gpt-5.6-luna

OpenAI·Dynamic Pricing

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

TPS

—

Average latency

—

Success rate

—

Pricing

Base Price

Input

$0.2/ 1M

Output

$1.2/ 1M

Cache Read$0.02/ 1M

Cache Write$0.25/ 1M

Dynamic Pricing

Prices vary by usage tier and request conditions

Tiered price table

0_272k

Length ≤ 272K

Input

$0.2000

Output

$1.2000

Cache Read

$0.0200

Cache Write

$0.2500

272k_plus

Input

$0.4000

Output

$1.8000

Cache Read

$0.0400

Cache Write

$0.5000

Tier	Input	Output	Cache Read	Cache Write
0_272k Length ≤ 272K	$0.2000	$1.2000	$0.0200	$0.2500
272k_plus	$0.4000	$1.8000	$0.0400	$0.5000

Pricing by Group

default2x

Tier	Input	Output	Cache Read	Cache Write
0_272k	$0.4	$2.4	$0.04	$0.5
272k_plus	$0.8	$3.6	$0.08	$1

Prices shown per 1M tokens

Model

ProviderOpenAI

TypeDynamic Pricing

Groups

default

Endpoints

openai