Skip to content
Dashboard

Novita AI models

Route requests to Novita AI through Vercel AI Gateway. Compare the models Novita AI 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
256K
Free
Free
1.0 s209 tps——
09/04/2026
256K
Free
Free
1.0 s209 tps——
09/04/2026
1M
$0.91/M
$2.86/M
1.7 s229 tps
Read$0.17/M
—
+1
08/18/2026
256K
$0.02/M
$0.06/M
0.9 s361 tps
Read$0.0042/M
—
08/06/2026
1M
$0.14/M
$0.28/M
3.5 s49 tps
Read$0.0028/M
—
+2
09/21/2026
1M
$0.44/M
$0.87/M
2.2 s33 tps
Read$0.0036/M
—
+2
09/21/2026
1M
$0.30/M
$1.20/M
3.6 s143 tps
Read$0.006/M
—
+1
09/08/2026
256K
$0.08/M
$0.22/M
1.3 s272 tps
Read$0.02/M
—
09/08/2026
256K
$0.06/M
$0.18/M
1.1 s357 tps
Read$0.01/M
—
08/27/2026
1M
$0.15/M
$0.50/M
1.3 s79 tps
Read$0.03/M
—
+2
08/26/2026
1M
$0.44/M
$1.32/M
1.0 s225 tps
Read$0.03/M
—
+1
08/21/2026
1M
$0.42/M
$3/M
1.4 s53 tps
Read$0.09/M
—
+1
08/14/2026
1M
$1.32/M
$3.96/M
1.4 s83 tps
Read$0.04/M
—
+1
08/12/2026
262K
$2/M
$6/M
2.0 s62 tps
Read$0.25/M
—
08/03/2026
1M
$0.44/M
$1.32/M
2.5 s147 tps
Read$0.03/M
—
+1
07/31/2026
262K
$0.14/M
$0.58/M
1.6 s153 tps
Read$0.04/M
—
07/06/2026
1M
$0.68/M
$2.15/M
1.6 s126 tps
Read$0.13/M
—
+1
06/16/2026
1M
$1.60/M
$3.20/M
1.4 s67 tps
Read$0.14/M
—
+1
04/23/2026
1M
$0.44/M
$1.32/M
2.6 s149 tps
Read$0.03/M
—
04/23/2026
262K
$0.80/M
$3.40/M
1.4 s51 tps
Read$0.16/M
—
+2
04/20/2026
205K
$1.38/M
$4.40/M
2.0 s101 tps
Read$0.26/M
—
+1
04/07/2026
262K
$0.13/M
$0.40/M
2.7 s16 tps——
+2
04/02/2026
262K
$0.14/M
$0.40/M
2.3 s21 tps——
+2
04/02/2026
205K
$0.30/M
$1.20/M
1.1 s68 tps
Read$0.06/M
—
03/18/2026
203K
$1/M
$3.20/M
1.4 s125 tps
Read$0.20/M
—
+1
02/12/2026
205K
$0.60/M
$2.40/M
——
Read$0.03/M
—
02/12/2026
262K
$0.60/M
$3/M
2.2 s55 tps
Read$0.10/M
—
+1
01/26/2026
205K
$0.30/M
$1.20/M
1.4 s101 tps
Read$0.03/M
—
12/23/2025
205K
$0.60/M
$2.20/M
4.3 s51 tps
Read$0.11/M
—
+1
12/22/2025
164K
$0.27/M
$0.40/M
1.6 s44 tps
Read$0.13/M
—
12/01/2025