LLM API Workload Cost Calculator
No token math required. Pick a use case, enter your volume, and see how much each model costs you per month.
① Pick a use case
Choose the closest match — we'll prefill typical usage, then you can tweak it.
500 conversations/day, ~2000 input + 500 output tokens each
② Adjust your volume
/ day
tokens
tokens
days
Days the service actually runs each month (use 30 for 24/7).
③ Monthly cost ranking
Based on 500 requests/day × 30 days/month, averaging 2,000 input + 500 output tokens:
Cheapest
Phi-4-mini
$0.900 / mo
Lowest total monthly cost
Best Value
Phi-4-mini
$0.900 / mo
Highest quality score ÷ cost
Top Performance
gpt-6-astra
Quality 99
Highest benchmark quality score
1
Phi-4-miniCheapestBest Value
Microsoft· Quality 68
$0.900/ mo
$0.030 / day · $0.00006 / req
2
qwen3.7-flash
Alibaba· Quality 82
$1.88/ mo
$0.063 / day · $0.00013 / req
3
mercury-2.5-preview
Inception· Quality 82
$2.33/ mo
$0.077 / day · $0.00015 / req
4
qwen-turbo
Alibaba· Quality 74
$3.00/ mo
$0.100 / day · $0.00020 / req
5
Phi-4
Microsoft· Quality 76
$3.15/ mo
$0.105 / day · $0.00021 / req
6
Hunyuan HY3
Tencent· Quality 87
$3.46/ mo
$0.116 / day · $0.00023 / req
7
granite-4.2-8b
IBM· Quality 77
$3.67/ mo
$0.122 / day · $0.00024 / req
8
Ling-3.0-flash
InclusionAI· Quality 80
$3.75/ mo
$0.125 / day · $0.00025 / req
9
Baichuan4-Air
Baichuan· Quality 70
$5.10/ mo
$0.170 / day · $0.00034 / req
10
Step 3.5 Flash
StepFun· Quality 79
$5.25/ mo
$0.175 / day · $0.00035 / req
11
Yi-Lightning
01.AI· Quality 78
$5.25/ mo
$0.175 / day · $0.00035 / req
12
Hunyuan TurboS
Tencent· Quality 79
$5.40/ mo
$0.180 / day · $0.00036 / req
13
MAI-DS-R1
Microsoft· Quality 90
$6.30/ mo
$0.210 / day · $0.00042 / req
14
mimo-v2.6-flash
Xiaomi
$6.30/ mo
$0.210 / day · $0.00042 / req
15
gpt-6-luna
OpenAI
$6.75/ mo
$0.225 / day · $0.00045 / req
16
claude-haiku-5.5
Anthropic
$6.75/ mo
$0.225 / day · $0.00045 / req
17
qwen3.5
Alibaba· Quality 91
$6.98/ mo
$0.233 / day · $0.00047 / req
18
qwen3.8-flash
Alibaba· Quality 90
$8.03/ mo
$0.268 / day · $0.00053 / req
19
qwen3.5-flash
Alibaba· Quality 82
$8.03/ mo
$0.268 / day · $0.00053 / req
20
GLM-5.3-Flash
Zhipu· Quality 89
$8.25/ mo
$0.275 / day · $0.00055 / req
21
gpt-4o-mini
OpenAI· Quality 80
$9.00/ mo
$0.300 / day · $0.00060 / req
22
deepseek-v4-flash
DeepSeek· Quality 88
$9.00/ mo
$0.300 / day · $0.00060 / req
23
qwen-plus
Alibaba· Quality 84
$13.65/ mo
$0.455 / day · $0.00091 / req
24
Step 3.7 Flash
StepFun· Quality 85
$14.63/ mo
$0.487 / day · $0.00097 / req
