← All models
ministral-8b-2512 · Mistral AI
35 runs · same model · across prompts
$0.40 total cost 960k input 12.6M cached 431k output 225.2s avg latency 35 outputs (100% of runs)
Stopped by an API error ▶ preview · view live runtime
146.2s
cost / run
$0.0045
tokens out
4.5k
tokens in
108k
▶ preview · view live runtime
324.1s
cost / run
$0.0166
tokens out
15k
tokens in
618k
▶ preview · view live runtime
37.4s
cost / run
$0.0017
tokens out
3.5k
tokens in
28k
Stopped by an API error ▶ preview · view live runtime
230.3s
cost / run
$0.0107
tokens out
11k
tokens in
440k
Stopped by an API error ▶ preview · view live runtime
302.1s
cost / run
$0.0156
tokens out
16k
tokens in
675k
Stopped by an API error ▶ preview · view live runtime
254.9s
cost / run
$0.0146
tokens out
7.1k
tokens in
654k
▶ preview · view live runtime
37.3s
cost / run
$0.0017
tokens out
3.4k
tokens in
21k
▶ preview · view live runtime
222.6s
cost / run
$0.0134
tokens out
14k
tokens in
618k
▶ preview · view live runtime
165.2s
cost / run
$0.0114
tokens out
16k
tokens in
474k
▶ preview · view live runtime
233.2s
cost / run
$0.0144
tokens out
16k
tokens in
481k
▶ preview · view live runtime
195.8s
cost / run
$0.0101
tokens out
11k
tokens in
175k
▶ preview · view live runtime
41.7s
cost / run
$0.0020
tokens out
5.0k
tokens in
17k
Stopped by an API error ▶ preview · view live runtime
294.9s
cost / run
$0.0147
tokens out
12k
tokens in
458k
Stopped by an API error ▶ preview · view live runtime
152.1s
cost / run
$0.0041
tokens out
3.1k
tokens in
133k
▶ preview · view live runtime
93.8s
cost / run
$0.0047
tokens out
7.1k
tokens in
96k
Stopped by an API error ▶ preview · view live runtime
290.7s
cost / run
$0.0108
tokens out
12k
tokens in
445k
Stopped by an API error ▶ preview · view live runtime
282.5s
cost / run
$0.0151
tokens out
11k
tokens in
430k
▶ preview · view live runtime
644.0s
cost / run
$0.0148
tokens out
32k
tokens in
431k
Stopped by an API error ▶ preview · view live runtime
295.0s
cost / run
$0.0170
tokens out
13k
tokens in
711k
▶ preview · view live runtime
32.2s
cost / run
$0.0011
tokens out
2.6k
tokens in
12k
Stopped by an API error ▶ preview · view live runtime
426.2s
cost / run
$0.0210
tokens out
21k
tokens in
637k
▶ preview · view live runtime
48.1s
cost / run
$0.0013
tokens out
2.2k
tokens in
11k
▶ preview · view live runtime
269.4s
cost / run
$0.0121
tokens out
23k
tokens in
453k
▶ preview · view live runtime
80.0s
cost / run
$0.0039
tokens out
5.8k
tokens in
125k
▶ preview · view live runtime
36.4s
cost / run
$0.0011
tokens out
2.6k
tokens in
15k
▶ preview · view live runtime
406.4s
cost / run
$0.0352
tokens out
20k
tokens in
1282k
▶ preview · view live runtime
25.8s
cost / run
$0.0009
tokens out
1.8k
tokens in
14k
▶ preview · view live runtime
672.1s
cost / run
$0.0261
tokens out
47k
tokens in
662k
▶ preview · view live runtime
123.5s
cost / run
$0.0062
tokens out
7.0k
tokens in
204k
▶ preview · view live runtime
51.4s
cost / run
$0.0033
tokens out
4.3k
tokens in
27k
▶ preview · view live runtime
129.5s
cost / run
$0.0078
tokens out
7.2k
tokens in
218k
▶ preview · view live runtime
172.5s
cost / run
$0.0050
tokens out
9.1k
tokens in
162k
Stopped by an API error ▶ preview · view live runtime
331.2s
cost / run
$0.0196
tokens out
20k
tokens in
939k
Stopped by an API error ▶ preview · view live runtime
220.6s
cost / run
$0.0084
tokens out
8.4k
tokens in
343k
▶ preview · view live runtime
613.1s
cost / run
$0.0464
tokens out
38k
tokens in
1403k