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
CompareLlama 3.1 70B Instruct
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Amazon Bedrockamazon-bedrock | Healthy | 100% | 100% | 99.97% | 99.40% | 372ms | 2.01s | 72 tps | 131K | $0.720 / $0.720 |
| Healthy | 100% | 99.48% | 96.98% | 94.83% | 318ms | 1.86s | 37 tps | 131K | $0.400 / $0.400 | |
| No data | — | — | — | 100% | — | — | — | 131K | $0.800 / $0.800 |
- Amazon Bedrock100%Healthy24h 100%
- 7d
- 99.97%
- 30d
- 99.40%
- p50
- 372ms
- p99
- 2.01s
- Throughput
- 72 tps
- Context
- 131K
- $/Mtok
- $0.720 / $0.720
amazon-bedrock - DeepInfra100%Healthy24h 99.48%
- 7d
- 96.98%
- 30d
- 94.83%
- p50
- 318ms
- p99
- 1.86s
- Throughput
- 37 tps
- Context
- 131K
- $/Mtok
- $0.400 / $0.400
deepinfra/turbofp8 - No data24h —
- 7d
- —
- 30d
- 100%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 131K
- $/Mtok
- $0.800 / $0.800
coreweave/bf16bf16
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 · 47 days with data, 43 endpoint-days below 90%.