← All models
gemma-4-26b-a4b-it · Google
35 runs · same model · across prompts
$0.23 total cost 1.1M input 309k cached 593k output 251.1s avg latency 35 outputs (100% of runs)
Timed out ▶ preview · view live runtime
900.0s
cost / run
$0.0141
tokens out
37k
tokens in
75k
▶ preview · view live runtime
170.2s
cost / run
$0.0051
tokens out
10k
tokens in
63k
▶ preview · view live runtime
45.4s
cost / run
$0.0012
tokens out
3.2k
tokens in
11k
▶ preview · view live runtime
691.7s
cost / run
$0.0403
tokens out
56k
tokens in
342k
Stopped by an API error ▶ preview · view live runtime
39.6s
cost / run
$0.0010
tokens out
3.6k
tokens in
4.3k
▶ preview · view live runtime
54.8s
cost / run
$0.0020
tokens out
5.5k
tokens in
9.0k
Stopped by an API error ▶ preview · view live runtime
33.1s
cost / run
$0.0007
tokens out
2.7k
tokens in
1.9k
▶ preview · view live runtime
271.0s
cost / run
$0.0062
tokens out
22k
tokens in
22k
▶ preview · view live runtime
55.7s
cost / run
$0.0017
tokens out
5.3k
tokens in
13k
▶ preview · view live runtime
59.7s
cost / run
$0.0017
tokens out
5.9k
tokens in
9.5k
▶ preview · view live runtime
501.1s
cost / run
$0.0218
tokens out
43k
tokens in
219k
Hit the output limit ▶ preview · view live runtime
552.0s
cost / run
$0.0113
tokens out
46k
tokens in
29k
▶ preview · view live runtime
532.2s
cost / run
$0.0158
tokens out
33k
tokens in
104k
▶ preview · view live runtime
62.3s
cost / run
$0.0014
tokens out
4.8k
tokens in
7.5k
▶ preview · view live runtime
43.0s
cost / run
$0.0018
tokens out
3.8k
tokens in
14k
▶ preview · view live runtime
744.6s
cost / run
$0.0122
tokens out
29k
tokens in
76k
▶ preview · view live runtime
74.5s
cost / run
$0.0020
tokens out
6.4k
tokens in
15k
▶ preview · view live runtime
229.3s
cost / run
$0.0080
tokens out
22k
tokens in
40k
▶ preview · view live runtime
42.1s
cost / run
$0.0012
tokens out
3.4k
tokens in
11k
Hit the output limit ▶ preview · view live runtime
481.4s
cost / run
$0.0139
tokens out
36k
tokens in
60k
▶ preview · view live runtime
272.5s
cost / run
$0.0045
tokens out
15k
tokens in
25k
▶ preview · view live runtime
78.8s
cost / run
$0.0018
tokens out
6.5k
tokens in
7.6k
▶ preview · view live runtime
877.5s
cost / run
$0.0213
tokens out
59k
tokens in
89k
Hit the output limit ▶ preview · view live runtime
362.2s
cost / run
$0.0082
tokens out
36k
tokens in
8.1k
▶ preview · view live runtime
114.8s
cost / run
$0.0027
tokens out
8.4k
tokens in
21k
▶ preview · view live runtime
68.0s
cost / run
$0.0024
tokens out
7.0k
tokens in
11k
▶ preview · view live runtime
75.6s
cost / run
$0.0011
tokens out
2.8k
tokens in
11k
▶ preview · view live runtime
60.8s
cost / run
$0.0019
tokens out
6.1k
tokens in
13k
▶ preview · view live runtime
146.1s
cost / run
$0.0027
tokens out
10k
tokens in
12k
▶ preview · view live runtime
442.4s
cost / run
$0.0098
tokens out
33k
tokens in
67k
▶ preview · view live runtime
95.5s
cost / run
$0.0031
tokens out
9.2k
tokens in
13k
Stopped by an API error ▶ preview · view live runtime
372.1s
cost / run
$0.0014
tokens out
5.9k
tokens in
2.0k
Stopped by an API error ▶ preview · view live runtime
105.9s
cost / run
$0.0009
tokens out
3.2k
tokens in
4.3k
▶ preview · view live runtime
53.1s
cost / run
$0.0019
tokens out
5.2k
tokens in
9.1k
▶ preview · view live runtime
80.9s
cost / run
$0.0029
tokens out
8.1k
tokens in
12k