The cheapest LLM API on the internet.

cat surp.ivc.lol | grep -i "what is this"

surp.ivc.lol is an x402-paywalled LLM gateway. You pay per request in USDC on Base — no account, no API key, no subscription. Behind the scenes we aggregate Surplus Intelligence (itself a marketplace of competing sellers) and route every request to whichever model is cheapest right now for the class of work you asked for.

You ask for surp/best-coding. We fetch live Surplus market prices, find the cheapest coding-class model at this instant, forward your request there, and stream the answer back. The price you pay is the Surplus spot price + a small markup, settled on-chain in micropennies.

client ──▶ surp.ivc.lol (x402 gateway) ──▶ Surplus Intelligence (seller market) ──▶ {cheapest model} ▲ ▲ ▲ │ │ │ │ verifies + live price book │ settles USDC (145+ models, │ on Base 76 active listings) └─── response streams back ◀── response ◀──────

live ticker — what each combo routes to right now

Live — refreshed every 30s from GET api.surplusintelligence.ai/api/markets. Current snapshot: 337 listings, of which 152 are text/chat LLMs.

surp/best-coding→kimi-k2.7-code$0.4664/1M-95%6 models

cheapest coding-class model (coder / codex / qwen3-coder) — compares 6 model(s), routes to the cheapest. click any row to see the full list.

#	model	class	USD / 1M tok	sellers
1	kimi-k2.7-code ◀ routed now	coding	$0.4664	15
2	qwen3-coder-turbo	coding	$0.9116	26
3	qwen3-coder	coding	$1.0100	17
4	kimi-k2.7-code:web	coding	$1.3497	3
5	gpt-5.2-codex	coding	$2.3625	55
6	gpt-5.3-codex	coding	$3.9375	65

surp/best-reasoning→qwen3-235b-a22b-thinking-2507$0.0500/1M-99%8 models

cheapest reasoning model (thinking / r1) — compares 8 model(s), routes to the cheapest. click any row to see the full list.

#	model	class	USD / 1M tok	sellers
1	qwen3-235b-a22b-thinking-2507 ◀ routed now	reasoning	$0.0500	40
2	glm-4.7-thinking	reasoning	$0.6125	2
3	glm-4.7-thinking:web	reasoning	$0.6125	2
4	trinity-large-thinking	reasoning	$0.9344	18
5	trinity-large-thinking:web	reasoning	$1.0781	1
6	kimi-k2-thinking	reasoning	$1.5500	7
7	glm-5.1-non-thinking:web	reasoning	$1.6250	5
8	deepseek-r1	reasoning	$2.4934	7

surp/best-fast→gemini-2.5-flash-image$0.0500/1M-99%34 models

cheapest small/fast model (mini / nano / lite / small) — compares 34 model(s), routes to the cheapest. click any row to see the full list.

#	model	class	USD / 1M tok	sellers
1	gemini-2.5-flash-image ◀ routed now	fast	$0.0500	9
2	qwen3-5-9b	fast	$0.0500	34
3	gpt-5.4-mini	fast	$0.0525	62
4	nvidia-nemotron-3-nano-30b-a3b	fast	$0.0938	41
5	llama-3.2-3b-instruct	fast	$0.0965	35
6	gemma-4-26b-a4b-it	fast	$0.1100	58
7	mistral-small-3.2-24b-instruct:web	fast	$0.1134	3
8	glm-4.5-air	fast	$0.1300	8
9	minimax-m2.5	fast	$0.1500	41
10	mistral-small-3.2-24b-instruct	fast	$0.1787	24
11	llama-3.2-3b-instruct:web	fast	$0.1875	7
12	mistral-small-4	fast	$0.2344	28
13	gpt-4o-mini	fast	$0.2623	60
14	qwen3-next-80b-a3b-instruct	fast	$0.2975	45
15	magistral-small-2509	fast	$0.3000	1
16	gpt-5-image-mini	fast	$0.3739	8
17	minimax-m2.5:web	fast	$0.3825	7
18	gpt-5-nano	fast	$0.4048	10
19	minimax-m2.7	fast	$0.4271	21
20	gemma-4-26b-a4b-it:web	fast	$0.4439	2
21	minimax-m2.7:web	fast	$0.4688	3
22	qwen3-next-80b-a3b-instruct:web	fast	$0.5625	8
23	minimax-m2.1	fast	$0.6200	9
24	gpt-5.4-nano	fast	$1.1773	11
25	gemini-2.5-flash	fast	$1.4000	10
26	gemini-3.1-flash-lite	fast	$1.4962	8
27	minimax-m3	fast	$1.5000	8
28	gemini-2.5-pro	fast	$1.6875	12
29	gemini-3-flash-preview	fast	$1.7500	33
30	gpt-5-mini	fast	$2.0248	10
31	minimax-m2.7-highspeed	fast	$2.7000	4
32	gemini-3-5-flash	fast	$5.2500	30
33	gemini-3.1-pro-preview	fast	$6.9300	29
34	gemini-3.1-pro	fast	$12.6000	3

surp/best-vision→qwen3-vl-235b-a22b-thinking$0.7150/1M-92%3 models

cheapest multimodal vision model (-vl / vision / 5v) — compares 3 model(s), routes to the cheapest. click any row to see the full list.

