Models
Available Models
12 enabled for organization members
14 Total
14
Free Tier Models
Zero token deduction for inference
4
Lowest Latency
Beam & Beam-free fast edge inference
0.1 s
Zero Data Retention
Enterprise privacy compliant (ZDR)
7 Models
Model Directory
Search model pricing per 1M tokens, latency benchmarks, routing providers, and zero-retention compliance
14 models found
Free tier only
| Model | Input | Output | Latency | Providers | ZDR | No Training | Gateway Credit | Capabilities | Released | Active |
|---|---|---|---|---|---|---|---|---|---|---|
D deepseek/deep_ash-101751% off | $0.08/M+1 more | $0.29/M+1 more | 0.2 s | DTG +7 | T+2 | 10/17/2026 | ||||
D deepseek/deepseek-v4_017-fastFast | $0.60/M | $2.40/M | 0.4 s | D | T+2 | 10/17/2026 | ||||
R reflection/beamFree | Free | Free | 0.1 s | RO +1 | T | 10/16/2026 | ||||
R reflection/beam-freeFree | Free | Free | 0.1 s | R | T+1 | 10/16/2026 | ||||
P perplexity/pplx-decider-v1.2 | $0.02/M | — | — | P | 10/16/2026 | |||||
E elorian/glimpse | $0.60/M | $3/M | — | E | T | 10/16/2026 | ||||
P perplexity/pplx-decider-flash-v1.2 | $0.01/M | — | — | P | 10/16/2026 | |||||
S stealth/cat-jamFree | Free | Free | 0.4 s | S | T+1 | 10/15/2026 | ||||
T typesafe-ai/jev-1.14.0 | $0.04/M | — | — | T | 10/15/2026 | |||||
M meta/muse-spark-open | $1.25/M | $4.25/M | 0.2 s | MT +2 | T+2 | 10/15/2026 | ||||
N nvidia/nemotron-3.5-super-vl | $0.10/M | $0.40/M | 0.2 s | NG +1 | T+2 | 10/15/2026 | ||||
L liquid/d1-ultra | $0.04/M | — | — | L | 10/15/2026 | |||||
B bfl/flux-3-image-klein | — | $0.009/img+4 more | — | B | 10/15/2026 | |||||
N nvidia/nemotron-3-ing-freeFree | Free | Free | 0.4 s | N | T+1 | 10/14/2026 |
Showing 14 of 14 models across 10 providers
Gateway Auto-Failover: Healthy