Llama 3.1 Euryale 70B v2.2
sao10k/l3.1-euryale-70b
Compare with Llama 3 8B Lunaris, Llama 3.3 Euryale 70B, GLM 5.2
CompareLlama 3.1 Euryale 70B v2.2
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
DeepInfradeepinfra/fp8fp8 | Healthy | 100% | 99.54% | 276ms | 2.03s | 52 tps | 131K | $0.850 / $0.850 |
Novitanovita/fp8fp8 | No data | — | 99.59% | 413ms | 869ms | 56 tps | 8K | $1.45 / $1.45 |
- DeepInfra100%Healthy24h 99.54%
- p50
- 276ms
- p99
- 2.03s
- Throughput
- 52 tps
- Context
- 131K
- $/Mtok
- $0.850 / $0.850
deepinfra/fp8fp8 - Novita—No data24h 99.59%
- p50
- 413ms
- p99
- 869ms
- Throughput
- 56 tps
- Context
- 8K
- $/Mtok
- $1.45 / $1.45
novita/fp8fp8
Measured 2m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint reporting no data is omitted from the charts.
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, averaged over the hour.
Throughput
Median tokens per second.