Novita
Hosted API- US East (Virginia)213 ms, view the regional leaderboard
- Asia Pacific (Tokyo)243 ms, view the regional leaderboard
- Models on live video
- 2
- Regions measured
- 2
- Real-time models
- 1 of 2
- Median output speed
- 195 tok/s
- Median E2E · US East
- 213 ms
- Median blended $/1M
- $0.15
Models on Novita
| # | Details | |||||||
|---|---|---|---|---|---|---|---|---|
| 1 | View gemma-4-26b-a4bGemma 4 26B A4B | 241 tok/s | 69 ms | 168 ms | $0.09 | <200 ms | ||
| 2 | View gemma-4-31bGemma 4 31B | 150 tok/s | 98 ms | 259 ms | $0.21 | – |
Real-time coverage
US East (Virginia)1 of 2 under 200 ms
Asia Pacific (Tokyo)1 of 2 under 200 ms
Latency columns use the US East (Virginia) reference region. Real-time marks a model that closes the loop under 200 ms end to end on Novita from at least one region.