Llama 3 8B Lunaris: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100%◆ (best) | 99.96% | 99.60% | 99.60% | 152ms◆ (best) | 1.09s◆ (best) | 79 tps◆ (best) | 8K | $0.040 / $0.050◆ (best) | |
| Healthy | 100%◆ (best) | 99.99% | 99.47% | 99.47% | 316ms | 1.33s | 74 tps | 8K | $0.050 / $0.050 | |
| Healthy | 99.45% | 99.96% | 99.75%◆ (best) | 99.75%◆ (best) | 877ms | 2.03s | 16 tps | 8K | $0.040 / $0.050◆ (best) |
- DeepInfra100%◆ (best)Healthy24h 99.96%
- 7d
- 99.60%
- 30d
- 99.60%
- p50
- 152ms◆ (best)
- p99
- 1.09s◆ (best)
- Throughput
- 79 tps◆ (best)
- Context
- 8K
- $/Mtok
- $0.040 / $0.050◆ (best)
deepinfra/turbofp8 - Novita100%◆ (best)Healthy24h 99.99%
- 7d
- 99.47%
- 30d
- 99.47%
- p50
- 316ms
- p99
- 1.33s
- Throughput
- 74 tps
- Context
- 8K
- $/Mtok
- $0.050 / $0.050
novita/bf16bf16 - Parasail99.45%Healthy24h 99.96%
- 7d
- 99.75%◆ (best)
- 30d
- 99.75%◆ (best)
- p50
- 877ms
- p99
- 2.03s
- Throughput
- 16 tps
- Context
- 8K
- $/Mtok
- $0.040 / $0.050◆ (best)
parasail/bf16bf16
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
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.