← All models
gpt-5-mini · OpenAI
35 runs · same model · across prompts
$0.40 total cost 802k input 1.3M cached 282k output 71.7s avg latency 35 outputs (100% of runs)
▶ preview · view live runtime
71.3s
cost / run
$0.0122
tokens out
9.8k
tokens in
29k
▶ preview · view live runtime
59.2s
cost / run
$0.0117
tokens out
7.8k
tokens in
49k
▶ preview · view live runtime
55.7s
cost / run
$0.0078
tokens out
5.9k
tokens in
30k
▶ preview · view live runtime
119.2s
cost / run
$0.0204
tokens out
13k
tokens in
178k
▶ preview · view live runtime
83.7s
cost / run
$0.0111
tokens out
8.2k
tokens in
46k
▶ preview · view live runtime
52.5s
cost / run
$0.0078
tokens out
6.1k
tokens in
15k
▶ preview · view live runtime
36.5s
cost / run
$0.0066
tokens out
5.1k
tokens in
14k
▶ preview · view live runtime
88.5s
cost / run
$0.0125
tokens out
8.8k
tokens in
64k
▶ preview · view live runtime
57.6s
cost / run
$0.0068
tokens out
5.0k
tokens in
20k
▶ preview · view live runtime
80.6s
cost / run
$0.0135
tokens out
10k
tokens in
45k
▶ preview · view live runtime
79.2s
cost / run
$0.0173
tokens out
10k
tokens in
181k
▶ preview · view live runtime
57.8s
cost / run
$0.0089
tokens out
7.0k
tokens in
16k
▶ preview · view live runtime
100.1s
cost / run
$0.0166
tokens out
12k
tokens in
68k
▶ preview · view live runtime
64.4s
cost / run
$0.0090
tokens out
5.9k
tokens in
62k
▶ preview · view live runtime
30.3s
cost / run
$0.0052
tokens out
4.1k
tokens in
11k
▶ preview · view live runtime
60.9s
cost / run
$0.0118
tokens out
7.8k
tokens in
64k
▶ preview · view live runtime
49.6s
cost / run
$0.0071
tokens out
5.8k
tokens in
14k
▶ preview · view live runtime
138.0s
cost / run
$0.0206
tokens out
14k
tokens in
165k
▶ preview · view live runtime
86.9s
cost / run
$0.0099
tokens out
6.2k
tokens in
58k
▶ preview · view live runtime
72.5s
cost / run
$0.0135
tokens out
9.7k
tokens in
48k
▶ preview · view live runtime
53.6s
cost / run
$0.0087
tokens out
6.5k
tokens in
33k
▶ preview · view live runtime
42.3s
cost / run
$0.0067
tokens out
5.2k
tokens in
19k
▶ preview · view live runtime
78.5s
cost / run
$0.0124
tokens out
10k
tokens in
35k
▶ preview · view live runtime
102.1s
cost / run
$0.0065
tokens out
4.2k
tokens in
29k
▶ preview · view live runtime
84.8s
cost / run
$0.0149
tokens out
9.8k
tokens in
112k
▶ preview · view live runtime
63.5s
cost / run
$0.0102
tokens out
7.4k
tokens in
43k
▶ preview · view live runtime
36.4s
cost / run
$0.0056
tokens out
4.2k
tokens in
14k
▶ preview · view live runtime
45.3s
cost / run
$0.0090
tokens out
7.4k
tokens in
18k
▶ preview · view live runtime
131.6s
cost / run
$0.0216
tokens out
13k
tokens in
214k
▶ preview · view live runtime
50.1s
cost / run
$0.0093
tokens out
6.9k
tokens in
35k
▶ preview · view live runtime
62.2s
cost / run
$0.0094
tokens out
7.2k
tokens in
33k
▶ preview · view live runtime
82.9s
cost / run
$0.0150
tokens out
9.6k
tokens in
133k
▶ preview · view live runtime
75.8s
cost / run
$0.0125
tokens out
8.3k
tokens in
93k
▶ preview · view live runtime
84.6s
cost / run
$0.0139
tokens out
9.4k
tokens in
100k
▶ preview · view live runtime
70.4s
cost / run
$0.0131
tokens out
10k
tokens in
43k