gpt-5.6-luna

OpenAI·Dynamic billing

Cost-efficient gpt-5.6 model for fast, high-volume workloads

Pricing

Supply channels

OfficialSales ratio 1x

Tiered price table

base

Length ≤ 272K

Input

$0.2 / 1M

Output

$1.2 / 1M

Cache Read

$0.02 / 1M

Cache Write

$0.25 / 1M

context_272000

Input

$0.4 / 1M

Output

$1.8 / 1M

Cache Read

$0.04 / 1M

Cache Write

$0.5 / 1M

Tier	Input	Output	Cache Read	Cache Write
base Length ≤ 272K	$0.2 / 1M	$1.2 / 1M	$0.02 / 1M	$0.25 / 1M
context_272000	$0.4 / 1M	$1.8 / 1M	$0.04 / 1M	$0.5 / 1M

Hybrid cloudSales ratio 0.8x

Tiered price table

base

Length ≤ 272K

Input

$0.2 / 1M$0.16 / 1M

Output

$1.2 / 1M$0.96 / 1M

Cache Read

$0.02 / 1M$0.016 / 1M

Cache Write

$0.25 / 1M$0.2 / 1M

context_272000

Input

$0.4 / 1M$0.32 / 1M

Output

$1.8 / 1M$1.44 / 1M

Cache Read

$0.04 / 1M$0.032 / 1M

Cache Write

$0.5 / 1M$0.4 / 1M

Tier	Input	Output	Cache Read	Cache Write
base Length ≤ 272K	$0.2 / 1M$0.16 / 1M	$1.2 / 1M$0.96 / 1M	$0.02 / 1M$0.016 / 1M	$0.25 / 1M$0.2 / 1M
context_272000	$0.4 / 1M$0.32 / 1M	$1.8 / 1M$1.44 / 1M	$0.04 / 1M$0.032 / 1M	$0.5 / 1M$0.4 / 1M

Special offerSales ratio 0.1x

Tiered price table

base

Length ≤ 272K

Input

$0.2 / 1M$0.02 / 1M

Output

$1.2 / 1M$0.12 / 1M

Cache Read

$0.02 / 1M$0.002 / 1M

Cache Write

$0.25 / 1M$0.025 / 1M

context_272000

Input

$0.4 / 1M$0.04 / 1M

Output

$1.8 / 1M$0.18 / 1M

Cache Read

$0.04 / 1M$0.004 / 1M

Cache Write

$0.5 / 1M$0.05 / 1M

Tier	Input	Output	Cache Read	Cache Write
base Length ≤ 272K	$0.2 / 1M$0.02 / 1M	$1.2 / 1M$0.12 / 1M	$0.02 / 1M$0.002 / 1M	$0.25 / 1M$0.025 / 1M
context_272000	$0.4 / 1M$0.04 / 1M	$1.8 / 1M$0.18 / 1M	$0.04 / 1M$0.004 / 1M	$0.5 / 1M$0.05 / 1M

Model

ProviderOpenAI

TypeDynamic billing

Endpoints

anthropicopenaiopenai-response

Tags

ReasoningToolsFilesVision1.1M

gpt-5.6-luna