Skip to content
ModelCap

Price ranking

Cheapest LLM APIs

Ranked language models with a listed API price, cheapest first by a 3:1 input-weighted blend of the lowest observed provider offer. Each row shows the ModelCap Index position so cheap and capable can be read together.

Snapshot as of 1 October 2026

Ling 3.0 Flash VL from InclusionAI leads the cheapest LLM API list as of 1 October 2026 with a blended price of $0.031 per 1M tokens ($0.021 in / $0.062 out), holding ModelCap Index position #50; 115 models qualify.

Models on this list
115
With openly downloadable weights
51
With a listed API price
100

Cheapest LLM APIs (top 100 of 115)

Every row is a current, canonical language model with a public position on the ModelCap Index; the list filters by a published fact and orders by a published figure.

Cheapest LLM APIs: current, canonical language models with a public ModelCap Index position and a fresh or bounded-stale listed price above zero on the OpenRouter catalogue, ordered by 0.75 × input + 0.25 × output price per million tokens
#ModelBlended $/1MModelCap IndexInput $/1MOutput $/1MContextWeights
1Ling 3.0 Flash VLInclusionAI$0.031#5065.9$0.021$0.062262KOpen weights
2Ling 3.0 FlashInclusionAI$0.032#6362.2$0.021$0.063262KOpen weights
3gpt-oss-20bOpenAI$0.036#16637.8$0.018$0.09131KOpen weights
4Nex-N2.5-MiniNex AGI$0.044#3371.1$0.025$0.10262KOpen weights
5Llama 3.1 8B InstructMeta$0.057#23313.5$0.05$0.08131KGated access
6Nova Micro 1.0Amazon$0.061#22417.4$0.035$0.14128KAPI only
7Gemma 3 4BGoogle$0.063#19427.4$0.05$0.10131KGated access
8Mercury 2.5Inception Labs$0.068#9055.8$0.04$0.15260KAPI only
9gpt-oss-120bOpenAI$0.07#13244.6$0.037$0.17131KOpen weights
10Llama 3.2 1B InstructMeta$0.071#2754.9$0.027$0.20160KGated access
11Laguna XS 2.1Poolside$0.075#8357.5$0.06$0.12262KRestricted license
12Gemma 3 12BGoogle$0.075#16338.1$0.05$0.15131KGated access
13Qwen3 30B A3B Instruct 2507Qwen$0.084#12050.6$0.048$0.193262KOpen weights
14Nemotron 3.5 LightningNVIDIA$0.087#8756.3$0.059$0.17262KRestricted license
15Solar Mini 4Upstage$0.087#5365.5$0.05$0.20524KAPI only
16Nemotron 3 Nano 30B A3BNVIDIA$0.087#17931.8$0.05$0.20262KRestricted license
17Phi 4Microsoft$0.088#21919.6$0.07$0.1416KOpen weights
18Ling 3.0 Flash FinInclusionAI$0.09#5964.3$0.06$0.18262KOpen weights
19Granite 4.2 8BIBM Granite$0.107#17234.8$0.06$0.25131KOpen weights
20Qwen3.5-9BQwen$0.112#9554.9$0.10$0.15262KOpen weights
21Laguna S 2.1Poolside$0.113#4268.4$0.09$0.181MRestricted license
22Nex-N2.5-ProNex AGI$0.119#2077.8$0.075$0.25262KOpen weights
23Llama 3.2 3B InstructMeta$0.12#2628.4$0.05$0.33131KGated access
24Gemma 4 26B A4BGoogle$0.121#4168.4$0.076$0.255262KOpen weights
25Qwen3 Coder 30B A3B InstructQwen$0.123#9954.1$0.07$0.28262KOpen weights
26Qwen3 32BQwen$0.13#14441.2$0.08$0.28131KOpen weights
27gpt-oss-safeguard-20bOpenAI$0.131#17533.8$0.075$0.30131KOpen weights
28Mistral Small 3.2 24BMistral AI$0.133#14143.1$0.094$0.25256KOpen weights
29DeepSeek V4.1 FlashDeepSeek$0.147#1579.3$0.03$0.501MOpen weights
30Llama 4 ScoutMeta$0.15#17732.9$0.10$0.301.3MGated access
31Gemma 4 31BGoogle$0.152#2872.9$0.09$0.34262KOpen weights
32Qwen3 235B A22B Instruct 2507Qwen$0.153#6462.1$0.087$0.35262KOpen weights
33Llama 3.3 70B InstructMeta$0.155#17832.4$0.10$0.32131KGated access
34Solar Pro 4Upstage$0.158#11950.8$0.09$0.36524KAPI only
35Gemma 3 27BGoogle$0.172#13344.5$0.08$0.45131KGated access
36Nemotron 3 SuperNVIDIA$0.172#13444.0$0.08$0.45262KRestricted license
37MiMo-V2.6-FlashXiaomi$0.175#2575.7$0.14$0.281MOpen weights
38MiMo-V2.5Xiaomi$0.175#4468.0$0.14$0.281MOpen weights
39GPT-6 LunaOpenAI$0.20#3171.4$0.10$0.501MAPI only
40Qwen3 30B A3BQwen$0.215#17135.7$0.12$0.50131KOpen weights
