Hermes 3 70B Instruct
nousresearch/hermes-3-llama-3.1-70bInputOutput
Incident RSSCompare with Hermes 3 405B Instruct, Hermes 4 405B, GLM 5.3
Showing only the deepinfra/fp8 provider · show all 1
CompareHermes 3 70B Instruct
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.99% | 99.99% | 100% | 689ms | 15.0s | 27 tps | 131K | $0.700 / $0.700 |
- DeepInfra100%Healthy24h 99.99%
- 7d
- 99.99%
- 30d
- 100%
- p50
- 689ms
- p99
- 15.0s
- Throughput
- 27 tps
- Context
- 131K
- $/Mtok
- $0.700 / $0.700
deepinfra/fp8fp8
Measured 3m 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, averaged over the hour.
Throughput
Median tokens per second.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 1 endpoint · 48 days with data, none below the red threshold. Tables and charts above are filtered to deepinfra/fp8.