#	model	class	USD / 1M tok	sellers
1	qwen3-vl-235b-a22b-thinking ◀ routed now	vision	$0.7150	28
2	qwen3-vl-30b-a3b-thinking	vision	$1.3200	10
3	glm-5v-turbo	vision	$1.6250	26

surp/best-chat→glm-5.2$0.0300/1M-100%135 models

cheapest general text LLM (no specialization) — compares 135 model(s), routes to the cheapest. click any row to see the full list.

#	model	class	USD / 1M tok	sellers
1	glm-5.2 ◀ routed now	chat	$0.0300	39
2	deepseek-v4-flash	chat	$0.0401	49
3	llama-3.3-70b-instruct	chat	$0.0420	64
4	e2ee-qwen-2-5-7b-p	chat	$0.0450	26
5	gemini-2.5-flash-image	fast	$0.0500	9
6	qwen3-5-9b	fast	$0.0500	34
7	gpt-5.4-mini	fast	$0.0525	62
8	e2ee-gpt-oss-20b-p	chat	$0.0600	21
9	e2ee-venice-uncensored-24b-p	chat	$0.0700	57
10	nvidia-nemotron-3-nano-30b-a3b	fast	$0.0938	41
11	qwen3-235b-a22b-2507	chat	$0.0950	35
12	llama-3.2-3b-instruct	fast	$0.0965	35
13	venice-uncensored	chat	$0.0990	6
14	gemma-4-26b-a4b-it	fast	$0.1100	58
15	mistral-small-3.2-24b-instruct:web	fast	$0.1134	3
16	venice-uncensored-role-play	chat	$0.1250	59
17	glm-4.5-air	fast	$0.1300	8
18	openai-gpt-oss-120b	chat	$0.1490	36
19	minimax-m2.5	fast	$0.1500	41
20	gemma-3-27b-it	chat	$0.1560	27
21	e2ee-gemma-3-27b	chat	$0.1600	27
22	glm-4.7-flash:web	chat	$0.1700	2
23	deepseek-v4-flash:web	chat	$0.1716	4
24	gpt-5.4	chat	$0.1750	44
25	gpt-5.6-terra	chat	$0.1750	40
26	mistral-small-3.2-24b-instruct	fast	$0.1787	24
27	llama-3.2-3b-instruct:web	fast	$0.1875	7
28	deepseek-v4-pro	chat	$0.1958	45
29	qwen3-30b-a3b	chat	$0.2046	53
30	glm-4.7	chat	$0.2150	78
31	glm-4.6	chat	$0.2170	86
32	gemma-4-31b-it:web	chat	$0.2228	3
33	qwen3-235b-a22b-2507:web	chat	$0.2250	7
34	mistral-small-4	fast	$0.2344	28
35	glm-4.7-flash-heretic	chat	$0.2350	38
36	openai-gpt-oss-120b:web	chat	$0.2479	3
37	e2ee-gemma-4-31b	chat	$0.2500	44
38	glm-5	chat	$0.2520	87
39	gemma-4-31b-it	chat	$0.2610	28
40	gpt-4o-mini	fast	$0.2623	60
41	venice-uncensored-1.2	chat	$0.2750	20
42	glm-4.5	chat	$0.2800	6
43	qwen3-next-80b-a3b-instruct	fast	$0.2975	45
44	glm-4.7-flash	chat	$0.2990	19
45	magistral-small-2509	fast	$0.3000	1
46	deepseek-v3.2	chat	$0.3264	29
47	gpt-5.5	chat	$0.3500	71
48	e2ee-gemma-4-26b-a4b-uncensored-p	chat	$0.3625	27
49	gpt-5-image-mini	fast	$0.3739	8
50	minimax-m2.5:web	fast	$0.3825	7
51	qwen3-5-35b-a3b	chat	$0.3906	33
52	gpt-5-nano	fast	$0.4048	10
53	e2ee-qwen3-5-122b-a10b	chat	$0.4050	7
54	minimax-m2.7	fast	$0.4271	21
55	gemma-4-uncensored	chat	$0.4306	22
56	grok-4.1-fast	chat	$0.4375	7
57	e2ee-glm-4.7-flash	chat	$0.4420	5
58	gemma-4-26b-a4b-it:web	fast	$0.4439	2
59	nvidia-nemotron-3-ultra-550b-a55b	chat	$0.4500	57
60	qwen3.5-flash	chat	$0.4500	9
61	minimax-m2.7:web	fast	$0.4688	3
62	gpt-5.6-luna	chat	$0.4900	41
63	e2ee-qwen3-6-35b-a3b	chat	$0.4998	42
64	e2ee-gpt-oss-120b-p	chat	$0.5069	20
65	nvidia-nemotron-cascade-2-30b-a3b	chat	$0.5170	4
66	glm-5-turbo	chat	$0.5200	92
67	qwen3-next-80b-a3b-instruct:web	fast	$0.5625	8
68	glm-5.1	chat	$0.5800	45
69	qwen-3-7-plus	chat	$0.6000	46
70	minimax-m2.1	fast	$0.6200	9
71	mercury-2	chat	$0.8124	22
72	llama-3.3-70b-instruct:web	chat	$0.8750	7
73	grok-4.20-multi-agent-beta	chat	$0.9375	31
74	kimi-k2.5:web	chat	$1.0150	8
75	kimi-k2.6	chat	$1.0175	37
76	hermes-3-llama-3.1-405b	chat	$1.0250	45
77	qwen3.6-plus-uncensored	chat	$1.0938	30
78	gpt-5.4-nano	fast	$1.1773	11
79	gpt-5.4-image-2	chat	$1.2158	8
80	gpt-5.6-sol	chat	$1.2200	40
81	glm-5:web	chat	$1.3125	8
82	e2ee-glm-5.1	chat	$1.3125	30
83	glm-4.7:web	chat	$1.3125	2
84	gemini-2.5-flash	fast	$1.4000	10
85	grok-code-fast-1	chat	$1.4450	3
86	gemini-3.1-flash-lite	fast	$1.4962	8
87	gpt-5-image	chat	$1.5000	3
88	minimax-m3	fast	$1.5000	8
89	qwen3.6-27b	chat	$1.5214	37
90	kimi-k2.5	chat	$1.5600	26
91	qwen3.5-plus	chat	$1.6380	11
92	gemini-2.5-pro	fast	$1.6875	12
93	gemini-3-flash-preview	fast	$1.7500	33
94	aion-labs.aion-2-0	chat	$1.8000	17
95	glm-5.1:web	chat	$1.8125	5
96	deepseek-v4-pro:web	chat	$1.8236	3
97	grok-4.20-beta	chat	$1.8750	24
98	grok-build-0-1	chat	$1.9880	47
99	gpt-5-mini	fast	$2.0248	10
100	e2ee-qwen3-6-35b-a3b-uncensored-p	chat	$2.0800	8
101	gpt-5.6-terra-pro	chat	$2.1000	34
102	mistral-large	chat	$2.1250	11
103	gpt-5.6-luna-pro	chat	$2.2000	31
104	qwen3.5-397b-a17b	chat	$2.2343	36
105	gpt-5.2	chat	$2.3625	66
106	kimi-k2	chat	$2.5830	7
107	minimax-m2.7-highspeed	fast	$2.7000	4
108	grok-4.3	chat	$2.7621	20
109	claude-opus-4.6	chat	$3.0000	39
110	qwen-3-7-max	chat	$3.4046	25
111	e2ee-glm-4.7	chat	$3.4125	5
112	kimi-k2.6:web	chat	$3.6883	5
113	grok-4.5	chat	$3.7203	8
114	gpt-4o	chat	$4.3748	62
115	claude-haiku-4.5	chat	$4.6360	12
116	gemini-3-5-flash	fast	$5.2500	30
117	claude-sonnet-5	chat	$6.8470	28
118	gemini-3.1-pro-preview	fast	$6.9300	29
119	claude-opus-4.7	chat	$7.5000	43
120	claude-sonnet-4.5	chat	$8.2650	41
121	claude-sonnet-4.6	chat	$8.2650	25
122	kimi-k3	chat	$10.4895	20
123	gemini-3.1-pro	fast	$12.6000	3
124	claude-opus-5-fast	chat	$15.0000	12
125	grok-4	chat	$15.3000	3
126	claude-opus-4.8	chat	$17.0469	58
127	claude-opus-5	chat	$17.1175	17
128	claude-opus-4-8-fast	chat	$17.2800	51
129	claude-opus-4.5	chat	$17.8821	35
130	gpt-5.6-sol-pro	chat	$19.2308	20
131	gpt-5.4-pro	chat	$31.5000	80
132	claude-fable-5	chat	$35.4444	45
133	claude-opus-4.6-fast	chat	$54.0000	31
134	gpt-5.5-pro	chat	$65.6250	61
135	claude-opus-4-7-fast	chat	$71.2800	23

