The same answer costs 4,800 times more on one model than another.

Providers publish price per million tokens, which is not comparable across models. This index prices one standard answer, 1,000 input tokens plus 500 output tokens, across 100 models from 28 providers. Last updated 2026-08-08.

Headline figures

  • Cheapest answer: $0.000025 on Ling-2.6-flash (inclusionAI).
  • Median answer: $0.0018 on Kimi K2.6.
  • Most expensive answer: $0.120 on GPT-5.5 Pro (OpenAI).
  • Spread from cheapest to most expensive: about 4,800 times.

How this is calculated

One standard answer is 1,000 input tokens, roughly a prompt with a couple of paragraphs of context, and 500 output tokens, roughly a substantial reply. Every model is priced on that identical workload: (input rate x 1,000 + output rate x 500) divided by 1,000,000.

Change the mix and the ordering shifts, which is the point. A model with cheap input and dear output wins on short prompts and loses on long replies. The formula is published so anyone can recompute the index against their own mix.

Sources and limits

  • Prices are public list rates from the OpenRouter model catalogue, in USD per million tokens, fetched 2026-08-08.
  • They exclude prompt caching discounts, batch pricing, and negotiated volume rates. Real bills at scale run lower.
  • Cost is not quality. A model that is far cheaper is not proportionally worse, and on many everyday tasks the gap is small.
  • The credits column is what Whizi charges per message on its own plans, for the 89 models it meters individually. It is not a provider rate.

The full index

100 models, cheapest first. Free to reuse with attribution to the Whizi AI Model Cost Index and a link to this page. Raw data: JSON and CSV.

