O
GPT-5.6 Luna is the efficient GPT-5.6 tier for cost-sensitive, high-volume workloads while retaining long context, reasoning controls, and agent tools.
- Success
- 99.6%
- Avg latency
- 7.3s
defaultx1
standard
Length ≤ 272K
Input$0.2 / 1M tokens
Output$1.2 / 1M tokens
Cache read$0.02 / 1M tokens
Cache write$0.25 / 1M tokens
long_context
Input$0.4 / 1M tokens
Output$1.8 / 1M tokens
Cache read$0.04 / 1M tokens
Cache write$0.5 / 1M tokens
Image input$8 / 1M tokens
Image output$30 / 1M tokens
discountx0.8
standard
Length ≤ 272K
Input$0.16 / 1M tokens
Output$0.96 / 1M tokens
Cache read$0.016 / 1M tokens
Cache write$0.2 / 1M tokens
long_context
Input$0.32 / 1M tokens
Output$1.44 / 1M tokens
Cache read$0.032 / 1M tokens
Cache write$0.4 / 1M tokens
Image input$6.4 / 1M tokens
Image output$24 / 1M tokens
relayx0.3
standard
Length ≤ 272K
Input$0.06 / 1M tokens
Output$0.36 / 1M tokens
Cache read$0.006 / 1M tokens
Cache write$0.075 / 1M tokens
long_context
Input$0.12 / 1M tokens
Output$0.54 / 1M tokens
Cache read$0.012 / 1M tokens
Cache write$0.15 / 1M tokens
Image input$2.4 / 1M tokens
Image output$9 / 1M tokens
tempx0.1
standard
Length ≤ 272K
Input$0.02 / 1M tokens
Output$0.12 / 1M tokens
Cache read$0.002 / 1M tokens
Cache write$0.025 / 1M tokens
long_context
Input$0.04 / 1M tokens
Output$0.18 / 1M tokens
Cache read$0.004 / 1M tokens
Cache write$0.05 / 1M tokens
Image input$0.8 / 1M tokens
Image output$3 / 1M tokens
openaiopenai-responseanthropicgeminiimage-generationopenai-response-compactopenai-alpha-searchOpenAI compatibleResponses APIAnthropic compatibleGemini compatibleImage generationVisionCompare