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.
#
Model
Provider
Per answer
Per 1,000 answers
$ / 1M in
$ / 1M out
Context
Whizi credits
1
Ling-3.0-flash
inclusionAI
$0.000053
$0.052
$0.021
$0.063
262K
1x
2
Nex-N2-Mini
Nex Agi
$0.000075
$0.075
$0.025
$0.1
262K
not metered
3
Nex-N2.5-Mini
Nex AGI
$0.000075
$0.075
$0.025
$0.1
262K
1x
4
Solar Pro 4
Upstage
$0.000090
$0.090
$0.03
$0.12
524K
1x
5
Qwen3.7 Flash
Qwen
$0.000095
$0.095
$0.03
$0.13
1M
1x
6
Granite 4.1 8B
Ibm Granite
$0.000100
$0.100
$0.05
$0.1
131K
not metered
7
Hy4 flash
Tencent
$0.000105
$0.105
$0.035
$0.1405
1M
1x
8
Mercury 2.5
Inception
$0.000115
$0.115
$0.04
$0.15
260K
not metered
9
Laguna XS 2.1
Poolside
$0.000120
$0.120
$0.06
$0.12
262K
not metered
10
Hy-MT2-1.8B
Tencent
$0.000133
$0.133
$0.044
$0.177
8K
not metered
11
Phi 4
Microsoft
$0.000140
$0.140
$0.07
$0.14
16K
1x
12
Ternary Bonsai 2 9B
PrismML
$0.000145
$0.145
$0.08
$0.13
262K
1x
13
Solar Mini 4
Upstage
$0.000150
$0.150
$0.05
$0.2
524K
1x
14
Nemotron 3.5 Lightning
NVIDIA
$0.000180
$0.180
$0.08
$0.2
262K
1x
15
Laguna S 2.1
Poolside
$0.000180
$0.180
$0.09
$0.18
1M
not metered
16
LFM3-1.7B
LiquidAI
$0.000180
$0.180
$0.08
$0.2
262K
1x
17
Granite 4.2 8B
IBM
$0.000185
$0.185
$0.06
$0.25
131K
1x
18
Ling 3.1 Flash
inclusionAI
$0.000188
$0.188
$0.075
$0.225
262K
1x
19
Nex-N2.5-Pro
Nex AGI
$0.000200
$0.200
$0.075
$0.25
262K
1x
20
Hy-MT2-30B-A3B
Tencent
$0.000222
$0.222
$0.074
$0.295
8K
not metered
21
Llama 3.3 70B Instruct
Meta
$0.000260
$0.260
$0.1
$0.32
131K
1x
22
Mercury 3
Inception
$0.000275
$0.275
$0.1
$0.35
1M
not metered
23
DeepSeek V4 Flash 0731
DeepSeek
$0.000280
$0.280
$0.14
$0.28
1M
1x
24
MiMo-V2.6-Flash
Xiaomi
$0.000280
$0.280
$0.14
$0.28
1M
1x
25
GLM 5.3 Flash
Z.ai
$0.000290
$0.290
$0.04
$0.5
1M
1x
26
Gemini 2.5 Flash Lite
Google
$0.000300
$0.300
$0.1
$0.4
1M
1x
27
Nex-N2.6
Nex AGI
$0.000320
$0.320
$0.12
$0.4
262K
1x
28
Ternary Bonsai 2 27B
PrismML
$0.000325
$0.325
$0.075
$0.5
262K
1x
29
GPT-6 Luna
OpenAI
$0.000350
$0.350
$0.1
$0.5
1M
1x
30
Claude Haiku 5.5
Anthropic
$0.000350
$0.350
$0.1
$0.5
1M
1x
31
Muse Ember
Meta
$0.000350
$0.350
$0.1
$0.5
1M
1x
32
Qwen3.8 Flash
Qwen
$0.000385
$0.385
$0.15
$0.47
1M
1x
33
Qwen3.8 Omni Flash
Qwen
$0.000385
$0.385
$0.15
$0.47
1M
1x
34
Ring-2.6-1T
inclusionAI
$0.000388
$0.388
$0.075
$0.625
262K
not metered
35
Hy3
Tencent
$0.000396
$0.396
$0.132
$0.528
262K
1x
36
Nemotron 3.5 Super VL
NVIDIA
$0.000400
$0.400
$0.15
$0.5
1M
1x
37
LFM2.5-24B-A2B
LiquidAI
$0.000400
$0.400
$0.05
$0.7
128K
1x
38
KAT-Coder-Air V2.5
Kwaipilot
$0.000450
$0.450
$0.15
$0.6
256K
not metered
