Skip to content
Dashboard

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
Web Search
Capabilities
ZDR
No Training
Regional Inference
Free Tier
Released
1M
$0.30/M
$1.20/M
1.7 s140 tps
Read$0.03/M
+1
09/08/2026
1M
$0.45/M
$1.50/M
1.1 s59 tps
Read$0.09/M
+1
08/26/2026
1M
$1.40/M
$4.40/M
0.4 s247 tps
Read$0.26/M
08/18/2026
262K
$2/M
$6/M
0.5 s
Read$0.25/M
08/03/2026
1M
$3/M
$15/M
3.6 s69 tps
Read$0.30/M
+2
07/16/2026
262K
$1.20/M
$5/M
0.4 s193 tps
Read$0.27/M
+1
07/15/2026