25
gpt-5.6-luna
OpenAI· Quality 90
$15.00/ mo
$0.500 / day · $0.00100 / req
26
gpt-5.4-nano
OpenAI· Quality 75
$15.38/ mo
$0.513 / day · $0.00103 / req
27
codestral-latest
Mistral· Quality 80
$15.75/ mo
$0.525 / day · $0.00105 / req
28
deepseek-chat-v4
DeepSeek· Quality 88
$16.28/ mo
$0.542 / day · $0.00109 / req
29
ERNIE X1
Baidu· Quality 86
$16.65/ mo
$0.555 / day · $0.00111 / req
30
MiniMax-M3
MiniMax· Quality 89
$18.00/ mo
$0.600 / day · $0.00120 / req
31
gemini-3.1-flash-lite
Google· Quality 80
$18.75/ mo
$0.625 / day · $0.00125 / req
32
qwen3.5-plus
Alibaba· Quality 89
$19.20/ mo
$0.640 / day · $0.00128 / req
33
deepseek-reasoner-v4
DeepSeek· Quality 92
$19.57/ mo
$0.652 / day · $0.00130 / req
34
mimo-v2.6-pro
Xiaomi
$19.57/ mo
$0.652 / day · $0.00130 / req
35
llama-3.3-70b-versatile
Groq· Quality 78
$23.63/ mo
$0.787 / day · $0.00158 / req
36
Llama-3.3-70B-Instruct
Microsoft· Quality 78
$26.63/ mo
$0.888 / day · $0.00178 / req
37
gemini-2.5-flash
Google· Quality 84
$27.75/ mo
$0.925 / day · $0.00185 / req
38
doubao-seed-2.1-turbo
ByteDance· Quality 85
$27.82/ mo
$0.927 / day · $0.00185 / req
39
meta-llama/Llama-3.3-70B-Instruct-Turbo
Together AI· Quality 78
$33.00/ mo
$1.10 / day · $0.00220 / req
40
ERNIE 4.5
Baidu· Quality 84
$33.00/ mo
$1.10 / day · $0.00220 / req
41
GLM-4.7
Zhipu· Quality 87
$34.50/ mo
$1.15 / day · $0.00230 / req
42
deepseek-v4-pro
DeepSeek· Quality 93
$34.65/ mo
$1.16 / day · $0.00231 / req
43
mistral-large-4-0
Mistral
$36.75/ mo
$1.22 / day · $0.00245 / req
44
ERNIE 5.1
Baidu· Quality 90
$37.58/ mo
$1.25 / day · $0.00251 / req
45
Qwen/Qwen2.5-72B-Instruct-Turbo
Together AI· Quality 79
$45.00/ mo
$1.50 / day · $0.00300 / req
46
kimi-k2.6
Moonshot AI· Quality 90
$45.08/ mo
$1.50 / day · $0.00301 / req
47
gemini-3.8-flash
Google· Quality 92
$50.63/ mo
$1.69 / day · $0.00337 / req
48
gemini-3.7-flash
Google· Quality 90
$50.63/ mo
$1.69 / day · $0.00337 / req
49
gemini-3.6-flash
Google· Quality 85
$50.63/ mo
$1.69 / day · $0.00337 / req
50
doubao-seed-2.1-pro
ByteDance· Quality 91
$55.95/ mo
$1.86 / day · $0.00373 / req
51
grok-4.20
xAI· Quality 90
$56.25/ mo
$1.88 / day · $0.00375 / req
52
grok-4.3
xAI· Quality 89
$56.25/ mo
$1.88 / day · $0.00375 / req
53
gpt-5.4-mini
OpenAI· Quality 85
$56.25/ mo
$1.88 / day · $0.00375 / req
54
o4-mini
OpenAI· Quality 88
$66.00/ mo
$2.20 / day · $0.00440 / req
55
gpt-6.1-terra
OpenAI
$67.50/ mo
$2.25 / day · $0.00450 / req
56
claude-haiku-4-5
Anthropic· Quality 82
$67.50/ mo
$2.25 / day · $0.00450 / req
