Llama 3.3 70B Instruct
meta-llama/llama-3.3-70b-instruct
Compare with Llama 3.2 3B Instruct, Llama 3.2 1B Instruct, Llama 3.1 8B Instruct
Showing only the parasail/fp8 provider · show all 13
CompareLlama 3.3 70B Instruct
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 98.21% | 98.12% | 97.85% | 97.85% | 665ms | 5.39s | 40 tps | 131K | $0.220 / $0.500 |
- Parasail98.21%Healthy24h 98.12%
- 7d
- 97.85%
- 30d
- 97.85%
- p50
- 665ms
- p99
- 5.39s
- Throughput
- 40 tps
- Context
- 131K
- $/Mtok
- $0.220 / $0.500
parasail/fp8fp8
Measured 44s ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
Price changes
- Llama 3.3 70B InstructAkashMLakashml/fp8$0.130 / $0.400 → $0.200 / $0.5202026-08-19 09:50 UTC
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.