GPT-6 Luna

gpt-6-luna

Optimized for cost-sensitive, high-volume workloads

Intelligence: 38.1
Context: 1.05M
Training cutoff: 2026-05
Added: 2026-09-30
Inputs: Vision

Providers

One route serves GPT-6 Luna, and every figure below is measured on it. Where the selected window has too little traffic, the figure names what it is based on instead.

OpenAI only route

gpt-6-luna

Uptime

99.9%

0% errors · 3 calls

Input / 1M: $0.10 ≤272K input
Output / 1M: $0.50 ≤272K input
TTFT: -- no requests yet
Output rate: -- no streamed responses

1.05M context 128,000 max output cache $0.02 read / $0.25 write per 1M Vision Standard retentionno streams · 3 calls · 30m

TTFT is the median time to the first visible answer token over real ModelRelay requests, with a fixed prompt standing in for models that have no traffic yet. Speed ranks by it. Intelligence is the Artificial Analysis Intelligence Index.