Provider guide
Where to run Llama Guard 4 12B
4 live offers tracked.
FASTEST MEASURED
14 tok/s
measured throughput · $0.20 input / $0.20 output per million tokens
OpenRouterCHEAPEST$0.18 in/1M$0.18 out/1M—1M—4h agoDeepInfra$0.18 in/1M$0.18 out/1M—164Kbfloat1610h agoDeepInfrazero-retention$0.18 in/1M$0.18 out/1M7 tok/s164Kbf164h agoTogether AIzero-retention$0.20 in/1M$0.20 out/1M14 tok/s1M—4h ago
Full specs, hardware verdicts and benchmarks on theLlama Guard 4 12B model page →