57
GLM-5.3
Zhipu· Quality 94
$75.00/ mo
$2.50 / day · $0.00500 / req
58
GLM-5.2
Zhipu· Quality 93
$75.00/ mo
$2.50 / day · $0.00500 / req
59
mistral-medium-3.5
Mistral· Quality 86
$101/ mo
$3.38 / day · $0.00675 / req
60
mistral-large-3
Mistral· Quality 82
$105/ mo
$3.50 / day · $0.00700 / req
61
grok-4.7
xAI
$105/ mo
$3.50 / day · $0.00700 / req
62
grok-4.6
xAI· Quality 93
$105/ mo
$3.50 / day · $0.00700 / req
63
grok-4.5
xAI· Quality 91
$105/ mo
$3.50 / day · $0.00700 / req
64
qwen3.8-max
Alibaba· Quality 94
$105/ mo
$3.50 / day · $0.00700 / req
65
gemini-2.5-pro
Google· Quality 93
$113/ mo
$3.75 / day · $0.00750 / req
66
gemini-3.5-flash
Google· Quality 86
$113/ mo
$3.75 / day · $0.00750 / req
67
o3
OpenAI· Quality 95
$120/ mo
$4.00 / day · $0.00800 / req
68
gpt-6.1-sol
OpenAI
$135/ mo
$4.50 / day · $0.00900 / req
69
gpt-6-sol
OpenAI
$135/ mo
$4.50 / day · $0.00900 / req
70
claude-sonnet-5.5
Anthropic
$135/ mo
$4.50 / day · $0.00900 / req
71
claude-sonnet-5
Anthropic· Quality 92
$135/ mo
$4.50 / day · $0.00900 / req
72
gpt-5.6-terra
OpenAI· Quality 95
$150/ mo
$5.00 / day · $0.010 / req
73
gpt-4o
OpenAI· Quality 88
$150/ mo
$5.00 / day · $0.010 / req
74
gemini-3.1-pro
Google· Quality 91
$150/ mo
$5.00 / day · $0.010 / req
75
command-a
Cohere· Quality 83
$150/ mo
$5.00 / day · $0.010 / req
76
command-r
Cohere· Quality 75
$150/ mo
$5.00 / day · $0.010 / req
77
gpt-5.4
OpenAI· Quality 92
$188/ mo
$6.25 / day · $0.013 / req
78
claude-sonnet-4-6
Anthropic· Quality 90
$203/ mo
$6.75 / day · $0.013 / req
79
kimi-k3
Moonshot AI· Quality 95
$203/ mo
$6.75 / day · $0.013 / req
80
gpt-5.6-sol
OpenAI· Quality 98
$270/ mo
$9.00 / day · $0.018 / req
81
claude-opus-5.5
Anthropic
$270/ mo
$9.00 / day · $0.018 / req
82
claude-opus-5
Anthropic· Quality 97
$338/ mo
$11.25 / day · $0.022 / req
83
claude-opus-4-8
Anthropic· Quality 94
$338/ mo
$11.25 / day · $0.022 / req
84
claude-opus-4-6
Anthropic· Quality 93
$338/ mo
$11.25 / day · $0.022 / req
85
gpt-5.5
OpenAI· Quality 97
$375/ mo
$12.50 / day · $0.025 / req
86
Baichuan4
Baichuan· Quality 80
$521/ mo
$17.36 / day · $0.035 / req
87
claude-fable-5.2
Anthropic
$540/ mo
$18.00 / day · $0.036 / req
88
gpt-6-astraTop Performance
OpenAI· Quality 99
$675/ mo
$22.50 / day · $0.045 / req
89
claude-fable-5.1
Anthropic· Quality 97
$675/ mo
$22.50 / day · $0.045 / req
90
claude-fable-5
Anthropic· Quality 96
$675/ mo
$22.50 / day · $0.045 / req
91
claude-mythos-5
Anthropic· Quality 96
$675/ mo
$22.50 / day · $0.045 / req
Loading model prices…