Skip to content
Dashboard

Moonshot AI models

Route requests to Moonshot AI through Vercel AI Gateway. Compare the models Moonshot AI 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
$2/M
$10/M
5.6 s65 tps
Read$0.20/M
Write$2/M
—
+2
10/23/2026
1M
$4/M
$20/M
3.5 s135 tps
Read$0.20/M
Write$4/M
—
+2
10/23/2026
1M
$3/M
$15/M
2.2 s48 tps
Read$0.30/M
Write$3/M
—
+3
07/16/2026
262K
$1.90/M
$8/M
——
Read$0.38/M
—
+3
06/15/2026
256K
$0.95/M+1 more
$4/M+1 more
2.0 s73 tps
Read$0.19/M
—
+3
06/12/2026
262K
$0.95/M
$4/M
1.7 s84 tps
Read$0.16/M
—
+1
04/20/2026