LLM API pricing: the same answer costs 2,000 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 167 models from 43 providers. Last updated August 20, 2026.

Headline figures

  • Cheapest answer: $0.000053 on Ling-3.0-flash (inclusionAI).
  • Median answer: $0.0016 on GLM 5.
  • Most expensive answer: $0.105 on Claude Opus 4.7 (Fast) (Anthropic).
  • Spread from cheapest to most expensive: about 2,000 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 you can recompute it against your own mix.

Sources and limits

  • Prices are public list rates from the OpenRouter model catalogue, in USD per million tokens, fetched August 20, 2026.
  • They exclude prompt caching discounts, batch pricing, and negotiated volume rates. Real bills at scale run lower.
  • Cost is not quality. A model 2,000 times cheaper is not 2,000 times worse, and on many everyday tasks the gap is small.
  • The credits column is what Whizi charges per message on its own plans, shown for the 143 models it meters individually. It is not a provider rate.

The full index

167 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 in$ / 1M outContextWhizi credits
1Ling-3.0-flashinclusionAI$0.000053$0.052$0.021$0.063262K1x
2Nex-N2-MiniNex Agi$0.000075$0.075$0.025$0.1262Knot metered
3Nex-N2.5-MiniNex AGI$0.000075$0.075$0.025$0.1262K1x
4Solar Pro 4Upstage$0.000090$0.090$0.03$0.12524K1x
5Qwen3.7 FlashQwen$0.000095$0.095$0.03$0.131M1x
6Granite 4.1 8BIbm Granite$0.000100$0.100$0.05$0.1131Knot metered
7Hy4 flashTencent$0.000105$0.105$0.035$0.14051M1x
8Mercury 2.5Inception$0.000115$0.115$0.04$0.15260Knot metered
9Laguna XS 2.1Poolside$0.000120$0.120$0.06$0.12262Knot metered
10Hy-MT2-1.8BTencent$0.000133$0.133$0.044$0.1778Knot metered
11Phi 4Microsoft$0.000140$0.140$0.07$0.1416K1x
12Ternary Bonsai 2 9BPrismML$0.000145$0.145$0.08$0.13262K1x
13Solar Mini 4Upstage$0.000150$0.150$0.05$0.2524K1x
14Nemotron 3.5 LightningNVIDIA$0.000180$0.180$0.08$0.2262K1x
15Laguna S 2.1Poolside$0.000180$0.180$0.09$0.181Mnot metered
16LFM3-1.7BLiquidAI$0.000180$0.180$0.08$0.2262K1x
17Granite 4.2 8BIBM$0.000185$0.185$0.06$0.25131K1x
18Ling 3.1 FlashinclusionAI$0.000188$0.188$0.075$0.225262K1x
19Nex-N2.5-ProNex AGI$0.000200$0.200$0.075$0.25262K1x
20Hy-MT2-30B-A3BTencent$0.000222$0.222$0.074$0.2958Knot metered
21Llama 3.3 70B InstructMeta$0.000260$0.260$0.1$0.32131K1x
22Mercury 3Inception$0.000275$0.275$0.1$0.351Mnot metered
23DeepSeek V4 Flash 0731DeepSeek$0.000280$0.280$0.14$0.281M1x
24MiMo-V2.6-FlashXiaomi$0.000280$0.280$0.14$0.281M1x
25GLM 5.3 FlashZ.ai$0.000290$0.290$0.04$0.51M1x
26Gemini 2.5 Flash LiteGoogle$0.000300$0.300$0.1$0.41M1x
27Nex-N2.6Nex AGI$0.000320$0.320$0.12$0.4262K1x
28Ternary Bonsai 2 27BPrismML$0.000325$0.325$0.075$0.5262K1x
29GPT-6 LunaOpenAI$0.000350$0.350$0.1$0.51M1x
30Claude Haiku 5.5Anthropic$0.000350$0.350$0.1$0.51M1x
31Muse EmberMeta$0.000350$0.350$0.1$0.51M1x