surp/best-coding-fast→kimi-k2.7-code$0.4664/1M-95%6 models

cheapest coding model, biased to small/fast variants — compares 6 model(s), routes to the cheapest. click any row to see the full list.

#	model	class	USD / 1M tok	sellers
1	kimi-k2.7-code ◀ routed now	coding	$0.4664	15
2	qwen3-coder-turbo	coding	$0.9116	26
3	qwen3-coder	coding	$1.0100	17
4	kimi-k2.7-code:web	coding	$1.3497	3
5	gpt-5.2-codex	coding	$2.3625	55
6	gpt-5.3-codex	coding	$3.9375	65

surp/pro-coding→qwen3-coder-turbo$0.9116/1M-90%4 models

cheapest FRONTIER-tier coding model — compares 4 model(s), routes to the cheapest. click any row to see the full list.

#	model	class	USD / 1M tok	sellers
1	qwen3-coder-turbo ◀ routed now	coding	$0.9116	26
2	qwen3-coder	coding	$1.0100	17
3	gpt-5.2-codex	coding	$2.3625	55
4	gpt-5.3-codex	coding	$3.9375	65

surp/pro-reasoning→deepseek-r1$2.4934/1M-72%1 models

cheapest FRONTIER-tier reasoning model — compares 1 model(s), routes to the cheapest. click any row to see the full list.