39
MiniMax M3.1 Flash
MiniMax
$0.000450
$0.450
$0.15
$0.6
1M
1x
40
DeepSeek V3.2
DeepSeek
$0.000469
$0.469
$0.269
$0.4
164K
1x
41
Qwen3 Coder Next
Qwen
$0.000520
$0.520
$0.12
$0.8
262K
1x
42
DeepSeek V4 Flash Vision Exp
DeepSeek
$0.000539
$0.539
$0.2156
$0.6468
1M
1x
43
Llama 4 Maverick
Meta
$0.000600
$0.600
$0.2
$0.8
1M
1x
44
Qwen3.6 35B A3B
Qwen
$0.000640
$0.640
$0.14
$1
262K
1x
45
DeepSeek V3.1
DeepSeek
$0.000725
$0.725
$0.25
$0.95
164K
1x
46
Codestral 2508
Mistral
$0.000750
$0.750
$0.3
$0.9
256K
1x
47
Qwen3.6 Flash
Qwen
$0.000750
$0.750
$0.1875
$1.125
1M
1x
48
Nex-N2-Pro
Nex Agi
$0.000750
$0.750
$0.25
$1
262K
not metered
49
Beam 1.0 501B A23B
Reflection
$0.000750
$0.750
$0.25
$1
1M
1x
50
MiniMax M2
MiniMax
$0.000765
$0.765
$0.255
$1.02
205K
not metered
51
Step 3.7 Flash
Stepfun
$0.000775
$0.775
$0.2
$1.15
262K
1x
52
GPT-5.6 Luna Pro
OpenAI
$0.000800
$0.800
$0.2
$1.2
1M
not metered
53
GPT-5.6 Luna
OpenAI
$0.000800
$0.800
$0.2
$1.2
1M
1x
54
Inkling 2 Small
Thinking Machines
$0.000800
$0.800
$0.3
$1
1M
2x
55
GPT-5.4 Nano
OpenAI
$0.000825
$0.825
$0.2
$1.25
400K
2x
56
MiMo-V2.6-Pro
Xiaomi
$0.000870
$0.870
$0.435
$0.87
1M
2x
57
MiniMax M3
MiniMax
$0.000900
$0.900
$0.3
$1.2
1M
1x
58
LongCat 2.0
Meituan
$0.000900
$0.900
$0.3
$1.2
1M
1x
59
Perceptron Mk1
Perceptron
$0.000900
$0.900
$0.15
$1.5
33K
1x
60
DeepSeek V4.1 Flash
DeepSeek
$0.000900
$0.900
$0.3
$1.2
1M
1x
61
Perceptron Mk1.5
Perceptron
$0.000900
$0.900
$0.15
$1.5
37K
2x
62
Qwen3.7 Plus
Qwen
$0.000960
$0.960
$0.32
$1.28
1M
1x
63
GLM 5.3 FlashX
Z.ai
$0.000995
$0.995
$0.37
$1.25
1M
2x
64
GLM 5.3 FlashX Legal
Z.ai
$0.000995
$0.995
$0.37
$1.25
1M
2x
65
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)
Google
$0.0010
$1.000
$0.25
$1.5
66K
not metered
66
Gemini 3.1 Flash Lite
Google
$0.0010
$1.000
$0.25
$1.5
1M
1x
67
Hy4
Tencent
$0.0010
$1.042
$0.417
$1.2505
1M
2x
68
Inkling Small
Thinkingmachines
$0.0010
$1.050
$0.45
$1.2
524K
1x
69
Command A+
Cohere
$0.0010
$1.050
$0.3
$1.5
192K
2x
70
Muse Glimmer 30B
Meta
$0.0011
$1.100
$0.35
$1.5
131K
2x
71
Qwen3.5 Plus 2026-04-20
Qwen
$0.0012
$1.200
$0.3
$1.8
1M
1x
72
Mistral Large 3 2512
Mistral
$0.0013
$1.250
$0.5
$1.5
262K
2x
73
GLM 4.7
Z.ai
$0.0013
$1.275
$0.4
$1.75
205K
2x
74
Gemini 3.7 Flash
Google
$0.0013
$1.313
$0.375
$1.875
1M
2x
75
Mistral Medium 3.1
Mistral
$0.0014
$1.400
$0.4
$2
131K
2x
76
Aion-3.0-Mini
Aion Labs
$0.0014
$1.400
$0.7
$1.4
131K
2x
77
Aion 3.5 Mini
AionLabs
$0.0014
$1.400
$0.7
$1.4
262K
3x
78
Devstral 2 2512
Mistral
$0.0014
$1.400
$0.4
$2
262K
2x
79
GLM 4.6
Z.ai
$0.0015
$1.500
$0.5
$2
205K
1x
80
Gemini 2.5 Flash
