Llama 4 Scout
meta-llama/llama-4-scoutInputOutput
Compare its 6 providersIncident RSSCompare with Llama 4 Maverick, Llama Guard 4 12B, Llama 3.3 70B Instruct
Showing only the deepinfra/fp8/priority provider · show all 6
CompareLlama 4 Scout
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Degraded | 100% | 96.32% | 96.83% | 96.83% | 600ms | 8.18s | 31 tps | 328K | $0.150 / $0.450 |
- DeepInfra100%Degraded24h 96.32%
- 7d
- 96.83%
- 30d
- 96.83%
- p50
- 600ms
- p99
- 8.18s
- Throughput
- 31 tps
- Context
- 328K
- $/Mtok
- $0.150 / $0.450
deepinfra/fp8/priorityfp8
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.
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 · 6 endpoints · 60 days with data, 30 endpoint-days below 90%. Tables and charts above are filtered to deepinfra/fp8/priority.