Llama Guard 4 12B
meta-llama/llama-guard-4-12b
Compare with Llama 4 Maverick, Llama 4 Scout, Llama 3.3 70B Instruct
CompareLlama Guard 4 12B
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
DeepInfradeepinfra/bf16bf16 | Healthy | 100% | 99.42% | 391ms | 2.34s | 6.0 tps | 164K | $0.180 / $0.180 |
Togethertogether | Healthy | 100% | 99.96% | 132ms | 940ms | 15 tps | 1.0M | $0.200 / $0.200 |
- DeepInfra100%Healthy24h 99.42%
- p50
- 391ms
- p99
- 2.34s
- Throughput
- 6.0 tps
- Context
- 164K
- $/Mtok
- $0.180 / $0.180
deepinfra/bf16bf16 - Together100%Healthy24h 99.96%
- p50
- 132ms
- p99
- 940ms
- Throughput
- 15 tps
- Context
- 1.0M
- $/Mtok
- $0.200 / $0.200
together
Measured 3m 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.