32Qwen3.8 FlashQwen$0.000385$0.385$0.15$0.471M1x
33Qwen3.8 Omni FlashQwen$0.000385$0.385$0.15$0.471M1x
34Ring-2.6-1TinclusionAI$0.000388$0.388$0.075$0.625262Knot metered
35Hy3Tencent$0.000396$0.396$0.132$0.528262K1x
36Nemotron 3.5 Super VLNVIDIA$0.000400$0.400$0.15$0.51M1x
37LFM2.5-24B-A2BLiquidAI$0.000400$0.400$0.05$0.7128K1x
38KAT-Coder-Air V2.5Kwaipilot$0.000450$0.450$0.15$0.6256Knot metered
39MiniMax M3.1 FlashMiniMax$0.000450$0.450$0.15$0.61M1x
40DeepSeek V3.2DeepSeek$0.000469$0.469$0.269$0.4164K1x
41Qwen3 Coder NextQwen$0.000520$0.520$0.12$0.8262K1x
42DeepSeek V4 Flash Vision ExpDeepSeek$0.000539$0.539$0.2156$0.64681M1x
43Llama 4 MaverickMeta$0.000600$0.600$0.2$0.81M1x
44Qwen3.6 35B A3BQwen$0.000640$0.640$0.14$1262K1x
45DeepSeek V3.1DeepSeek$0.000725$0.725$0.25$0.95164K1x
46Codestral 2508Mistral$0.000750$0.750$0.3$0.9256K1x
47Qwen3.6 FlashQwen$0.000750$0.750$0.1875$1.1251M1x
48Nex-N2-ProNex Agi$0.000750$0.750$0.25$1262Knot metered
49Beam 1.0 501B A23BReflection$0.000750$0.750$0.25$11M1x
50MiniMax M2MiniMax$0.000765$0.765$0.255$1.02205Knot metered
51Step 3.7 FlashStepfun$0.000775$0.775$0.2$1.15262K1x
52GPT-5.6 Luna ProOpenAI$0.000800$0.800$0.2$1.21Mnot metered
53GPT-5.6 LunaOpenAI$0.000800$0.800$0.2$1.21M1x
54Inkling 2 SmallThinking Machines$0.000800$0.800$0.3$11M2x
55GPT-5.4 NanoOpenAI$0.000825$0.825$0.2$1.25400K2x
56MiMo-V2.6-ProXiaomi$0.000870$0.870$0.435$0.871M2x
57MiniMax M3MiniMax$0.000900$0.900$0.3$1.21M1x
58LongCat 2.0Meituan$0.000900$0.900$0.3$1.21M1x
59Perceptron Mk1Perceptron$0.000900$0.900$0.15$1.533K1x
60DeepSeek V4.1 FlashDeepSeek$0.000900$0.900$0.3$1.21M1x
61Perceptron Mk1.5Perceptron$0.000900$0.900$0.15$1.537K2x
62Qwen3.7 PlusQwen$0.000960$0.960$0.32$1.281M1x
63GLM 5.3 FlashXZ.ai$0.000995$0.995$0.37$1.251M2x
64GLM 5.3 FlashX LegalZ.ai$0.000995$0.995$0.37$1.251M2x
65Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)Google$0.0010$1.000$0.25$1.566Knot metered
66Gemini 3.1 Flash LiteGoogle$0.0010$1.000$0.25$1.51M1x
67Hy4Tencent$0.0010$1.042$0.417$1.25051M2x
68Inkling SmallThinkingmachines$0.0010$1.050$0.45$1.2524K1x
69Command A+Cohere$0.0010$1.050$0.3$1.5192K2x
70Muse Glimmer 30BMeta$0.0011$1.100$0.35$1.5131K2x
71Qwen3.5 Plus 2026-04-20Qwen$0.0012$1.200$0.3$1.81M1x
72Mistral Large 3 2512Mistral$0.0013$1.250$0.5$1.5262K2x
73GLM 4.7Z.ai$0.0013$1.275$0.4$1.75205K2x
74Gemini 3.7 FlashGoogle$0.0013$1.313$0.375$1.8751M2x
75Mistral Medium 3.1Mistral$0.0014$1.400$0.4$2131K2x
76Aion-3.0-MiniAion Labs$0.0014$1.400$0.7$1.4131K2x
77Aion 3.5 MiniAionLabs$0.0014$1.400$0.7$1.4262K3x
78Devstral 2 2512Mistral$0.0014$1.400$0.4$2262K2x
79GLM 4.6Z.ai$0.0015$1.500$0.5$2205K1x
80Gemini 2.5 FlashGoogle$0.0015$1.550$0.3$2.51M2x
81Gemini 3.5 Flash LiteGoogle$0.0015$1.550$0.3$2.51M2x
82Moondream 3 PreviewMoondream$0.0015$1.550$0.3$2.532K2x
83Moondream 3.1Moondream$0.0015$1.550$0.3$2.532K2x
84GLM 5Z.ai$0.0016$1.560$0.6$1.92205K2x
