Llama 3.2 3B Instruct
meta-llama/llama-3.2-3b-instruct
Compare with Llama 3.2 1B Instruct, Llama 3.3 70B Instruct, Llama 3.1 8B Instruct
CompareLlama 3.2 3B Instruct
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Cloudflarecloudflare | Healthy | 100% | 97.12% | 328ms | 850ms | 59 tps | 80K | $0.051 / $0.335 |
Parasailparasail/bf16bf16 | Healthy | 100% | 99.99% | 310ms | 3.43s | 60 tps | 131K | $0.050 / $0.330 |
- Cloudflare100%Healthy24h 97.12%
- p50
- 328ms
- p99
- 850ms
- Throughput
- 59 tps
- Context
- 80K
- $/Mtok
- $0.051 / $0.335
cloudflare - Parasail100%Healthy24h 99.99%
- p50
- 310ms
- p99
- 3.43s
- Throughput
- 60 tps
- Context
- 131K
- $/Mtok
- $0.050 / $0.330
parasail/bf16bf16
Measured 5m 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 and p99 are OpenRouter's rolling 30-minute windows, averaged over the hour.
Throughput
Median tokens per second.