Llama 3 8B Lunaris
sao10k/l3-lunaris-8bInputOutput
Compare its 3 providersIncident RSSCompare with Llama 3.1 Euryale 70B v2.2, Llama 3.3 Euryale 70B, GLM 5.3
CompareLlama 3 8B Lunaris
- DeepInfra100%Healthy24h 99.94%
- 7d
- 99.96%
- 30d
- 99.93%
- p50
- 137ms
- p99
- 1.29s
- Throughput
- 86 tps
- Context
- 8K
- $/Mtok
- $0.040 / $0.050
deepinfra/turbofp8 - Novita100%Healthy24h 99.98%
- 7d
- 99.98%
- 30d
- 99.91%
- p50
- 299ms
- p99
- 1.35s
- Throughput
- 80 tps
- Context
- 8K
- $/Mtok
- $0.050 / $0.050
novita/bf16bf16 - Parasail100%Healthy24h 99.89%
- 7d
- 99.83%
- 30d
- 99.91%
- p50
- 523ms
- p99
- 2.08s
- Throughput
- 45 tps
- Context
- 8K
- $/Mtok
- $0.040 / $0.050
parasail/bf16bf16
Measured 1m 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 · 3 endpoints · 47 days with data, 3 endpoint-days below 90%.