Llama 3.1 8B Instruct
meta-llama/llama-3.1-8b-instruct
Compare with Llama 3.1 70B Instruct, Llama 3.2 3B Instruct, Llama 3.2 1B Instruct
Compare its 5 providers · Incident RSS
Showing only the cloudflare/fp8 provider · show all 5
CompareLlama 3.1 8B Instruct
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.79% | 99.88% | 99.88% | 517ms | 3.74s | 15 tps | 32K | $0.152 / $0.287 |
- Cloudflare100%Healthy24h 99.79%
- 7d
- 99.88%
- 30d
- 99.88%
- p50
- 517ms
- p99
- 3.74s
- Throughput
- 15 tps
- Context
- 32K
- $/Mtok
- $0.152 / $0.287
cloudflare/fp8fp8
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, averaged over the hour.
Throughput
Median tokens per second.
Daily availability
One row per endpoint · one cell per week · up to a year.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC week · 5 endpoints · 24 weeks with data, 1 endpoint-week below 90%.