41Qwen3.8 FlashQwen$0.23#1878.4$0.15$0.471MRestricted license
42GLM 5.3 FlashZ.ai$0.237#1778.9$0.15$0.501MOpen weights
43Mistral Small 4Mistral AI$0.262#9455.0$0.15$0.60262KOpen weights
44GPT-4o-miniOpenAI$0.262#16138.8$0.15$0.60128KAPI only
45Command R (08-2024)Cohere$0.262#22118.5$0.15$0.60128KAPI only
46Qwen3 Coder NextQwen$0.29#11053.3$0.12$0.80262KOpen weights
47Llama 4 MaverickMeta$0.304#17434.8$0.188$0.6521MGated access
48GLM 4.5 AirZ.ai$0.31#12547.4$0.13$0.85131KOpen weights
49DeepSeek V3.2DeepSeek$0.315#6661.7$0.28$0.42164KOpen weights
50DeepSeek V4 Flash Vision ExpDeepSeek$0.323#2773.8$0.216$0.6471MOpen weights
51Qwen3 Next 80B A3B InstructQwen$0.35#9854.7$0.10$1.10262KOpen weights
52Qwen3.6 35B A3BQwen$0.362#7260.7$0.15$1.00262KOpen weights
53Qwen2.5 72B InstructQwen$0.37#18929.0$0.36$0.4033KRestricted license
54Trinity Large ThinkingArcee AI$0.387#12448.3$0.25$0.80262KRestricted license
55Qwen3 Next 80B A3B ThinkingQwen$0.412#12746.9$0.15$1.20262KOpen weights
56MiniMax-01MiniMax$0.425#14242.2$0.20$1.101MLicense unverified
57Step 3.7 FlashStepFun$0.438#11252.8$0.20$1.15262KOpen weights
58GLM 4.6VZ.ai$0.45#12249.0$0.30$0.90131KOpen weights
59GPT-5.4 NanoOpenAI$0.463#8456.5$0.20$1.25400KAPI only
60DeepSeek V3.1 TerminusDeepSeek$0.475#7659.7$0.30$1.00164KOpen weights
61Qwen3 Coder 480B A35BQwen$0.475#11551.9$0.30$1.00262KOpen weights
62LongCat 2.0Meituan$0.525#1679.0$0.30$1.201MOpen weights
63MiniMax M3MiniMax$0.525#4068.5$0.30$1.201MRestricted license
64MiMo-V2.6-ProXiaomi$0.544#683.1$0.435$0.871MOpen weights
65Qwen3.7 PlusQwen$0.56#3071.9$0.32$1.281MAPI only
66Command A+Cohere$0.60#8556.5$0.30$1.50192KAPI only
67Qwen3 VL 235B A22B InstructQwen$0.632#7859.5$0.21$1.90262KOpen weights
68Muse Glimmer 30BMeta$0.637#3470.7$0.35$1.50131KOpen weights
69Inkling SmallThinking Machines$0.637#8257.6$0.45$1.20524KOpen weights
70Qwen3.5-122B-A10BQwen$0.715#7759.5$0.26$2.08262KOpen weights
71Qwen2.5 Coder 32B InstructQwen$0.745#21023.6$0.66$1.0033KOpen weights
72Qwen3 235B A22B Thinking 2507Qwen$0.747#9654.8$0.23$2.30131KOpen weights
73Mistral Large 3 2512Mistral AI$0.75#7459.9$0.50$1.50262KAPI only
74Qwen3 235B A22BQwen$0.796#9255.7$0.455$1.82131KOpen weights
75Gemini 3.5 Flash LiteGoogle$0.85#3271.2$0.30$2.501MAPI only
76Nova 2 LiteAmazon$0.85#16238.5$0.30$2.501MAPI only
77R1 0528DeepSeek$0.913#6761.5$0.50$2.15164KOpen weights
78DeepSeek V4 Pro 0813DeepSeek$0.99#2476.4$0.66$1.981MOpen weights
79Seed 2.1 TurboByteDance Seed$1.00#2377.0$0.50$2.50262KAPI only
80GLM 5.3Z.ai$1.01#1180.9$0.222$3.391MRestricted license
81Qwen3.8 27BQwen$1.06#3968.9$0.42$3.001MOpen weights
82Kimi K2 ThinkingMoonshot AI$1.07#5265.6$0.60$2.50262KRestricted license
83Hy4 previewTencent$1.13#2673.8$0.751$2.251MOpen weights
84Qwen3.5 397B A17BQwen$1.29#4368.0$0.55$3.50262KOpen weights
85Qwen3 VL 235B A22B ThinkingQwen$1.30#10153.8$0.40$4.00131KOpen weights
86Kimi K2.7 CodeMoonshot AI$1.34#4965.9$0.671$3.35262KRestricted license
87Nova Pro 1.0Amazon$1.40#19526.5$0.80$3.20300KAPI only
88Gemini 3.8 FlashGoogle$1.50#982.7$0.75$3.751MAPI only
89Grok 4.20 Multi-AgentxAI$1.56#1379.8$1.25$2.502MAPI only
90GPT-5.4 MiniOpenAI$1.69#3669.5$0.75$4.50400KAPI only
91InklingThinking Machines$1.76#4767.5$1.00$4.05524KOpen weights
92GLM 5V TurboZ.ai$1.90#4567.9$1.20$4.00203KAPI only
93GLM 5 TurboZ.ai$1.90#10953.5$1.20$4.00203KAPI only
94o4 MiniOpenAI$1.93#11751.2$1.10$4.40200KAPI only
95Muse Spark 1.3Meta$2.00#584.6$1.25$4.251MAPI only
96Claude Haiku 4.5Anthropic$2.00#7559.8$1.00$5.00200KAPI only
97Kimi K3Moonshot AI$2.77#1082.2$0.365$10.001MRestricted license
98Qwen3.8 Max (0902)Qwen$3.00#783.0$2.00$6.001MAPI only
99Grok 4.7xAI$3.00#2972.8$2.00$6.00500KAPI only
100Mistral Medium 3.5Mistral AI$3.00#6561.9$1.50$7.50262KAPI only

