opus-highCursor	8	5.22B	0.1%	55.5M	25.3M	99%	$4,607
44	muse-spark-1.3-contributor-freeOpenCode · Hermes	26	5.11B	0.1%	241.3M	8.9M	95%	$0
45	composer-2-fastCursor	50	4.95B	0.1%	388.1M	32.4M	92%	$2,106
46	gpt-5.5-highCursor	18	4.82B	0.1%	299.5M	19.6M	94%	$4,279
47	claude-4-sonnet-thinkingCursor	31	4.61B	0.1%	43.2M	42.0M	99%	$3,426
48	deepseek-v4-proOpenCode · Claude Code · Hermes +2	38	4.49B	0.1%	108.3M	10.5M	98%	$132
49	gpt-6-lunaCodex CLI · OpenCode · Hermes	31	4.42B	0.1%	100.4M	16.9M	98%	$133
50	glm-5.2OpenCode · Claude Code · Hermes +3	32	4.32B	0.1%	527.9M	27.5M	88%	$1,365
51	claude-4-sonnetCursor	35	4.05B	0.1%	38.1M	24.2M	99%	$2,384
52	deepseek-v4.1-flashHermes · OpenCode · Codex CLI	12	4.04B	0.1%	87.2M	24.7M	98%	$12.27
53	claude-opus-5-thinkingClaude Code · OpenCode	2	4.01B	0.1%	498.4M	8.3M	87%	$3,978
54	rollupClaude Code	4	4.00B	0.1%	4.00B	0	0.0%	$3,429
55	gpt-5.4-miniCodex CLI · OpenCode · Hermes +1	81	3.94B	0.1%	426.6M	26.6M	89%	$1,318
56	claude-opus-4-7-thinking-xhighCursor	28	3.80B	0.1%	13.8M	16.7M	100%	$3,660
57	grok-bot-cuaCursor	19	3.79B	0.1%	22.0M	10.7M	99%	$395
58	k3Kimi CLI · Claude Code · OpenCode	6	3.66B	0.1%	117.4M	20.5M	97%	$1,702
59	claude-opus-5-thinking-highCursor	21	3.55B	0.1%	22.4M	18.3M	99%	$2,917
60	minimax-m3OpenCode · Codex CLI · Hermes +1	20	3.49B	0.1%	189.9M	12.0M	95%	$279

AI MODEL USAGE RANKINGS — real coding burn, all time

Models by real token burn

Daily burn × model

AI MODEL USAGE RANKINGS — real coding burn, all time

▮Models by real token burn

▮Daily burn × model

Models by real token burn

Daily burn × model