#ModelProviderPer answerPer 1,000 answers$ / 1M input$ / 1M outputContextWhizi credits
1Ling-2.6-flashinclusionAI$0.000025$0.025$0.01$0.03262K1x
2Ling-3.0-flashinclusionAI$0.000053$0.052$0.021$0.063262K1x
3Nex-N2-MiniNex Agi$0.000075$0.075$0.025$0.1262K1x
4Qwen3.7 FlashQwen$0.000095$0.095$0.03$0.131M1x
5Granite 4.1 8BIbm Granite$0.000100$0.100$0.05$0.1131K1x
6Laguna XS 2.1Poolside$0.000120$0.120$0.06$0.12262K1x
7Phi 4Microsoft$0.000140$0.140$0.07$0.1416K1x
8Hy3 previewTencent$0.000168$0.168$0.063$0.21262K1x
9DeepSeek V4 Flash 0731DeepSeek$0.000180$0.180$0.09$0.181M1x
10Laguna S 2.1Poolside$0.000180$0.180$0.09$0.181M1x
11Llama 3.3 70B InstructMeta$0.000260$0.260$0.1$0.32131K1x
12DeepSeek V4 Flash 0423DeepSeek$0.000280$0.280$0.14$0.281M1x
13MiMo-V2.5Xiaomi$0.000280$0.280$0.14$0.281M1x
14Gemini 2.5 Flash LiteGoogle$0.000300$0.300$0.1$0.41M1x
15Ring-2.6-1TinclusionAI$0.000388$0.388$0.075$0.625262K1x
16Ling-2.6-1TinclusionAI$0.000388$0.388$0.075$0.625262K1x
17Hy3Tencent$0.000396$0.396$0.132$0.528262K1x
18GPT-5.6 Luna ProOpenAI$0.000400$0.400$0.1$0.61Mnot metered
19GPT-5.6 LunaOpenAI$0.000400$0.400$0.1$0.61M1x
20KAT-Coder-Air V2.5Kwaipilot$0.000450$0.450$0.15$0.6256K1x
21GLM 5.2Z.ai$0.000468$0.468$0.182$0.5721M3x
22DeepSeek V3.2DeepSeek$0.000469$0.469$0.269$0.4164K1x
23Qwen3 Coder NextQwen$0.000520$0.520$0.12$0.8262K1x
24Llama 4 MaverickMeta$0.000600$0.600$0.2$0.81M1x
25Qwen3.6 35B A3BQwen$0.000650$0.650$0.15$1262K1x
26DeepSeek V3.1DeepSeek$0.000725$0.725$0.25$0.95164K1x
27Codestral 2508Mistral$0.000750$0.750$0.3$0.9256K1x
28Qwen3.6 FlashQwen$0.000750$0.750$0.1875$1.1251M1x
29Nex-N2-ProNex Agi$0.000750$0.750$0.25$1262K1x
30MiniMax M2MiniMax$0.000765$0.765$0.255$1.02205K1x
31Step 3.7 FlashStepfun$0.000775$0.775$0.2$1.15262K1x
32GPT-5.4 NanoOpenAI$0.000825$0.825$0.2$1.25400K2x
33DeepSeek V4 ProDeepSeek$0.000870$0.870$0.435$0.871M2x
34MiMo-V2.5-ProXiaomi$0.000870$0.870$0.435$0.871M1x
35MiniMax M3MiniMax$0.000900$0.900$0.3$1.21M1x
36LongCat 2.0Meituan$0.000900$0.900$0.3$1.21M1x
37Perceptron Mk1Perceptron$0.000900$0.900$0.15$1.533K1x
38Qwen3.7 PlusQwen$0.000960$0.960$0.32$1.281M1x
39Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google$0.0010$1.000$0.25$1.566Knot metered
40Gemini 3.1 Flash LiteGoogle$0.0010$1.000$0.25$1.51M1x
41Inkling SmallThinkingmachines$0.0010$1.050$0.45$1.2524K1x
42Qwen3.5 Plus 2026-04-20Qwen$0.0012$1.200$0.3$1.81M1x
43Mistral Large 3 2512Mistral$0.0013$1.250$0.5$1.5262K2x
44GLM 4.7Z.ai$0.0013$1.275$0.4$1.75205K2x
45Mistral Medium 3.1Mistral$0.0014$1.400$0.4$2131K2x
46Aion-3.0-MiniAion Labs$0.0014$1.400$0.7$1.4131K2x
47GLM 4.6Z.ai$0.0015$1.500$0.5$2205K1x
48Gemini 2.5 FlashGoogle$0.0015$1.550$0.3$2.51M2x
49Gemini 3.5 Flash LiteGoogle$0.0015$1.550$0.3$2.51M2x
50Kimi K2 0711Moonshot$0.0017$1.720$0.57$2.3131K10x
51Kimi K2.6Moonshot$0.0018$1.800$0.5795$2.44262K10x
52Kimi K2 ThinkingMoonshot$0.0019$1.850$0.6$2.5262K10x
53R1DeepSeek$0.0019$1.950$0.7$2.5164K2x
54Nano Banana 2 (Gemini 3.1 Flash Image)Google$0.0020$2.000$0.5$3131Knot metered
55Grok Build 0.1xAI$0.0020$2.000$1$2256K3x
56KAT-Coder-Pro V2.5Kwaipilot$0.0022$2.220$0.74$2.96256K3x
57GLM 5Z.ai$0.0022$2.225$0.95$2.55205K2x
58Nova Pro 1.0Amazon$0.0024$2.400$0.8$3.2300K3x
59Nemotron 3 UltraNVIDIA$0.0024$2.400$0.6$3.6512K3x
60Qwen3.6 27BQwen$0.0024$2.400$0.6$3.6262K3x
61GLM 5.1Z.ai$0.0024$2.448$0.952$2.992205K3x
62Kimi K2.7 CodeMoonshot$0.0024$2.450$0.7$3.5262K10x
63Grok 4.3xAI$0.0025$2.500$1.25$2.51M4x
64InklingThinkingmachines$0.0030$2.975$0.95$4.051M4x
65GPT-5.4 MiniOpenAI$0.0030$3.000$0.75$4.5400K4x
66Muse Spark 1.2Meta$0.0034$3.375$1.25$4.251M5x
67Muse Spark 1.1Meta$0.0034$3.375$1.25$4.251M5x
68Claude Haiku 4.5Anthropic$0.0035$3.500$1$5200K4x
69Qwen3.7 MaxQwen$0.0037$3.688$1.475$4.4251M5x
70GPT-5.6 Terra ProOpenAI$0.0040$4.000$1$61Mnot metered
71GPT-5.6 TerraOpenAI$0.0040$4.000$1$61M4x
72Qwen3.6 Max PreviewQwen$0.0041$4.108$1.027$6.162262K6x
73Grok 4.5xAI$0.0050$5.000$2$6500K6x
74Qwen3.8 MaxQwen$0.0050$5.000$2$61M6x
75Gemini 3.6 FlashGoogle$0.0053$5.250$1.5$7.51M3x
76Mistral Medium 3.5Mistral$0.0053$5.250$1.5$7.5262K6x
77Gemini 3.5 FlashGoogle$0.0060$6.000$1.5$91M8x
78Aion-3.0Aion Labs$0.0060$6.000$3$6131K10x
79Claude Sonnet 5Anthropic$0.0070$7.000$2$101M10x
80Command ACohere$0.0075$7.500$2.5$10256K10x
81Gemini 3.1 Pro PreviewGoogle$0.0080$8.000$2$121M10x
82Nano Banana Pro (Gemini 3 Pro Image)Google$0.0080$8.000$2$12131Knot metered
83GPT-5.4OpenAI$0.010$10.000$2.5$151M15x
84Claude Sonnet 4.6Anthropic$0.011$10.500$3$151M10x
85Claude Sonnet 4.5Anthropic$0.011$10.500$3$151M10x
86Kimi K3Moonshot$0.011$10.500$3$151M10x
87GPT-5.4 Image 2OpenAI$0.015$15.500$8$15272Knot metered
88Claude Opus 5Anthropic$0.018$17.500$5$251M20x
89Claude Opus 4.8Anthropic$0.018$17.500$5$251M20x
90Claude Opus 4.7Anthropic$0.018$17.500$5$251M20x
91GPT-5.5OpenAI$0.020$20.000$5$301M20x
92GPT Chat LatestOpenAI$0.020$20.000$5$30400K25x
93GPT-5.6 Sol ProOpenAI$0.020$20.000$5$301Mnot metered
94GPT-5.6 SolOpenAI$0.020$20.000$5$301M20x
95Fugu UltraSakana$0.020$20.000$5$301M25x
96Claude Opus 5 (Fast)Anthropic$0.035$35.000$10$501Mnot metered
97Claude Fable 5Anthropic$0.035$35.000$10$501M50x
98Claude Opus 4.8 (Fast)Anthropic$0.035$35.000$10$501Mnot metered
99Claude Opus 4.7 (Fast)Anthropic$0.105$105.000$30$1501Mnot metered
100GPT-5.5 ProOpenAI$0.120$120.000$30$1801Mnot metered

Next step

Price your own text with the token cost calculator, or compare plans on Whizi pricing.