#	model	class	USD / 1M tok	sellers
1	deepseek-r1 ◀ routed now	reasoning	$2.4934	7

surp/pro-vision→qwen3-vl-235b-a22b-thinking$0.7150/1M-92%3 models

cheapest FRONTIER-tier vision model — compares 3 model(s), routes to the cheapest. click any row to see the full list.

#	model	class	USD / 1M tok	sellers
1	qwen3-vl-235b-a22b-thinking ◀ routed now	vision	$0.7150	28
2	qwen3-vl-30b-a3b-thinking	vision	$1.3200	10
3	glm-5v-turbo	vision	$1.6250	26

surp/pro-chat→gpt-5.6-terra$0.1750/1M-98%34 models

cheapest FRONTIER-tier chat model — compares 34 model(s), routes to the cheapest. click any row to see the full list.

#	model	class	USD / 1M tok	sellers
1	gpt-5.6-terra ◀ routed now	chat	$0.1750	40
2	gpt-5.5	chat	$0.3500	71
3	grok-4.1-fast	chat	$0.4375	7
4	gpt-5.6-luna	chat	$0.4900	41
5	grok-4.20-multi-agent-beta	chat	$0.9375	31
6	gpt-5.6-sol	chat	$1.2200	40
7	gemini-2.5-pro	fast	$1.6875	12
8	grok-4.20-beta	chat	$1.8750	24
9	grok-build-0-1	chat	$1.9880	47
10	gpt-5.6-terra-pro	chat	$2.1000	34
11	gpt-5.6-luna-pro	chat	$2.2000	31
12	qwen3.5-397b-a17b	chat	$2.2343	36
13	grok-4.3	chat	$2.7621	20
14	claude-opus-4.6	chat	$3.0000	39
15	grok-4.5	chat	$3.7203	8
16	claude-sonnet-5	chat	$6.8470	28
17	gemini-3.1-pro-preview	fast	$6.9300	29
18	claude-opus-4.7	chat	$7.5000	43
19	claude-sonnet-4.5	chat	$8.2650	41
20	claude-sonnet-4.6	chat	$8.2650	25
21	kimi-k3	chat	$10.4895	20
22	gemini-3.1-pro	fast	$12.6000	3
23	claude-opus-5-fast	chat	$15.0000	12
24	grok-4	chat	$15.3000	3
25	claude-opus-4.8	chat	$17.0469	58
26	claude-opus-5	chat	$17.1175	17
27	claude-opus-4-8-fast	chat	$17.2800	51
28	claude-opus-4.5	chat	$17.8821	35
29	gpt-5.6-sol-pro	chat	$19.2308	20
30	gpt-5.4-pro	chat	$31.5000	80
31	claude-fable-5	chat	$35.4444	45
32	claude-opus-4.6-fast	chat	$54.0000	31
33	gpt-5.5-pro	chat	$65.6250	61
34	claude-opus-4-7-fast	chat	$71.2800	23

surp/pro-fast→gemini-2.5-pro$1.6875/1M-81%3 models

cheapest FRONTIER-tier fast model — compares 3 model(s), routes to the cheapest. click any row to see the full list.

#	model	class	USD / 1M tok	sellers
1	gemini-2.5-pro ◀ routed now	fast	$1.6875	12
2	gemini-3.1-pro-preview	fast	$6.9300	29
3	gemini-3.1-pro	fast	$12.6000	3

surp/coding→kimi-k2.7-code$0.4664/1M-95%6 models

alias of best-coding — compares 6 model(s), routes to the cheapest. click any row to see the full list.

#	model	class	USD / 1M tok	sellers
1	kimi-k2.7-code ◀ routed now	coding	$0.4664	15
2	qwen3-coder-turbo	coding	$0.9116	26
3	qwen3-coder	coding	$1.0100	17
4	kimi-k2.7-code:web	coding	$1.3497	3
5	gpt-5.2-codex	coding	$2.3625	55
6	gpt-5.3-codex	coding	$3.9375	65

surp/fast→gemini-2.5-flash-image$0.0500/1M-99%34 models

alias of best-fast — compares 34 model(s), routes to the cheapest. click any row to see the full list.

