Skip to content
Dashboard

RunInfra models

Route requests to RunInfra through Vercel AI Gateway. Compare the models RunInfra 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
$0.10/M
$0.40/M
0.9 s50 tps
Read$0.01/M
+1
08/26/2026
1M
$0.12/M
$0.40/M
Read$0.01/M
+1
08/26/2026
262K
$0.10/M
$0.40/M
2.9 s58 tps
Read$0.01/M
+1
08/14/2026
1M
$0.60/M
$1.90/M
Read$0.03/M
08/12/2026
262K
$0.05/M
$0.15/M
0.4 s
Read$0.05/M
08/11/2026
262K
$2/M
$6/M
Read$0.20/M
08/03/2026
1M
$0.13/M
$0.27/M
0.7 s22 tps
Read$0.01/M
07/31/2026
33K
$0.01/M
11/14/2025
33K
$0.05/M
06/05/2025