Cheapest LLM APIs: common questions

Which model tops the cheapest LLM API list right now?

Ling 3.0 Flash VL (InclusionAI), as of 1 October 2026, with a blended price of $0.031 per 1M tokens ($0.021 in / $0.062 out) and ModelCap Index position #50.

How is the cheapest LLM API list built?

It contains current, canonical language models with a public ModelCap Index position and a fresh or bounded-stale listed price above zero on the OpenRouter catalogue, ordered by 0.75 × input + 0.25 × output price per million tokens. Nothing is estimated for the list itself: the filter is a published fact and the order is a published figure, and every row links to the model page that shows its evidence.

How many models qualify for the cheapest LLM API list?

115 models qualify; the page shows the first 100. The population is the live ModelCap Index, so a model appears here the moment it holds a public position and meets the filter.

Which model on this list ranks highest on the ModelCap Index?

Muse Spark 1.3 holds ModelCap Index position #5, the highest of any model in the list, and sits at #95 here by blended $/1m.

What is the cheapest model among the top ten on the ModelCap Index?

MiMo-V2.6-Pro (Index #6) at $0.544 blended per 1M tokens — $0.435 input, $0.87 output.

Why order by a blended price instead of the output price?

Most production traffic is prompt-heavy, so the list weights input at 75% and output at 25%; both raw prices are shown in the table so a generation-heavy workload can re-order by the output column on the model pages.

Which is the best open-weight model on this list?

Ling 3.0 Flash VL from InclusionAI is the highest-placed model with openly downloadable weights (#1 here, ModelCap Index #50).

How current is the cheapest LLM API list?

Positions, prices and context figures come from the same published snapshot dated 1 October 2026. Publication and page updates happen separately; use the snapshot date shown on the page.

Explore further