Skip to content
Dashboard
Vercel Live

Nov 12: Intro to AI Gateway

Modal models

Route requests to Modal through Vercel AI Gateway. Compare the models Modal serves, with unified billing and automatic failover across providers.
Model
Context
Input
Output
Latency
Throughput
Cache
Search
Capabilities
ZDR
No Training
Regional Inference
Free AI Gateway Credit
Released
1M
$1.25/M
$4.25/M
0.5 s347 tps
Read$0.15/M
—
+2
—10/15/2026
1M
$0.30/M
$1.20/M
1.2 s123 tps
Read$0.03/M
—
+2
—09/08/2026
1M
$0.45/M
$1.50/M
0.4 s57 tps
Read$0.09/M
—
+2
—08/26/2026
1M
$1.40/M
$4.40/M
0.4 s26 tps
Read$0.26/M
—
+1
—08/18/2026
262K
$2/M
$6/M
0.3 s—
Read$0.25/M
—
+1
—08/03/2026
1M
$3/M
$15/M
0.7 s206 tps
Read$0.30/M
—
+3
—07/16/2026
262K
$1.20/M
$5/M
0.4 s195 tps
Read$0.27/M
—
+2
—07/15/2026