LLMap
Models /gpt-oss-safeguard-20b /Where to run
Provider guide

Where to run gpt-oss-safeguard-20b

13 live listings tracked — output prices vary 3.3× between the cheapest and most expensive host, so the provider choice matters as much as the model choice.

CHEAPEST
Amazon Bedrock
$0.070 / $0.15
per 1M tokens in / out
FASTEST MEASURED
Groq
690 tok/s
measured throughput · $0.075 input / $0.30 output per million tokens
Darkbloom$0.018 in/1M$0.090 out/1M23 tok/s131Kfp84 hours agoAkashMLzero-retention$0.020 in/1M$0.10 out/1M37 tok/s131Kfp44 hours agoCoreWeavezero-retention$0.030 in/1M$0.13 out/1M141 tok/s131Kfp44 hours agoDeepInfrazero-retention through OpenRouterDirect and through OpenRouter$0.030 in/1M$0.14 out/1M88 tok/sthrough OpenRouter131Kbf164 hours agoDekaLLMzero-retention$0.029 in/1M$0.14 out/1M17 tok/s131Kbf164 hours agoParasailzero-retention$0.030 in/1M$0.15 out/1M17 tok/s131Kfp44 hours agoNovita AIzero-retention through OpenRouterDirect and through OpenRouter$0.040 in/1M$0.15 out/1M48 tok/sthrough OpenRouter131Kfp44 hours agoAmazon Bedrockzero-retentionCHEAPEST$0.070 in/1M$0.15 out/1M241 tok/s131K—4 hours agoAmazon Bedrockzero-retention$0.070 in/1M$0.15 out/1M70 tok/s131K—4 hours agoSiliconFlowzero-retention$0.040 in/1M$0.18 out/1M67 tok/s131Kfp810 hours agoGoogle Vertex AIzero-retention$0.070 in/1M$0.25 out/1M86 tok/s131K—4 hours agoGroqzero-retention$0.075 in/1M$0.30 out/1M690 tok/s131K—4 hours agoOpenRouter$0.075 in/1M$0.30 out/1M—131K—5 days ago
Full specs, hardware verdicts and benchmarks on the gpt-oss-safeguard-20b model page →