Replicate
Replicate.com is a mature platform for deploying and sharing AI models.

Replicate Serverless GPU Prices

CPU
084
0.0001/s
0.36/h
0
1684
0.000225/s
0.81/h
0
48164
0.000575/s
2.07/h
-12%
487210
0.000725/s
2.61/h
+12%
407210
0.00115/s
4.14/h
-10%
8014410
0.0014/s
5.04/h
+10%
38468048
0.0058/s
20.88/h

Recent benchmarks

hello_gpu by replicate on t4
Median16.2s
Average30.44s
Failures0
13.43s 12:01:47 AM
12.94s 12:02:15 AM
17.07s 12:02:08 AM
12.94s 12:01:52 AM
9.74s 12:02:19 AM
10.42s 12:01:38 AM
20.37s 12:02:22 AM
17.05s 12:02:08 AM
23.26s 12:02:26 AM
23.01s 12:02:21 AM
13.69s 12:02:28 AM
15.36s 12:02:03 AM
14.84s 12:02:19 AM
12.44s 12:01:26 AM
12.21s 12:02:04 AM
11.82s 12:01:37 AM
28.88s 12:02:11 AM
37.42s 12:01:26 AM
17.31s 12:01:48 AM
65.29s 12:02:27 AM
11.35s 12:01:52 AM
12.35s 12:01:57 AM
24.01s 12:02:37 AM
142.7s 7:49:42 PM
13.18s 12:02:05 AM
20.57s 12:02:10 AM
13.46s 12:03:53 AM
114.63s 12:04:37 AM
91.68s 7:48:54 PM
20.85s 12:02:48 AM
13.22s 12:01:27 AM
106.6s 7:48:52 PM
hello_torch by replicate on t4
Median88.54s
Average100.29s
Failures0
95.22s 12:01:47 AM
90.06s 12:02:15 AM
89.19s 12:02:08 AM
78.86s 12:01:52 AM
86.57s 12:02:19 AM
81.03s 12:01:38 AM
115.47s 12:02:22 AM
105.1s 12:02:08 AM
91.28s 12:02:26 AM
120.27s 12:02:21 AM
92.77s 12:02:28 AM
80.3s 12:02:03 AM
77.46s 12:02:19 AM
82.68s 12:01:26 AM
77s 12:02:04 AM
76.41s 12:01:37 AM
76.01s 12:02:11 AM
80.6s 12:01:26 AM
77.8s 12:01:48 AM
87.9s 12:02:27 AM
85.39s 12:01:52 AM
82.3s 12:01:57 AM
95.89s 12:02:37 AM
118.41s 7:49:42 PM
89.87s 12:02:05 AM
95.66s 12:02:10 AM
227.53s 12:03:53 AM
246.83s 12:04:37 AM
76.33s 7:48:54 PM
154.69s 12:02:48 AM
78.88s 12:01:27 AM
95.61s 7:48:52 PM

About Replicate

There are large amounts of models made by the community as a showcase and for demonstration on the platform. You can publish your own model on Replicate for free, but you pay per second used by server.

With public models you only pay for the time the server is running, and with private models you also pay for the start up time.

You develop functions using the COG SDK, which makes it quite easy to containerize and deploy your AI models.

Replicate has stable support for webhooks, logging, and offer some observability.

The start up time for functions on Replicate is quite long (as of March 2024), so if fast responses are needed, it's better to use another vendor or configure Replicate to always keep a replica online.