Llama 3.2 3B Instruct
meta-llama/llama-3.2-3b-instructInputOutput
Compare its 2 providersIncident RSSCompare with Llama 3.2 1B Instruct, Llama 3.3 70B Instruct, Llama 3.1 8B Instruct
CompareLlama 3.2 3B Instruct
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| Healthy | 100% | 99.94% | 99.99% | 99.95% | 452ms | 1.02s | 303 tps | 131K | $0.050 / $0.330 | |
Cloudflarecloudflare | Healthy | 97.76% | 99.48% | 98.46% | 98.44% | 258ms | 594ms | 264 tps | 80K | $0.051 / $0.335 |
- Parasail100%Healthy24h 99.94%
- 7d
- 99.99%
- 30d
- 99.95%
- p50
- 452ms
- p99
- 1.02s
- Throughput
- 303 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.330
parasail/bf16bf16 - Cloudflare97.76%Healthy24h 99.48%
- 7d
- 98.46%
- 30d
- 98.44%
- p50
- 258ms
- p99
- 594ms
- Throughput
- 264 tps
- Context
- 80K
- $/Mtok
- $0.051 / $0.335
cloudflare
Measured 2m 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.
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 · 2 endpoints · 47 days with data, 14 endpoint-days below 90%.