Hermes 4 405B
nousresearch/hermes-4-405b
Compare with Hermes 4 70B, Hermes 3 405B Instruct, Hermes 3 70B Instruct
CompareHermes 4 405B
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Nebiusnebius/fp8fp8 | Healthy | 100% | 100% | 493ms | 7.47s | 27 tps | 131K | $1.00 / $3.00 |
- Nebius100%Healthy24h 100%
- p50
- 493ms
- p99
- 7.47s
- Throughput
- 27 tps
- Context
- 131K
- $/Mtok
- $1.00 / $3.00
nebius/fp8fp8
Measured 5m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. p50 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.