#	model	class	USD / 1M tok	sellers
1	gemini-2.5-flash-image ◀ routed now	fast	$0.0500	9
2	qwen3-5-9b	fast	$0.0500	34
3	gpt-5.4-mini	fast	$0.0525	62
4	nvidia-nemotron-3-nano-30b-a3b	fast	$0.0938	41
5	llama-3.2-3b-instruct	fast	$0.0965	35
6	gemma-4-26b-a4b-it	fast	$0.1100	58
7	mistral-small-3.2-24b-instruct:web	fast	$0.1134	3
8	glm-4.5-air	fast	$0.1300	8
9	minimax-m2.5	fast	$0.1500	41
10	mistral-small-3.2-24b-instruct	fast	$0.1787	24
11	llama-3.2-3b-instruct:web	fast	$0.1875	7
12	mistral-small-4	fast	$0.2344	28
13	gpt-4o-mini	fast	$0.2623	60
14	qwen3-next-80b-a3b-instruct	fast	$0.2975	45
15	magistral-small-2509	fast	$0.3000	1
16	gpt-5-image-mini	fast	$0.3739	8
17	minimax-m2.5:web	fast	$0.3825	7
18	gpt-5-nano	fast	$0.4048	10
19	minimax-m2.7	fast	$0.4271	21
20	gemma-4-26b-a4b-it:web	fast	$0.4439	2
21	minimax-m2.7:web	fast	$0.4688	3
22	qwen3-next-80b-a3b-instruct:web	fast	$0.5625	8
23	minimax-m2.1	fast	$0.6200	9
24	gpt-5.4-nano	fast	$1.1773	11
25	gemini-2.5-flash	fast	$1.4000	10
26	gemini-3.1-flash-lite	fast	$1.4962	8
27	minimax-m3	fast	$1.5000	8
28	gemini-2.5-pro	fast	$1.6875	12
29	gemini-3-flash-preview	fast	$1.7500	33
30	gpt-5-mini	fast	$2.0248	10
31	minimax-m2.7-highspeed	fast	$2.7000	4
32	gemini-3-5-flash	fast	$5.2500	30
33	gemini-3.1-pro-preview	fast	$6.9300	29
34	gemini-3.1-pro	fast	$12.6000	3

surp/chat→glm-5.2$0.0300/1M-100%135 models

alias of best-chat — compares 135 model(s), routes to the cheapest. click any row to see the full list.