Google
$0.0015
$1.550
$0.3
$2.5
1M
2x
81
Gemini 3.5 Flash Lite
Google
$0.0015
$1.550
$0.3
$2.5
1M
2x
82
Moondream 3 Preview
Moondream
$0.0015
$1.550
$0.3
$2.5
32K
2x
83
Moondream 3.1
Moondream
$0.0015
$1.550
$0.3
$2.5
32K
2x
84
GLM 5
Z.ai
$0.0016
$1.560
$0.6
$1.92
205K
2x
85
Kimi K2 0711
Moonshot
$0.0017
$1.720
$0.57
$2.3
131K
10x
86
Mistral Large 4
Mistral
$0.0017
$1.725
$0.68
$2.09
524K
3x
87
Seed 2.1 Turbo
Bytedance Seed
$0.0018
$1.750
$0.5
$2.5
262K
2x
88
Kimi K2 Thinking
Moonshot
$0.0019
$1.850
$0.6
$2.5
262K
10x
89
R1
DeepSeek
$0.0019
$1.950
$0.7
$2.5
64K
not metered
90
Seed-2.0-Code
Bytedance Seed
$0.0020
$2.000
$0.5
$3
262K
3x
91
Nano Banana 2 (Gemini 3.1 Flash Image)
Google
$0.0020
$2.000
$0.5
$3
131K
not metered
92
Grok Build 0.1
xAI
$0.0020
$2.000
$1
$2
256K
3x
93
Qwen3.8 27B
Qwen
$0.0021
$2.050
$0.45
$3.2
1M
3x
94
Hy4 preview
Tencent
$0.0021
$2.084
$0.834
$2.501
1M
3x
95
Glimpse
Elorian
$0.0021
$2.100
$0.6
$3
262K
3x
96
KAT-Coder-Pro V2.5
Kwaipilot
$0.0022
$2.220
$0.74
$2.96
256K
not metered
97
Step 5 Preview
StepFun
$0.0024
$2.350
$1
$2.7
1M
4x
98
Nova Pro 1.0
Amazon
$0.0024
$2.400
$0.8
$3.2
300K
3x
99
Nemotron 3 Ultra
NVIDIA
$0.0024
$2.400
$0.6
$3.6
512K
3x
100
Pareto 26.10
unbiased
$0.0024
$2.400
$0.8
$3.2
1M
4x
101
Pareto 26.10 Preview
unbiased
$0.0024
$2.400
$0.8
$3.2
1M
4x
102
Kimi K2.7 Code
Moonshot
$0.0025
$2.460
$0.71
$3.5
262K
10x
103
GLM 5.2
Z.ai
$0.0025
$2.484
$0.966
$3.036
1M
3x
104
Grok 4.3
xAI
$0.0025
$2.500
$1.25
$2.5
1M
4x
105
Gemini 3.6 Flash
Google
$0.0026
$2.625
$0.75
$3.75
1M
3x
106
Sakana Namazu
Sakana
$0.0029
$2.950
$0.95
$4
262K
4x
107
DeepSeek V4 Pro 0813
DeepSeek
$0.0030
$2.970
$1.188
$3.564
1M
2x
108
Inkling
Thinkingmachines
$0.0030
$2.975
$0.95
$4.05
1M
4x
109
GPT-5.4 Mini
OpenAI
$0.0030
$3.000
$0.75
$4.5
400K
4x
110
Muse Spark 1.2
Meta
$0.0034
$3.375
$1.25
$4.25
1M
5x
111
Muse Spark 1.1
Meta
$0.0034
$3.375
$1.25
$4.25
1M
5x
112
Muse Spark 1.3
Meta
$0.0034
$3.375
$1.25
$4.25
1M
5x
113
Muse Spark Open
Meta
$0.0034
$3.375
$1.25
$4.25
1M
5x
114
Claude Haiku 4.5
Anthropic
$0.0035
$3.500
$1
$5
200K
4x
115
GPT-6.1 Terra
OpenAI
$0.0035
$3.500
$1
$5
1M
5x
116
Qwen4 Max
Qwen
$0.0036
$3.563
$1.425
$4.275
1M
5x
117
GLM 5.3
Z.ai
$0.0036
$3.600
$1.4
$4.4
1M
5x
118
Qwen3.7 Max
Qwen
$0.0037
$3.688
$1.475
$4.425
1M
5x
119
Grok 4.7
xAI
$0.0040
$4.000
$1.6
$4.8
500K
6x
120
Grok 4.5
xAI
$0.0050
$5.000
$2
$6
500K
6x
121
Qwen3.8 Max
Qwen
$0.0050
$5.000
$2
$6
1M
not metered
122
Qwen3.8 2.4T A95B
Qwen
$0.0050
$5.000
$2
$6
1M
8x
123
Grok 4.6
xAI
$0.0050
$5.000
$2
$6
500K
6x
124
Fugu Max
Sakana
$0.0050
$5.000
$2
