Skip to content
Dashboard

NVIDIA models

Browse and compare every NVIDIA model available on Vercel AI Gateway. Compare pricing, context windows, and capabilities, then call any of them through a single API.
Model
Context
Input
Output
Latency
Throughput
Cache
Search
Capabilities
Providers
ZDR
No Training
Regional Inference
Free AI Gateway Credit
Released
1M
$0.10/M
$0.50/M
0.2 s487 tps
Read$0.02/M
—
+2
baseten logo
deepinfra logo
gmicloud logo
+1
US
10/15/2026
1M
Free
Free
0.4 s309 tps——
+1
nvidia logo
10/14/2026
262K
$0.05/M
$0.15/M
0.1 s415 tps
Read$0.01/M
—
+1
deepinfra logo
fireworks logo
runinfra logo
08/11/2026
1M
$0.50/M
$2.20/M
0.3 s163 tps
Read$0.10/M
—
+1
baseten logo
deepinfra logo
fireworks logo
US
06/04/2026
256K
$0.15/M
$0.65/M
0.3 s157 tps——
bedrock logo
03/11/2026
262K
$0.05/M
$0.20/M
0.2 s158 tps
Read$0.03/M
—
deepinfra logo
12/15/2025
131K
$0.20/M
$0.60/M
0.2 s———
bedrock logo
10/28/2025
131K
$0.06/M
$0.23/M
0.2 s142 tps——
bedrock logo
08/18/2025