#	model	class	USD / 1M tok	sellers
1	glm-5.2 ◀ routed now	chat	$0.0300	39
2	deepseek-v4-flash	chat	$0.0401	49
3	llama-3.3-70b-instruct	chat	$0.0420	64
4	e2ee-qwen-2-5-7b-p	chat	$0.0450	26
5	gemini-2.5-flash-image	fast	$0.0500	9
6	qwen3-5-9b	fast	$0.0500	34
7	gpt-5.4-mini	fast	$0.0525	62
8	e2ee-gpt-oss-20b-p	chat	$0.0600	21
9	e2ee-venice-uncensored-24b-p	chat	$0.0700	57
10	nvidia-nemotron-3-nano-30b-a3b	fast	$0.0938	41
11	qwen3-235b-a22b-2507	chat	$0.0950	35
12	llama-3.2-3b-instruct	fast	$0.0965	35
13	venice-uncensored	chat	$0.0990	6
14	gemma-4-26b-a4b-it	fast	$0.1100	58
15	mistral-small-3.2-24b-instruct:web	fast	$0.1134	3
16	venice-uncensored-role-play	chat	$0.1250	59
17	glm-4.5-air	fast	$0.1300	8
18	openai-gpt-oss-120b	chat	$0.1490	36
19	minimax-m2.5	fast	$0.1500	41
20	gemma-3-27b-it	chat	$0.1560	27
21	e2ee-gemma-3-27b	chat	$0.1600	27
22	glm-4.7-flash:web	chat	$0.1700	2
23	deepseek-v4-flash:web	chat	$0.1716	4
24	gpt-5.4	chat	$0.1750	44
25	gpt-5.6-terra	chat	$0.1750	40
26	mistral-small-3.2-24b-instruct	fast	$0.1787	24
27	llama-3.2-3b-instruct:web	fast	$0.1875	7
28	deepseek-v4-pro	chat	$0.1958	45
29	qwen3-30b-a3b	chat	$0.2046	53
30	glm-4.7	chat	$0.2150	78
31	glm-4.6	chat	$0.2170	86
32	gemma-4-31b-it:web	chat	$0.2228	3
33	qwen3-235b-a22b-2507:web	chat	$0.2250	7
34	mistral-small-4	fast	$0.2344	28
35	glm-4.7-flash-heretic	chat	$0.2350	38
36	openai-gpt-oss-120b:web	chat	$0.2479	3
37	e2ee-gemma-4-31b	chat	$0.2500	44
38	glm-5	chat	$0.2520	87
39	gemma-4-31b-it	chat	$0.2610	28
40	gpt-4o-mini	fast	$0.2623	60
41	venice-uncensored-1.2	chat	$0.2750	20
42	glm-4.5	chat	$0.2800	6
43	qwen3-next-80b-a3b-instruct	fast	$0.2975	45
44	glm-4.7-flash	chat	$0.2990	19
45	magistral-small-2509	fast	$0.3000	1
46	deepseek-v3.2	chat	$0.3264	29
47	gpt-5.5	chat	$0.3500	71
48	e2ee-gemma-4-26b-a4b-uncensored-p	chat	$0.3625	27
49	gpt-5-image-mini	fast	$0.3739	8
50	minimax-m2.5:web	fast	$0.3825	7
51	qwen3-5-35b-a3b	chat	$0.3906	33
52	gpt-5-nano	fast	$0.4048	10
53	e2ee-qwen3-5-122b-a10b	chat	$0.4050	7
54	minimax-m2.7	fast	$0.4271	21
55	gemma-4-uncensored	chat	$0.4306	22
56	grok-4.1-fast	chat	$0.4375	7
57	e2ee-glm-4.7-flash	chat	$0.4420	5
58	gemma-4-26b-a4b-it:web	fast	$0.4439	2
59	nvidia-nemotron-3-ultra-550b-a55b	chat	$0.4500	57
60	qwen3.5-flash	chat	$0.4500	9
61	minimax-m2.7:web	fast	$0.4688	3
62	gpt-5.6-luna	chat	$0.4900	41
63	e2ee-qwen3-6-35b-a3b	chat	$0.4998	42
64	e2ee-gpt-oss-120b-p	chat	$0.5069	20
65	nvidia-nemotron-cascade-2-30b-a3b	chat	$0.5170	4
66	glm-5-turbo	chat	$0.5200	92
67	qwen3-next-80b-a3b-instruct:web	fast	$0.5625	8
68	glm-5.1	chat	$0.5800	45
69	qwen-3-7-plus	chat	$0.6000	46
70	minimax-m2.1	fast	$0.6200	9
71	mercury-2	chat	$0.8124	22
72	llama-3.3-70b-instruct:web	chat	$0.8750	7
73	grok-4.20-multi-agent-beta	chat	$0.9375	31
74	kimi-k2.5:web	chat	$1.0150	8
75	kimi-k2.6	chat	$1.0175	37
76	hermes-3-llama-3.1-405b	chat	$1.0250	45
77	qwen3.6-plus-uncensored	chat	$1.0938	30
78	gpt-5.4-nano	fast	$1.1773	11
79	gpt-5.4-image-2	chat	$1.2158	8
80	gpt-5.6-sol	chat	$1.2200	40
81	glm-5:web	chat	$1.3125	8
82	e2ee-glm-5.1	chat	$1.3125	30
83	glm-4.7:web	chat	$1.3125	2
84	gemini-2.5-flash	fast	$1.4000	10
85	grok-code-fast-1	chat	$1.4450	3
86	gemini-3.1-flash-lite	fast	$1.4962	8
87	gpt-5-image	chat	$1.5000	3
88	minimax-m3	fast	$1.5000	8
89	qwen3.6-27b	chat	$1.5214	37
90	kimi-k2.5	chat	$1.5600	26
91	qwen3.5-plus	chat	$1.6380	11
92	gemini-2.5-pro	fast	$1.6875	12
93	gemini-3-flash-preview	fast	$1.7500	33
94	aion-labs.aion-2-0	chat	$1.8000	17
95	glm-5.1:web	chat	$1.8125	5
96	deepseek-v4-pro:web	chat	$1.8236	3
97	grok-4.20-beta	chat	$1.8750	24
98	grok-build-0-1	chat	$1.9880	47
99	gpt-5-mini	fast	$2.0248	10
100	e2ee-qwen3-6-35b-a3b-uncensored-p	chat	$2.0800	8
101	gpt-5.6-terra-pro	chat	$2.1000	34
102	mistral-large	chat	$2.1250	11
103	gpt-5.6-luna-pro	chat	$2.2000	31
104	qwen3.5-397b-a17b	chat	$2.2343	36
105	gpt-5.2	chat	$2.3625	66
106	kimi-k2	chat	$2.5830	7
107	minimax-m2.7-highspeed	fast	$2.7000	4
108	grok-4.3	chat	$2.7621	20
109	claude-opus-4.6	chat	$3.0000	39
110	qwen-3-7-max	chat	$3.4046	25
111	e2ee-glm-4.7	chat	$3.4125	5
112	kimi-k2.6:web	chat	$3.6883	5
113	grok-4.5	chat	$3.7203	8
114	gpt-4o	chat	$4.3748	62
115	claude-haiku-4.5	chat	$4.6360	12
116	gemini-3-5-flash	fast	$5.2500	30
117	claude-sonnet-5	chat	$6.8470	28
118	gemini-3.1-pro-preview	fast	$6.9300	29
119	claude-opus-4.7	chat	$7.5000	43
120	claude-sonnet-4.5	chat	$8.2650	41
121	claude-sonnet-4.6	chat	$8.2650	25
122	kimi-k3	chat	$10.4895	20
123	gemini-3.1-pro	fast	$12.6000	3
124	claude-opus-5-fast	chat	$15.0000	12
125	grok-4	chat	$15.3000	3
126	claude-opus-4.8	chat	$17.0469	58
127	claude-opus-5	chat	$17.1175	17
128	claude-opus-4-8-fast	chat	$17.2800	51
129	claude-opus-4.5	chat	$17.8821	35
130	gpt-5.6-sol-pro	chat	$19.2308	20
131	gpt-5.4-pro	chat	$31.5000	80
132	claude-fable-5	chat	$35.4444	45
133	claude-opus-4.6-fast	chat	$54.0000	31
134	gpt-5.5-pro	chat	$65.6250	61
135	claude-opus-4-7-fast	chat	$71.2800	23

surp/srup-free→glm-5.2$0.0300/1M-100%152 models

zero-price model if one exists, else the absolute cheapest text LLM — compares 152 model(s), routes to the cheapest. click any row to see the full list.

