Skip to content

Modal models

Get startedRead the docs
Route requests to Modal through Vercel AI Gateway. Compare the models Modal serves, with unified billing and automatic failover across providers.
Model
Context
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
Providers
ZDR
No Training
Regional Inference
Free Tier
Released
moonshotai/kimi-k3
1M
1.1s
201tps
$2.90/MFast $4.50/M
$14/MFast $22.50/M
Read:$0.29/M
Write:—
—
+2
baseten logo
digitalocean logo
fireworks logo
+5
US
07/16/2026