Skip to content
Dashboard
Vercel Live

Nov 12: Intro to AI Gateway

Boundless models

Boundless is an AI inference platform and engineering partner helping startups run open-weight models in production. Its engineers select models for each workload, tune serving infrastructure to real traffic, and manage ongoing operations to improve throughput and reduce costs. Teams get inference tailored to their product, with hands-on support as usage grows and better models emerge.
Model
Context
Input
Output
Latency
Throughput
Cache
Search
Capabilities
ZDR
No Training
Regional Inference
Free AI Gateway Credit
Released
1M
$1.70/M
$8.50/M
0.4 s79 tps
Read$0.20/M
—
+2
—10/23/2026
1M
$0.24/M
$0.96/M
0.8 s97 tps
Read$0.0048/M
—
+2
—10/17/2026
8K
$0.01/M
—
————
—10/01/2026
1M
$0.14/M
$0.28/M
0.8 s35 tps
Read$0.0028/M
—
+2
—09/21/2026
1M
$0.44/M
$0.87/M
0.7 s62 tps
Read$0.0036/M
—
+2
—09/21/2026
1M
$0.20/M
$1/M
0.4 s106 tps
Read$0.01/M
—
+2
—09/08/2026
1M
$0.12/M
$0.40/M
1.1 s34 tps
Read$0.02/M
—
+2
—08/26/2026
1M
$1.12/M
$3.52/M
0.5 s183 tps
Read$0.14/M
—
—08/18/2026
1M
$0.04/M
$0.21/M
0.7 s43 tps
Read$0.02/M
—
+1
—07/31/2026
1M
$2.30/M
$11.40/M
0.5 s179 tps
Read$0.23/M
—
+2
—07/16/2026