#	model	class	USD / 1M tok	sellers
1	glm-5.2 ◀ routed now	chat	$0.0300	39
2	deepseek-v4-flash	chat	$0.0401	49
3	llama-3.3-70b-instruct	chat	$0.0420	64
4	e2ee-qwen-2-5-7b-p	chat	$0.0450	26
5	gemini-2.5-flash-image	fast	$0.0500	9
6	qwen3-5-9b	fast	$0.0500	34
7	qwen3-235b-a22b-thinking-2507	reasoning	$0.0500	40
8	gpt-5.4-mini	fast	$0.0525	62
9	e2ee-gpt-oss-20b-p	chat	$0.0600	21
10	e2ee-venice-uncensored-24b-p	chat	$0.0700	57
11	nvidia-nemotron-3-nano-30b-a3b	fast	$0.0938	41
12	qwen3-235b-a22b-2507	chat	$0.0950	35
13	llama-3.2-3b-instruct	fast	$0.0965	35
14	venice-uncensored	chat	$0.0990	6
15	gemma-4-26b-a4b-it	fast	$0.1100	58
16	mistral-small-3.2-24b-instruct:web	fast	$0.1134	3
17	venice-uncensored-role-play	chat	$0.1250	59
18	glm-4.5-air	fast	$0.1300	8
19	openai-gpt-oss-120b	chat	$0.1490	36
20	minimax-m2.5	fast	$0.1500	41
21	gemma-3-27b-it	chat	$0.1560	27
22	e2ee-gemma-3-27b	chat	$0.1600	27
23	glm-4.7-flash:web	chat	$0.1700	2
24	deepseek-v4-flash:web	chat	$0.1716	4
25	gpt-5.4	chat	$0.1750	44
26	gpt-5.6-terra	chat	$0.1750	40
27	mistral-small-3.2-24b-instruct	fast	$0.1787	24
28	llama-3.2-3b-instruct:web	fast	$0.1875	7
29	deepseek-v4-pro	chat	$0.1958	45
30	qwen3-30b-a3b	chat	$0.2046	53
31	glm-4.7	chat	$0.2150	78
32	glm-4.6	chat	$0.2170	86
33	gemma-4-31b-it:web	chat	$0.2228	3
34	qwen3-235b-a22b-2507:web	chat	$0.2250	7
35	mistral-small-4	fast	$0.2344	28
36	glm-4.7-flash-heretic	chat	$0.2350	38
37	openai-gpt-oss-120b:web	chat	$0.2479	3
38	e2ee-gemma-4-31b	chat	$0.2500	44
39	glm-5	chat	$0.2520	87
40	gemma-4-31b-it	chat	$0.2610	28
41	gpt-4o-mini	fast	$0.2623	60
42	venice-uncensored-1.2	chat	$0.2750	20
43	glm-4.5	chat	$0.2800	6
44	qwen3-next-80b-a3b-instruct	fast	$0.2975	45
45	glm-4.7-flash	chat	$0.2990	19
46	magistral-small-2509	fast	$0.3000	1
47	deepseek-v3.2	chat	$0.3264	29
48	gpt-5.5	chat	$0.3500	71
49	e2ee-gemma-4-26b-a4b-uncensored-p	chat	$0.3625	27
50	gpt-5-image-mini	fast	$0.3739	8
51	minimax-m2.5:web	fast	$0.3825	7
52	qwen3-5-35b-a3b	chat	$0.3906	33
53	gpt-5-nano	fast	$0.4048	10
54	e2ee-qwen3-5-122b-a10b	chat	$0.4050	7
55	minimax-m2.7	fast	$0.4271	21
56	gemma-4-uncensored	chat	$0.4306	22
57	grok-4.1-fast	chat	$0.4375	7
58	e2ee-glm-4.7-flash	chat	$0.4420	5
59	gemma-4-26b-a4b-it:web	fast	$0.4439	2
60	nvidia-nemotron-3-ultra-550b-a55b	chat	$0.4500	57
61	qwen3.5-flash	chat	$0.4500	9
62	kimi-k2.7-code	coding	$0.4664	15
63	minimax-m2.7:web	fast	$0.4688	3
64	gpt-5.6-luna	chat	$0.4900	41
65	e2ee-qwen3-6-35b-a3b	chat	$0.4998	42
66	e2ee-gpt-oss-120b-p	chat	$0.5069	20
67	nvidia-nemotron-cascade-2-30b-a3b	chat	$0.5170	4
68	glm-5-turbo	chat	$0.5200	92
69	qwen3-next-80b-a3b-instruct:web	fast	$0.5625	8
70	glm-5.1	chat	$0.5800	45
71	qwen-3-7-plus	chat	$0.6000	46
72	glm-4.7-thinking	reasoning	$0.6125	2
73	glm-4.7-thinking:web	reasoning	$0.6125	2
74	minimax-m2.1	fast	$0.6200	9
75	qwen3-vl-235b-a22b-thinking	vision	$0.7150	28
76	mercury-2	chat	$0.8124	22
77	llama-3.3-70b-instruct:web	chat	$0.8750	7
78	qwen3-coder-turbo	coding	$0.9116	26
79	trinity-large-thinking	reasoning	$0.9344	18
80	grok-4.20-multi-agent-beta	chat	$0.9375	31
81	qwen3-coder	coding	$1.0100	17
82	kimi-k2.5:web	chat	$1.0150	8
83	kimi-k2.6	chat	$1.0175	37
84	hermes-3-llama-3.1-405b	chat	$1.0250	45
85	trinity-large-thinking:web	reasoning	$1.0781	1
86	qwen3.6-plus-uncensored	chat	$1.0938	30
87	gpt-5.4-nano	fast	$1.1773	11
88	gpt-5.4-image-2	chat	$1.2158	8
89	gpt-5.6-sol	chat	$1.2200	40
90	glm-5:web	chat	$1.3125	8
91	e2ee-glm-5.1	chat	$1.3125	30
92	glm-4.7:web	chat	$1.3125	2
