Llama 3.1 70B Instruct
meta-llama/llama-3.1-70b-instruct
Compare 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% | 99.36% | 99.71% | 99.71% | 319ms | 1.07s | 19 tps | 131K | $0.720 / $0.720 |
| Healthy | 100% | 99.99% | 99.97% | 99.97% | 200ms | 538ms | 25 tps | 128K | $0.800 / $0.800 | |
| Healthy | 99.92% | 97.10% | 96.31% | 96.31% | 285ms | 1.26s | 19 tps | 131K | $0.400 / $0.400 |
- Amazon Bedrock100%Healthy24h 99.36%
- 7d
- 99.71%
- 30d
- 99.71%
- p50
- 319ms
- p99
- 1.07s
- Throughput
- 19 tps
- Context
- 131K
- $/Mtok
- $0.720 / $0.720
amazon-bedrock - CoreWeave100%Healthy24h 99.99%
- 7d
- 99.97%
- 30d
- 99.97%
- p50
- 200ms
- p99
- 538ms
- Throughput
- 25 tps
- Context
- 128K
- $/Mtok
- $0.800 / $0.800
coreweave/bf16bf16 - DeepInfra99.92%Healthy24h 97.10%
- 7d
- 96.31%
- 30d
- 96.31%
- p50
- 285ms
- p99
- 1.26s
- Throughput
- 19 tps
- Context
- 131K
- $/Mtok
- $0.400 / $0.400
deepinfra/turbofp8
Measured 4m 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.