Skip to content
Dashboard

DeepInfra models

Route requests to DeepInfra through Vercel AI Gateway. Compare the models DeepInfra serves, with unified billing and automatic failover across providers.
Model
Context
Input
Output
Latency
Throughput
Cache
Search
Capabilities
ZDR
No Training
Regional Inference
Free AI Gateway Credit
Released
1M
$0.14/M
$0.42/M
1.1 s83 tps
Read$0.0042/M
—
+2
09/08/2026
1M
$0.08/M
$0.25/M
4.3 s9 tps
Read$0.02/M
—
+2
08/26/2026
1M
$0.22/M
$0.65/M
2.3 s131 tps
Read$0.0069/M
—
+2
08/21/2026
1M
$0.56/M
$2.50/M
1.2 s67 tps
Read$0.13/M
—
+1
08/18/2026
262K
$0.15/M
$1.88/M
0.3 s57 tps
Read$0.04/M
—
+2
08/14/2026
1M
$0.43/M
$0.87/M
1.8 s25 tps
Read$0.0036/M
—
+2
09/21/2026
1M
$0.14/M
$0.28/M
3.5 s16 tps
Read$0.0028/M
—
+2
09/21/2026
262K
$0.06/M
$0.18/M
1.6 s34 tps
Read$0.01/M
—
+1
08/27/2026
1M
$1.30/M
$2.60/M
1.2 s61 tps
Read$0.10/M
—
+1
08/12/2026
262K
$0.06/M
$0.16/M
0.3 s—
Read$0.03/M
—
+1
08/11/2026
256K
$2/M
$6/M
0.5 s143 tps
Read$0.20/M
—
+1
08/03/2026
1M
$0.06/M
$0.18/M
1.4 s44 tps
Read$0.02/M
—
+1
07/31/2026
1M
$0.45/M
$1.20/M
0.4 s273 tps
Read$0.10/M
—
+3
07/30/2026
1M
$2.85/M
$14.25/M
0.5 s88 tps
Read$0.29/M
—
+3
07/16/2026
524K
$0.95/M
$4.05/M
0.6 s125 tps
Read$0.16/M
—
+2
07/15/2026
262K
$0.13/M
$0.53/M
0.6 s81 tps
Read$0.03/M
—
+1
07/06/2026
1M
$0.56/M
$1.80/M
1.3 s78 tps
Read$0.11/M
—
+1
06/16/2026
262K
$0.50/M
$2.20/M
0.7 s79 tps
Read$0.10/M
—
+1
06/04/2026
66K
$1.30/M
$2.60/M
1.3 s47 tps
Read$0.10/M
—
+1
04/23/2026
1M
$0.06/M
$0.18/M
2.3 s52 tps
Read$0.02/M
—
04/23/2026
203K
$0.40/M
$1.75/M
1.0 s15 tps
Read$0.08/M
—
+1
12/22/2025
262K
$0.05/M
$0.20/M
0.3 s103 tps
Read$0.03/M
—
12/15/2025
164K
$0.26/M
$0.38/M
2.7 s4 tps
Read$0.13/M
—
12/01/2025
164K
$0.26/M
$0.38/M
2.4 s4 tps
Read$0.13/M
—
+1
12/01/2025
33K
$0.01/M
—
————
11/14/2025
203K
$0.50/M
$2/M
0.6 s20 tps
Read$0.10/M
—
+1
09/30/2025
262K
$0.20/M
$0.88/M
0.8 s13 tps
Read$0.11/M
—
09/23/2025
262K
$0.20/M
$0.88/M
——
Read$0.11/M
—
09/23/2025
262K
$0.09/M
$1.10/M
0.5 s55 tps——
09/11/2025
164K
$0.25/M
$0.95/M
0.8 s9 tps
Read$0.13/M
—
+1
08/21/2025