93	qwen3-vl-30b-a3b-thinking	vision	$1.3200	10
94	kimi-k2.7-code:web	coding	$1.3497	3
95	gemini-2.5-flash	fast	$1.4000	10
96	grok-code-fast-1	chat	$1.4450	3
97	gemini-3.1-flash-lite	fast	$1.4962	8
98	gpt-5-image	chat	$1.5000	3
99	minimax-m3	fast	$1.5000	8
100	qwen3.6-27b	chat	$1.5214	37
101	kimi-k2-thinking	reasoning	$1.5500	7
102	kimi-k2.5	chat	$1.5600	26
103	glm-5.1-non-thinking:web	reasoning	$1.6250	5
104	glm-5v-turbo	vision	$1.6250	26
105	qwen3.5-plus	chat	$1.6380	11
106	gemini-2.5-pro	fast	$1.6875	12
107	gemini-3-flash-preview	fast	$1.7500	33
108	aion-labs.aion-2-0	chat	$1.8000	17
109	glm-5.1:web	chat	$1.8125	5
110	deepseek-v4-pro:web	chat	$1.8236	3
111	grok-4.20-beta	chat	$1.8750	24
112	grok-build-0-1	chat	$1.9880	47
113	gpt-5-mini	fast	$2.0248	10
114	e2ee-qwen3-6-35b-a3b-uncensored-p	chat	$2.0800	8
115	gpt-5.6-terra-pro	chat	$2.1000	34
116	mistral-large	chat	$2.1250	11
117	gpt-5.6-luna-pro	chat	$2.2000	31
118	qwen3.5-397b-a17b	chat	$2.2343	36
119	gpt-5.2-codex	coding	$2.3625	55
120	gpt-5.2	chat	$2.3625	66
121	deepseek-r1	reasoning	$2.4934	7
122	kimi-k2	chat	$2.5830	7
123	minimax-m2.7-highspeed	fast	$2.7000	4
124	grok-4.3	chat	$2.7621	20
125	claude-opus-4.6	chat	$3.0000	39
126	qwen-3-7-max	chat	$3.4046	25
127	e2ee-glm-4.7	chat	$3.4125	5
128	kimi-k2.6:web	chat	$3.6883	5
129	grok-4.5	chat	$3.7203	8
130	gpt-5.3-codex	coding	$3.9375	65
131	gpt-4o	chat	$4.3748	62
132	claude-haiku-4.5	chat	$4.6360	12
133	gemini-3-5-flash	fast	$5.2500	30
134	claude-sonnet-5	chat	$6.8470	28
135	gemini-3.1-pro-preview	fast	$6.9300	29
136	claude-opus-4.7	chat	$7.5000	43
137	claude-sonnet-4.5	chat	$8.2650	41
138	claude-sonnet-4.6	chat	$8.2650	25
139	kimi-k3	chat	$10.4895	20
140	gemini-3.1-pro	fast	$12.6000	3
141	claude-opus-5-fast	chat	$15.0000	12
142	grok-4	chat	$15.3000	3
143	claude-opus-4.8	chat	$17.0469	58
144	claude-opus-5	chat	$17.1175	17
145	claude-opus-4-8-fast	chat	$17.2800	51
146	claude-opus-4.5	chat	$17.8821	35
147	gpt-5.6-sol-pro	chat	$19.2308	20
148	gpt-5.4-pro	chat	$31.5000	80
149	claude-fable-5	chat	$35.4444	45
150	claude-opus-4.6-fast	chat	$54.0000	31
151	gpt-5.5-pro	chat	$65.6250	61
152	claude-opus-4-7-fast	chat	$71.2800	23

Savings are vs a blended claude-sonnet-4.6 list price (~$9/1M). Click any combo to expand it and see every model in its pool, cheapest first — the top row is what your request routes to right now.

how it works — 3 steps

you request

POST /v1/chat/completions with model: "surp/best-chat". no auth header.

we 402

we resolve the combo to the live cheapest model, compute the exact micropayment, and return HTTP 402 with payment requirements.

you pay & go

your wallet signs an EIP-3009 USDC authorization. we verify + settle on Base. the completion streams back.

why this is different

Most "cheap LLM" services are static: they pick one model, hide it behind a flat price, and pocket the spread. surp.ivc.lol is dynamic: the model you get is whatever is cheapest on Surplus at the second you asked, and the price you pay is that spot price + a transparent markup. We're not a provider — we're a price arbitrageur sitting on top of a marketplace that itself sits on top of every other provider. Aggregating the aggregator.

live: payments settle in real USDC on Base mainnet (eip155:8453) via the x402 protocol. each request is a single on-chain EIP-3009 transfer — no account, no API key, no subscription. your wallet pays, your model answers.

connect your hermes build your own combo try the playground read the docs