OpenAI · Released Apr 10, 2026
GPT-5.6 Luna (max)
OpenAI's ultra-low-cost, high-speed model offering frontier class intelligence at a fraction of a cent per task.
OpenRating Index
52.5
0–100 composite
Reasoning Index
70.8
0–100 composite
Cost / Task
$0.048
benchmark run
Output speed
149 tok/s
blended tok/s
Time to first token
0.4s
median latency
Input price
$0.08
per 1M tokens
Output price
$0.32
per 1M tokens
Context window
400K
tokens
Strengths
Lowest task cost among frontier architectures ($0.048)
149 tok/s output speed with sub-second TTFT
Ideal for classification, batch routing, and extraction
How we rate GPT-5.6 Luna (max)
OpenRating scores every model on the same axes. The OpenRating Index is a weighted composite of reasoning, knowledge, and agentic benchmarks, normalised to a 0–100 scale. Speed is blended output measured in tokens per second under standardised load, with time-to-first-token reported separately. Prices are list input and output prices per million tokens, and Task Cost measures end-to-end workload spending.
OpenRating Index
52.5
Reasoning Index
70.8
Token Pricing
Input per 1M tokens
$0.08
Output per 1M tokens
$0.32
Cost of 1M input + 1M output
$0.4
Task Cost Economics
Empirical cost breakdown for a standard OpenRating Index benchmark task ($0.048 total).
Related models
Compare GPT-5.6 Luna (max) with the models it is most often measured against.