Skip to content
Dashboard

Relace models

Relace is a hosted inference provider for open-weight AI models, delivering cost-efficient access optimized for coding, reasoning, and agentic workloads.
Model
Context
Input
Output
Latency
Throughput
Cache
Search
Capabilities
ZDR
No Training
Regional Inference
Free AI Gateway Credit
Released
1M
$0.04/M
$1.28/M
——
Read$0.04/M
—
+1
09/21/2026
1M
$0.02/M
$1.20/M
1.4 s116 tps
Read$0.02/M
—
+1
09/08/2026
1M
$0.03/M
$0.50/M
0.9 s53 tps
Read$0.03/M
—
+1
08/26/2026
1M
$0.03/M
$12/M
0.5 s165 tps
Read$0.03/M
—
08/18/2026
1M
$0.02/M
$1.28/M
1.8 s30 tps
Read$0.02/M
—
+1
07/31/2026
1M
$0.82/M
$13/M
0.6 s107 tps
Read$0.45/M
—
+2
07/16/2026