Skip to content

RunInfra models

Get API keyRead the docs
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
alibaba/qwen3.8-27b
262K
$0.10/M
$0.40/M
1.3 s124 tps
Read$0.01/M
—
+2
08/14/2026
nvidia/nemotron-3.5-lightning
262K
$0.05/M
$0.15/M
0.3 s426 tps
Read$0.01/M
—
+1
08/11/2026