$6
1M
8x
125
Mistral Medium 3.5
Mistral
$0.0053
$5.250
$1.5
$7.5
262K
6x
126
Gemini 4 Hydrogen
Google
$0.0053
$5.250
$1.5
$7.5
1M
8x
127
Gemini 3.5 Flash
Google
$0.0060
$6.000
$1.5
$9
1M
8x
128
Aion-3.0
Aion Labs
$0.0060
$6.000
$3
$6
131K
10x
129
Aion 3.5
AionLabs
$0.0060
$6.000
$3
$6
262K
10x
130
Pareto 26.9
unbiased
$0.0063
$6.250
$2.5
$7.5
262K
10x
131
Claude Sonnet 5
Anthropic
$0.0070
$7.000
$2
$10
1M
10x
132
GPT-6 Sol
OpenAI
$0.0070
$7.000
$2
$10
1M
10x
133
Claude Sonnet 5.5
Anthropic
$0.0070
$7.000
$2
$10
1M
10x
134
GPT-6.1 Sol
OpenAI
$0.0070
$7.000
$2
$10
1M
10x
135
Gemini 4 Argon
Google
$0.0070
$7.000
$2
$10
1M
10x
136
Kimi K3.1 Pro
Moonshot
$0.0070
$7.000
$2
$10
1M
10x
137
Gemini 4 Carbon
Google
$0.0070
$7.000
$2
$10
1M
10x
138
GPT-6.2 Sol
OpenAI
$0.0070
$7.000
$2
$10
1M
10x
139
GLM 5.3 Prime
Z.ai
$0.0072
$7.200
$2.8
$8.8
1M
10x
140
Command A
Cohere
$0.0075
$7.500
$2.5
$10
256K
10x
141
Gemini 3.1 Pro Preview
Google
$0.0080
$8.000
$2
$12
1M
10x
142
GPT-5.6 Terra Pro
OpenAI
$0.0080
$8.000
$2
$12
1M
not metered
143
GPT-5.6 Terra
OpenAI
$0.0080
$8.000
$2
$12
1M
4x
144
Nano Banana Pro (Gemini 3 Pro Image)
Google
$0.0080
$8.000
$2
$12
131K
not metered
145
MiMo-V2.6-Pro-UltraSpeed
Xiaomi
$0.0087
$8.700
$4.35
$8.7
1M
15x
146
GPT-5.4
OpenAI
$0.010
$10.000
$2.5
$15
1M
15x
147
GPT-5.6 Sol Pro
OpenAI
$0.010
$10.000
$2.5
$15
1M
not metered
148
GPT-5.6 Sol
OpenAI
$0.010
$10.000
$2.5
$15
1M
20x
149
Qwen3.8 Max Prime
Qwen
$0.010
$10.000
$4
$12
1M
15x
150
Claude Sonnet 4.6
Anthropic
$0.011
$10.500
$3
$15
1M
10x
151
Claude Sonnet 4.5
Anthropic
$0.011
$10.500
$3
$15
1M
10x
152
Kimi K3
Moonshot
$0.011
$10.500
$3
$15
1M
10x
153
Ember-1
Fireworks
$0.011
$10.500
$3
$15
1M
15x
154
Claude Opus 5.5
Anthropic
$0.014
$14.000
$4
$20
1M
20x
155
Muse Wonder
Meta
$0.014
$14.000
$4
$20
1M
20x
156
Claude Opus 5
Anthropic
$0.018
$17.500
$5
$25
1M
20x
157
Claude Opus 4.8
Anthropic
$0.018
$17.500
$5
$25
1M
20x
158
GPT-5.5
OpenAI
$0.020
$20.000
$5
$30
1M
20x
159
GPT Chat Latest
OpenAI
$0.020
$20.000
$5
$30
400K
25x
160
Fugu Ultra
Sakana
$0.020
$20.000
$5
$30
1M
25x
161
Fugu Ultra v2
Sakana
$0.020
$20.000
$5
$30
1M
25x
162
Claude Fable 5.2
Anthropic
$0.028
$28.000
$8
$40
1M
100x
163
GPT-6.2 Astra
OpenAI
$0.028
$28.000
$8
$40
1M
100x
164
Claude Opus 5 (Fast)
Anthropic
$0.035
$35.000
$10
$50
1M
not metered
165
Claude Fable 5
Anthropic
$0.035
$35.000
$10
$50
1M
100x
166
Claude Opus 4.8 (Fast)
Anthropic
$0.035
$35.000
$10
$50
1M
not metered
167
Claude Opus 4.7 (Fast)
Anthropic
$0.105
$105.000
$30
$150
1M
not 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.