inference
Together
San Francisco · us-east, us-west, europe · Open-weight hosting. H100/H200 fleet.
Reported availability
99.72%
Shown separately from GBU samples
Live endpoints
3
Regions covered
3
| Model | API id | TTFT | tok/s | EWR | $/correct | GBU avail | Evidence |
|---|---|---|---|---|---|---|---|
| Llama 4 405B Together | meta-llama/Llama-4-405B-Instruct | 280 ms | 110 | 2.97 | $0.032 | 99.72% | LIVE_MEASURED |
| Llama 4 70B Together | meta-llama/Llama-4-70B-Instruct | 140 ms | 195 | 32.3 | $0.0064 | 99.75% | LIVE_MEASURED |
| Qwen3-Max Together | Qwen/Qwen3-Max | 260 ms | 92 | 2.56 | $0.036 | 99.70% | LIVE_MEASURED |