85Kimi K2 0711Moonshot$0.0017$1.720$0.57$2.3131K10x
86Mistral Large 4Mistral$0.0017$1.725$0.68$2.09524K3x
87Seed 2.1 TurboBytedance Seed$0.0018$1.750$0.5$2.5262K2x
88Kimi K2 ThinkingMoonshot$0.0019$1.850$0.6$2.5262K10x
89R1DeepSeek$0.0019$1.950$0.7$2.564Knot metered
90Seed-2.0-CodeBytedance Seed$0.0020$2.000$0.5$3262K3x
91Nano Banana 2 (Gemini 3.1 Flash Image)Google$0.0020$2.000$0.5$3131Knot metered
92Grok Build 0.1xAI$0.0020$2.000$1$2256K3x
93Qwen3.8 27BQwen$0.0021$2.050$0.45$3.21M3x
94Hy4 previewTencent$0.0021$2.084$0.834$2.5011M3x
95GlimpseElorian$0.0021$2.100$0.6$3262K3x
96KAT-Coder-Pro V2.5Kwaipilot$0.0022$2.220$0.74$2.96256Knot metered
97Step 5 PreviewStepFun$0.0024$2.350$1$2.71M4x
98Nova Pro 1.0Amazon$0.0024$2.400$0.8$3.2300K3x
99Nemotron 3 UltraNVIDIA$0.0024$2.400$0.6$3.6512K3x
100Pareto 26.10unbiased$0.0024$2.400$0.8$3.21M4x
101Pareto 26.10 Previewunbiased$0.0024$2.400$0.8$3.21M4x
102Kimi K2.7 CodeMoonshot$0.0025$2.460$0.71$3.5262K10x
103GLM 5.2Z.ai$0.0025$2.484$0.966$3.0361M3x
104Grok 4.3xAI$0.0025$2.500$1.25$2.51M4x
105Gemini 3.6 FlashGoogle$0.0026$2.625$0.75$3.751M3x
106Sakana NamazuSakana$0.0029$2.950$0.95$4262K4x
107DeepSeek V4 Pro 0813DeepSeek$0.0030$2.970$1.188$3.5641M2x
108InklingThinkingmachines$0.0030$2.975$0.95$4.051M4x
109GPT-5.4 MiniOpenAI$0.0030$3.000$0.75$4.5400K4x
110Muse Spark 1.2Meta$0.0034$3.375$1.25$4.251M5x
111Muse Spark 1.1Meta$0.0034$3.375$1.25$4.251M5x
112Muse Spark 1.3Meta$0.0034$3.375$1.25$4.251M5x
113Muse Spark OpenMeta$0.0034$3.375$1.25$4.251M5x
114Claude Haiku 4.5Anthropic$0.0035$3.500$1$5200K4x
115GPT-6.1 TerraOpenAI$0.0035$3.500$1$51M5x
116Qwen4 MaxQwen$0.0036$3.563$1.425$4.2751M5x
117GLM 5.3Z.ai$0.0036$3.600$1.4$4.41M5x
118Qwen3.7 MaxQwen$0.0037$3.688$1.475$4.4251M5x
119Grok 4.7xAI$0.0040$4.000$1.6$4.8500K6x
120Grok 4.5xAI$0.0050$5.000$2$6500K6x
121Qwen3.8 MaxQwen$0.0050$5.000$2$61Mnot metered
122Qwen3.8 2.4T A95BQwen$0.0050$5.000$2$61M8x
123Grok 4.6xAI$0.0050$5.000$2$6500K6x
124Fugu MaxSakana$0.0050$5.000$2$61M8x
125Mistral Medium 3.5Mistral$0.0053$5.250$1.5$7.5262K6x
126Gemini 4 HydrogenGoogle$0.0053$5.250$1.5$7.51M8x
127Gemini 3.5 FlashGoogle$0.0060$6.000$1.5$91M8x
128Aion-3.0Aion Labs$0.0060$6.000$3$6131K10x
129Aion 3.5AionLabs$0.0060$6.000$3$6262K10x
130Pareto 26.9unbiased$0.0063$6.250$2.5$7.5262K10x
131Claude Sonnet 5Anthropic$0.0070$7.000$2$101M10x
132GPT-6 SolOpenAI$0.0070$7.000$2$101M10x
133Claude Sonnet 5.5Anthropic$0.0070$7.000$2$101M10x
134GPT-6.1 SolOpenAI$0.0070$7.000$2$101M10x
135Gemini 4 ArgonGoogle$0.0070$7.000$2$101M10x
136Kimi K3.1 ProMoonshot$0.0070$7.000$2$101M10x
137Gemini 4 CarbonGoogle$0.0070$7.000$2$101M10x
138GPT-6.2 SolOpenAI$0.0070$7.000$2$101M10x
139GLM 5.3 PrimeZ.ai$0.0072$7.200$2.8$8.81M10x
140Command ACohere$0.0075$7.500$2.5$10256K10x
141Gemini 3.1 Pro PreviewGoogle$0.0080$8.000$2$121M10x
142GPT-5.6 Terra ProOpenAI$0.0080$8.000$2$121Mnot metered
