ABCDEFGHIJKLMNOPQRSTUVWXYZ
1
compared to GPT-4oClaude 3.5 Sonnetcompared to Gemini 1.5 Procompared to Mistral-Large
2
ProviderModelinput price per 1M Tokenoutput price per 1M Tokeninput tokenoutput tokeninput tokenoutput tokeninput tokenoutput tokeninput tokenoutput token
3
(Azure)
OpenAI
GPT-4o$2.50$10.000.00%0.00%-16.67%-33.33%-28.57%-4.76%-37.50%-16.67%
4
GPT-4o-mini$0.15$0.60-94.00%-94.00%-99.00%-99.20%-40.00%-52.00%-70.00%-60.00%
5
GPT-4 (8K)$30.00$60.001100.00%500.00%900.00%300.00%757.14%471.43%650.00%400.00%
6
GPT-4 Turbo$10.00$30.00300.00%200.00%233.33%100.00%185.71%185.71%150.00%150.00%
7
(Amazon Bedrock)
Anthropic
Claude 3 (Opus)$15.00$75.00500.00%650.00%400.00%400.00%328.57%614.29%275.00%525.00%
8
Claude 3.5 (Sonnet)$3.00$15.0020.00%50.00%0.00%0.00%-14.29%42.86%-25.00%25.00%
9
Claude 3 (Haiku)$0.25$1.25-90.00%-87.50%-91.67%-91.67%-92.86%-88.10%-93.75%-89.58%
10
Google Vertex AIGemini 1.5 Pro$3.50$10.5040.00%5.00%16.67%-30.00%0.00%0.00%-12.50%-12.50%
11
Gemini 1.5 Flash$0.075$0.35-97.00%-96.50%-97.50%-97.67%-97.86%-96.67%-98.13%-97.08%
12
(Amazon Bedrock)
Cohere
Command R+$3.00$15.0020.00%50.00%0.00%0.00%-14.29%42.86%-25.00%25.00%
13
Command R$0.50$1.50-80.00%-85.00%-83.33%-90.00%-85.71%-85.71%-87.50%-87.50%
14
Mistralmistral-large-2402 $4.00$12.0060.00%20.00%33.33%-20.00%14.29%14.29%0.00%0.00%
15
codestral-2405 $1.00$3.00-60.00%-70.00%-66.67%-80.00%-71.43%-71.43%-75.00%-75.00%
16
open-mixtral-8x22b $2.00$6.00-20.00%-40.00%-33.33%-60.00%-42.86%-42.86%-50.00%-50.00%
17
open-mixtral-8x7b $0.70$0.70-72.00%-93.00%-76.67%-95.33%-80.00%-93.33%-82.50%-94.17%
18
Deepspeekdeepseek-chat$0.14$0.28-94.40%-97.20%-95.33%-98.13%-96.00%-97.33%-96.50%-97.67%
19
deepseek-coder$0.14$0.28-94.40%-97.20%-95.33%-98.13%-96.00%-97.33%-96.50%-97.67%
20
Together.AIMistral-small (8x7B)$0.60$0.60-76.00%-94.00%-80.00%-96.00%-82.86%-94.29%-85.00%-95.00%
21
Llama 3 70b$0.90$0.90-64.00%-91.00%-70.00%-94.00%-74.29%-91.43%-77.50%-92.50%
22
Meta Llama 3.1 405B Turbo
$5.00$5.00100.00%-50.00%66.67%-66.67%42.86%-52.38%25.00%-58.33%
23
CerebrasLlama 3 70b$0.60$0.60-76.00%-94.00%-80.00%-96.00%-82.86%-94.29%-85.00%-95.00%
24
Perplexity APILlama 3 70b$1.00$1.00-60.00%-90.00%-66.67%-93.33%-71.43%-90.48%-75.00%-91.67%
25
Mixtral 8x7B$0.60$0.60-76.00%-94.00%-80.00%-96.00%-82.86%-94.29%-85.00%-95.00%
26
Replicate Llama 3 70b$0.65$2.75-74.00%-72.50%-78.33%-81.67%-81.43%-73.81%-83.75%-77.08%
27
Mixtral 8x7B$0.30$1.00-88.00%-90.00%-90.00%-93.33%-91.43%-90.48%-92.50%-91.67%
28
meta-llama-3.1-405b-instruct
$9.50$9.50280.00%-5.00%216.67%-36.67%171.43%-9.52%137.50%-20.83%
29
IBM WatsonXLlama 3 70b$1.80$1.80-28.00%-82.00%-40.00%-88.00%-48.57%-82.86%-55.00%-85.00%
30
Llama 3.1 405B$5.00$35.00100.00%250.00%66.67%133.33%42.86%233.33%25.00%191.67%
31
Mistral Large$10.00$10.00300.00%0.00%233.33%-33.33%185.71%-4.76%150.00%-16.67%
32
GroqLlama 3 70b$0.59$0.79-76.40%-92.10%-80.33%-94.73%-83.14%-92.48%-85.25%-93.42%
33
Mixtral 8x7B$0.24$0.24-90.40%-97.60%-92.00%-98.40%-93.14%-97.71%-94.00%-98.00%
34
FireworksLlama 3 70b$0.90$0.90-64.00%-91.00%-70.00%-94.00%-74.29%-91.43%-77.50%-92.50%
35
Mixtral 8x7B$0.50$0.50-80.00%-95.00%-83.33%-96.67%-85.71%-95.24%-87.50%-95.83%
36
Meta Llama 3.1 405B $3.00$3.0020.00%-70.00%0.00%-80.00%-14.29%-71.43%-25.00%-75.00%
37
Yi-Large$3.00$3.0020.00%-70.00%0.00%-80.00%-14.29%-71.43%-25.00%-75.00%
38
01.aiYi-Large$3.00$3.0020.00%-70.00%0.00%-80.00%-14.29%-71.43%-25.00%-75.00%
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100