Llama 3.1 70B Instruct
meta-llama/llama-3.1-70b-instructInputOutput
Compare its 3 providersIncident RSSCompare with Llama 3.1 8B Instruct, Llama 3.2 3B Instruct, Llama 3.2 1B Instruct
Showing only the deepinfra/turbo provider · show all 3
CompareLlama 3.1 70B Instruct
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Degraded | 94.14% | 99.32% | 97.25% | 95.21% | 385ms | 62.6s | 38 tps | 131K | $0.400 / $0.400 |
- DeepInfra94.14%Degraded24h 99.32%
- 7d
- 97.25%
- 30d
- 95.21%
- p50
- 385ms
- p99
- 62.6s
- Throughput
- 38 tps
- Context
- 131K
- $/Mtok
- $0.400 / $0.400
deepinfra/turbofp8
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 · 50 days with data, 43 endpoint-days below 90%. Tables and charts above are filtered to deepinfra/turbo.