Hermes 4 70B
nousresearch/hermes-4-70b
Compare with Hermes 4 405B, Hermes 3 405B Instruct, Hermes 3 70B Instruct
CompareHermes 4 70B
| State | ||||||||
|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 100% | 234ms | 5.24s | 72 tps | 131K | $0.130 / $0.400 |
- Nebius100%Healthy24h 100%
- p50
- 234ms
- p99
- 5.24s
- Throughput
- 72 tps
- Context
- 131K
- $/Mtok
- $0.130 / $0.400
nebius/fp8fp8
Measured 2m 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 is OpenRouter's rolling 30-minute window.
Throughput
Median tokens per second.