← All models
gpt-oss-20b · OpenAI
35 runs · same model · across prompts
$0.09 total cost 568k input 1.9M cached 268k output 95.5s avg latency 31 outputs (89% of runs)
▶ preview · view live runtime
273.0s
cost / run
$0.0113
tokens out
21k
tokens in
369k
▶ preview · view live runtime
81.4s
cost / run
$0.0013
tokens out
6.5k
tokens in
12k
▶ preview · view live runtime
37.6s
cost / run
$0.0008
tokens out
3.5k
tokens in
12k
Stopped by an API error ▶ preview · view live runtime
80.4s
cost / run
$0.0022
tokens out
8.0k
tokens in
44k
▶ preview · view live runtime
88.5s
cost / run
$0.0048
tokens out
7.0k
tokens in
155k
▶ preview · view live runtime
89.4s
cost / run
$0.0016
tokens out
7.9k
tokens in
15k
▶ preview · view live runtime
156.9s
cost / run
$0.0041
tokens out
11k
tokens in
114k
▶ preview · view live runtime
87.2s
cost / run
$0.0029
tokens out
6.0k
tokens in
89k
▶ preview · view live runtime
44.0s
cost / run
$0.0008
tokens out
3.8k
tokens in
9.0k
▶ preview · view live runtime
186.3s
cost / run
$0.0046
tokens out
15k
tokens in
103k
▶ preview · view live runtime
98.9s
cost / run
$0.0018
tokens out
8.8k
tokens in
19k
▶ preview · view live runtime
56.1s
cost / run
$0.0015
tokens out
4.0k
tokens in
43k
▶ preview · view live runtime
43.3s
cost / run
$0.0009
tokens out
3.9k
tokens in
13k
▶ preview · view live runtime
55.9s
cost / run
$0.0013
tokens out
4.4k
tokens in
29k
Stopped by an API error ▶ preview · view live runtime
58.4s
cost / run
$0.0013
tokens out
5.4k
tokens in
32k
▶ preview · view live runtime
59.3s
cost / run
$0.0010
tokens out
5.3k
tokens in
8.3k
▶ preview · view live runtime
78.2s
cost / run
$0.0019
tokens out
6.4k
tokens in
38k
▶ preview · view live runtime
79.0s
cost / run
$0.0025
tokens out
6.6k
tokens in
68k
▶ preview · view live runtime
193.0s
cost / run
$0.0050
tokens out
15k
tokens in
124k
▶ preview · view live runtime
26.7s
cost / run
$0.0006
tokens out
2.2k
tokens in
8.4k
▶ preview · view live runtime
84.5s
cost / run
$0.0019
tokens out
6.9k
tokens in
40k
▶ preview · view live runtime
36.3s
cost / run
$0.0006
tokens out
2.9k
tokens in
5.5k
▶ preview · view live runtime
64.8s
cost / run
$0.0013
tokens out
5.6k
tokens in
17k
▶ preview · view live runtime
69.8s
cost / run
$0.0015
tokens out
5.5k
tokens in
28k
▶ preview · view live runtime
333.0s
cost / run
$0.0085
tokens out
26k
tokens in
206k
▶ preview · view live runtime
122.2s
cost / run
$0.0047
tokens out
8.3k
tokens in
159k
▶ preview · view live runtime
59.9s
cost / run
$0.0010
tokens out
4.4k
tokens in
17k
▶ preview · view live runtime
223.3s
cost / run
$0.0058
tokens out
17k
tokens in
140k
▶ preview · view live runtime
147.3s
cost / run
$0.0073
tokens out
14k
tokens in
247k
▶ preview · view live runtime
79.8s
cost / run
$0.0015
tokens out
6.6k
tokens in
23k
▶ preview · view live runtime
199.7s
cost / run
$0.0073
tokens out
14k
tokens in
251k
Arpeggiator pad
Provider finish_reason: error
See transcript →runtime
5.5s
cost / run
$0.0000
tokens out
380
tokens in
1.8k
Lorenz attractor
Provider finish_reason: error
See transcript →runtime
3.9s
cost / run
$0.0000
tokens out
216
tokens in
1.8k
Reaction-diffusion
Provider finish_reason: error
See transcript →runtime
31.1s
cost / run
$0.0007
tokens out
2.6k
tokens in
19k
Snake
Provider finish_reason: error
See transcript →runtime
7.5s
cost / run
$0.0000
tokens out
573
tokens in
1.7k