LLMap
Models /GPT-6 Luna /Where to run
Provider guide

Where to run GPT-6 Luna

8 live listings tracked.

CHEAPEST
Microsoft Azure AI
$0.10 / $0.50
per 1M tokens in / out
FASTEST MEASURED
OpenAI
94 tok/s
measured throughput · $0.20 input / $1.00 output per million tokens
OpenRouter$0.10 in/1M$0.50 out/1M—1.1M—3 hours agoOpenAI$0.10 in/1M$0.50 out/1M66 tok/s922K—3 hours agoMicrosoft Azure AIzero-retentionCHEAPEST$0.10 in/1M$0.50 out/1M54 tok/s1.1M—3 hours agoAmazon Bedrock$0.11 in/1M$0.55 out/1M86 tok/s1.1M—3 hours agoMicrosoft Azure AIzero-retention$0.11 in/1M$0.55 out/1M26 tok/s1.1M—3 hours agoMicrosoft Azure AIzero-retention$0.11 in/1M$0.55 out/1M83 tok/s1.1M—3 hours agoOpenAIflex tier$0.050 in/1M$0.25 out/1M35 tok/s1.1M—3 hours agoOpenAIfast tier$0.20 in/1M$1.00 out/1M94 tok/s1.1M—3 hours ago
Full specs, hardware verdicts and benchmarks on the GPT-6 Luna model page →