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
Compare its 13 providers · Incident RSS
Showing only the crusoe/bf16 provider · show all 13
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.74% | 99.07% | 99.07% | 326ms | 1.98s | 55 tps | 131K | $0.250 / $0.750 |
- Crusoe100%Healthy24h 99.74%
- 7d
- 99.07%
- 30d
- 99.07%
- p50
- 326ms
- p99
- 1.98s
- Throughput
- 55 tps
- Context
- 131K
- $/Mtok
- $0.250 / $0.750
crusoe/bf16bf16
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
Price history
Input $/Mtok
Step line — each recorded price holds until the next change.
Output $/Mtok
Step line — each recorded price holds until the next change.
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.
Throughput
Median tokens per second.
Daily availability
Half a year, one cell per UTC day.
Colour by worst endpoint-hour of each UTC day · 3 days with data, 3 with at least one endpoint-hour below 90%.