Llama Guard 4 12B: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
- DeepInfra100%◆ (best)Healthy24h 99.75%
- 7d
- 99.47%
- 30d
- 99.47%
- p50
- 440ms
- p99
- 4.48s
- Throughput
- 6.0 tps
- Context
- 164K
- $/Mtok
- $0.180 / $0.180◆ (best)
deepinfra/bf16bf16 - Together100%◆ (best)Healthy24h 99.90%
- 7d
- 99.91%◆ (best)
- 30d
- 99.91%◆ (best)
- p50
- 123ms◆ (best)
- p99
- 1.06s◆ (best)
- Throughput
- 16 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.200 / $0.200
together
Measured 57s ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
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.