llm.ing

GPT-6 Luna

OpenAIOpenRouter ↗Artificial Analysis ↗

OpenAI's most efficient model for focused, high-volume tasks

Benchmarks

BenchmarkCategoryScoreVariantProvenanceSourceObserved
AA Intelligence Indexintelligence27.9—mirroropenrouterNov 4, 2026
23.5xhigh-effortindependentaaNov 4, 2026
Median output speedspeed115 tok/sxhigh-effortindependentaaNov 19, 2026
Median time to first tokenspeed31.71sxhigh-effortindependentaaNov 18, 2026

Includes index data from Artificial Analysis.

Providers

Live operational stats per hosting endpoint, via OpenRouter.

ProviderQuantContext$/1M in · outUptime 24hLatencyThroughput
Amazon Bedrock—1.1M$0.1 · $0.599.86%——
Azure—1.1M$0.1 · $0.598.06%——
OpenAI—1.1M$0.1 · $0.5100.00%——
OpenAI—1.1M$0.2 · $1100.00%——
OpenAI—1.1M$0.05 · $0.25100.00%——