Together
Hosted API- US East (Virginia)150 ms, view the regional leaderboard
- US West (Oregon)164 ms, view the regional leaderboard
- EU West (Ireland)171 ms, view the regional leaderboard
- Models on live video
- 3
- Regions measured
- 3
- Real-time models
- 2 of 3
- Median output speed
- 261 tok/s
- Median E2E · US East
- 150 ms
- Median blended $/1M
- $0.12
Models on Together
| # | Details | |||||||
|---|---|---|---|---|---|---|---|---|
| 1 | View holo3-35b-a3bHolo3 35B A3B | H Company | 262 tok/s | 58 ms | 150 ms | $0.12 | <200 ms | |
| 2 | View gemma-4-26b-a4bGemma 4 26B A4B | 261 tok/s | 58 ms | 150 ms | $0.12 | <200 ms | ||
| 3 | View gemma-4-31bGemma 4 31B | 173 tok/s | 91 ms | 230 ms | $0.27 | – |
Real-time coverage
US East (Virginia)2 of 3 under 200 ms
US West (Oregon)2 of 3 under 200 ms
EU West (Ireland)2 of 3 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 Together from at least one region.