143GPT-5.6 TerraOpenAI$0.0080$8.000$2$121M4x
144Nano Banana Pro (Gemini 3 Pro Image)Google$0.0080$8.000$2$12131Knot metered
145MiMo-V2.6-Pro-UltraSpeedXiaomi$0.0087$8.700$4.35$8.71M15x
146GPT-5.4OpenAI$0.010$10.000$2.5$151M15x
147GPT-5.6 Sol ProOpenAI$0.010$10.000$2.5$151Mnot metered
148GPT-5.6 SolOpenAI$0.010$10.000$2.5$151M20x
149Qwen3.8 Max PrimeQwen$0.010$10.000$4$121M15x
150Claude Sonnet 4.6Anthropic$0.011$10.500$3$151M10x
151Claude Sonnet 4.5Anthropic$0.011$10.500$3$151M10x
152Kimi K3Moonshot$0.011$10.500$3$151M10x
153Ember-1Fireworks$0.011$10.500$3$151M15x
154Claude Opus 5.5Anthropic$0.014$14.000$4$201M20x
155Muse WonderMeta$0.014$14.000$4$201M20x
156Claude Opus 5Anthropic$0.018$17.500$5$251M20x
157Claude Opus 4.8Anthropic$0.018$17.500$5$251M20x
158GPT-5.5OpenAI$0.020$20.000$5$301M20x
159GPT Chat LatestOpenAI$0.020$20.000$5$30400K25x
160Fugu UltraSakana$0.020$20.000$5$301M25x
161Fugu Ultra v2Sakana$0.020$20.000$5$301M25x
162Claude Fable 5.2Anthropic$0.028$28.000$8$401M100x
163GPT-6.2 AstraOpenAI$0.028$28.000$8$401M100x
164Claude Opus 5 (Fast)Anthropic$0.035$35.000$10$501Mnot metered
165Claude Fable 5Anthropic$0.035$35.000$10$501M100x
166Claude Opus 4.8 (Fast)Anthropic$0.035$35.000$10$501Mnot metered
167Claude Opus 4.7 (Fast)Anthropic$0.105$105.000$30$1501Mnot metered

Questions

Why price an answer instead of a million tokens?

Because nobody buys a million tokens. Providers quote input and output separately at different rates, so two models can look close per million and differ by a lot on the same real task. Pricing one fixed workload makes the numbers comparable.

Which model is the best value?

Value depends on the task. The useful reading is that the middle of this table is within a few hundredths of a cent per answer, so for most everyday work the price difference between good models is negligible and the choice should be made on output quality.

How often is it updated?

Prices are refreshed from the provider catalogue and the page carries the fetch date, currently August 20, 2026. Rates in this market move often, so check the date before quoting a figure.

What are Whizi credits?

Whizi charges a message against a monthly allowance, and expensive models cost more credits than cheap ones, from 1x up to 20x. The column shows that multiplier so you can see how a provider list rate maps onto a flat subscription.

How to cite this

A dataset is only reused as often as it is easy to credit, so here is the line to copy:

Whizi AI Model Cost Index, prices as of 2026-08-20. https://whizi.io/tools/model-cost-index

Published under CC BY 4.0, which permits commercial reuse as long as the index is named and this page is linked. Writers who need a figure verified before publishing can reach the maintainers at hello@whizi.io.

Next step

Price your own text with the Token counter, or compare plans on Whizi pricing.