← All models
gpt-5.6-terra · OpenAI
35 runs · same model · across prompts
$2.00 total cost 621k input 3.3M cached 149k output 68.8s avg latency 35 outputs (100% of runs)
▶ preview · view live runtime
107.0s
cost / run
$0.1123
tokens out
6.1k
tokens in
346k
▶ preview · view live runtime
97.1s
cost / run
$0.0598
tokens out
4.8k
tokens in
118k
▶ preview · view live runtime
50.1s
cost / run
$0.0556
tokens out
2.8k
tokens in
115k
▶ preview · view live runtime
92.5s
cost / run
$0.0862
tokens out
6.9k
tokens in
177k
▶ preview · view live runtime
76.7s
cost / run
$0.0699
tokens out
4.5k
tokens in
170k
▶ preview · view live runtime
69.0s
cost / run
$0.0617
tokens out
4.5k
tokens in
124k
▶ preview · view live runtime
53.7s
cost / run
$0.0508
tokens out
3.3k
tokens in
88k
▶ preview · view live runtime
53.3s
cost / run
$0.0526
tokens out
4.0k
tokens in
70k
▶ preview · view live runtime
70.7s
cost / run
$0.0462
tokens out
3.6k
tokens in
76k
▶ preview · view live runtime
51.8s
cost / run
$0.0372
tokens out
3.2k
tokens in
50k
▶ preview · view live runtime
85.2s
cost / run
$0.0730
tokens out
5.8k
tokens in
135k
▶ preview · view live runtime
52.6s
cost / run
$0.0462
tokens out
3.3k
tokens in
89k
▶ preview · view live runtime
59.4s
cost / run
$0.0654
tokens out
4.9k
tokens in
123k
▶ preview · view live runtime
76.9s
cost / run
$0.0398
tokens out
3.1k
tokens in
59k
▶ preview · view live runtime
55.2s
cost / run
$0.0402
tokens out
2.9k
tokens in
63k
▶ preview · view live runtime
46.2s
cost / run
$0.0447
tokens out
3.6k
tokens in
59k
▶ preview · view live runtime
56.8s
cost / run
$0.0503
tokens out
4.0k
tokens in
86k
▶ preview · view live runtime
86.1s
cost / run
$0.0657
tokens out
4.9k
tokens in
124k
▶ preview · view live runtime
91.1s
cost / run
$0.0872
tokens out
6.3k
tokens in
217k
▶ preview · view live runtime
43.7s
cost / run
$0.0394
tokens out
2.9k
tokens in
69k
▶ preview · view live runtime
81.3s
cost / run
$0.0647
tokens out
4.6k
tokens in
140k
▶ preview · view live runtime
70.1s
cost / run
$0.0562
tokens out
3.0k
tokens in
114k
▶ preview · view live runtime
41.3s
cost / run
$0.0403
tokens out
3.3k
tokens in
60k
▶ preview · view live runtime
27.2s
cost / run
$0.0228
tokens out
2.6k
tokens in
11k
▶ preview · view live runtime
110.5s
cost / run
$0.1202
tokens out
8.1k
tokens in
344k
▶ preview · view live runtime
47.2s
cost / run
$0.0445
tokens out
3.1k
tokens in
88k
▶ preview · view live runtime
64.3s
cost / run
$0.0484
tokens out
3.2k
tokens in
75k
▶ preview · view live runtime
127.1s
cost / run
$0.0507
tokens out
4.7k
tokens in
69k
▶ preview · view live runtime
88.0s
cost / run
$0.0719
tokens out
5.0k
tokens in
185k
▶ preview · view live runtime
47.5s
cost / run
$0.0397
tokens out
4.0k
tokens in
40k
▶ preview · view live runtime
65.4s
cost / run
$0.0475
tokens out
3.4k
tokens in
88k
Stopped by an API error ▶ preview · view live runtime
65.2s
cost / run
$0.0357
tokens out
3.4k
tokens in
39k
▶ preview · view live runtime
63.6s
cost / run
$0.0610
tokens out
5.0k
tokens in
113k
▶ preview · view live runtime
75.8s
cost / run
$0.0790
tokens out
5.6k
tokens in
200k
Stopped by an API error ▶ preview · view live runtime
58.4s
cost / run
$0.0335
tokens out
4.3k
tokens in
9.7k