← All models
nemotron-3.5-super-vl · NVIDIA
35 runs · same model · across prompts
$1.65 total cost 7.9M input 4.9M cached 720k output 142.4s avg latency 35 outputs (100% of runs)
▶ preview · view live runtime
110.5s
cost / run
$0.0253
tokens out
23k
tokens in
126k
▶ preview · view live runtime
41.1s
cost / run
$0.0098
tokens out
7.0k
tokens in
46k
▶ preview · view live runtime
54.0s
cost / run
$0.0110
tokens out
6.7k
tokens in
55k
Stopped by an API error ▶ preview · view live runtime
312.6s
cost / run
$0.1136
tokens out
45k
tokens in
874k
▶ preview · view live runtime
56.1s
cost / run
$0.0129
tokens out
10k
tokens in
64k
▶ preview · view live runtime
66.1s
cost / run
$0.0129
tokens out
11k
tokens in
55k
▶ preview · view live runtime
52.7s
cost / run
$0.0238
tokens out
6.3k
tokens in
186k
Stopped by an API error ▶ preview · view live runtime
258.9s
cost / run
$0.0907
tokens out
23k
tokens in
704k
▶ preview · view live runtime
144.8s
cost / run
$0.0499
tokens out
16k
tokens in
436k
Stopped by an API error ▶ preview · view live runtime
166.8s
cost / run
$0.0810
tokens out
8.4k
tokens in
633k
Stopped by an API error ▶ preview · view live runtime
799.6s
cost / run
$0.1679
tokens out
170k
tokens in
1378k
▶ preview · view live runtime
81.6s
cost / run
$0.0218
tokens out
12k
tokens in
155k
▶ preview · view live runtime
123.4s
cost / run
$0.0715
tokens out
12k
tokens in
549k
▶ preview · view live runtime
32.6s
cost / run
$0.0079
tokens out
4.3k
tokens in
42k
▶ preview · view live runtime
56.3s
cost / run
$0.0125
tokens out
7.7k
tokens in
58k
▶ preview · view live runtime
184.6s
cost / run
$0.0477
tokens out
38k
tokens in
342k
Stopped by an API error ▶ preview · view live runtime
292.8s
cost / run
$0.1402
tokens out
25k
tokens in
1587k
▶ preview · view live runtime
113.1s
cost / run
$0.0247
tokens out
17k
tokens in
125k
Stopped by an API error ▶ preview · view live runtime
250.7s
cost / run
$0.0935
tokens out
19k
tokens in
698k
▶ preview · view live runtime
156.0s
cost / run
$0.0529
tokens out
23k
tokens in
563k
▶ preview · view live runtime
96.4s
cost / run
$0.0209
tokens out
16k
tokens in
123k
▶ preview · view live runtime
48.6s
cost / run
$0.0117
tokens out
6.8k
tokens in
59k
▶ preview · view live runtime
131.3s
cost / run
$0.0473
tokens out
17k
tokens in
333k
▶ preview · view live runtime
88.4s
cost / run
$0.0121
tokens out
16k
tokens in
27k
▶ preview · view live runtime
98.5s
cost / run
$0.0298
tokens out
13k
tokens in
285k
▶ preview · view live runtime
79.2s
cost / run
$0.0325
tokens out
11k
tokens in
274k
▶ preview · view live runtime
31.0s
cost / run
$0.0063
tokens out
4.8k
tokens in
26k
▶ preview · view live runtime
391.9s
cost / run
$0.1550
tokens out
77k
tokens in
1031k
Stopped by an API error ▶ preview · view live runtime
205.2s
cost / run
$0.0886
tokens out
12k
tokens in
698k
▶ preview · view live runtime
37.8s
cost / run
$0.0113
tokens out
7.1k
tokens in
63k
▶ preview · view live runtime
42.8s
cost / run
$0.0116
tokens out
6.3k
tokens in
68k
▶ preview · view live runtime
47.6s
cost / run
$0.0143
tokens out
6.9k
tokens in
117k
▶ preview · view live runtime
74.2s
cost / run
$0.0211
tokens out
12k
tokens in
152k
Stopped by an API error ▶ preview · view live runtime
182.3s
cost / run
$0.0978
tokens out
13k
tokens in
823k
▶ preview · view live runtime
72.6s
cost / run
$0.0153
tokens out
16k
tokens in
57k