Llama 3 8B Lunaris
sao10k/l3-lunaris-8b
Compare with Llama 3.1 Euryale 70B v2.2, Llama 3.3 Euryale 70B, GLM 5.2
CompareLlama 3 8B Lunaris
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
DeepInfradeepinfra/turbofp8 | Healthy | 100% | 98.89% | 139ms | 1.09s | 75 tps | 8K | $0.040 / $0.050 |
Novitanovita/bf16bf16 | Healthy | 100% | 98.95% | 327ms | 921ms | 71 tps | 8K | $0.050 / $0.050 |
Parasailparasail/bf16bf16 | Healthy | 100% | 99.62% | 466ms | 1.28s | 67 tps | 8K | $0.040 / $0.050 |
- DeepInfra100%Healthy24h 98.89%
- p50
- 139ms
- p99
- 1.09s
- Throughput
- 75 tps
- Context
- 8K
- $/Mtok
- $0.040 / $0.050
deepinfra/turbofp8 - Novita100%Healthy24h 98.95%
- p50
- 327ms
- p99
- 921ms
- Throughput
- 71 tps
- Context
- 8K
- $/Mtok
- $0.050 / $0.050
novita/bf16bf16 - Parasail100%Healthy24h 99.62%
- p50
- 466ms
- p99
- 1.28s
- Throughput
- 67 tps
- Context
- 8K
- $/Mtok
- $0.040 / $0.050
parasail/bf16bf16
Measured 4m 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.