Back to all models

GPT-5.6 Luna

Cost-optimized GPT-5.6 model for high-volume tasks like classification and data extraction.

gpt-5.6-luna
STABLEGet StartedView uptime
1,050,000 context
Starting at $0.20/M input tokens (tiered)
Starting at $1.20/M output tokens (tiered)
Streaming
Vision
Tools
Reasoning
JSON Output

Select Provider

All Providers for GPT-5.6 Luna

LLM Gateway routes requests to the best providers that are able to handle your prompt size and parameters.

OpenAI
Context: 1.1M
Input
$0.2
/M tokens
Cached
$0.02
/M tokens
Output
$1.2
/M tokens
Tiered Pricing
IN
CACHED
OUT
≤272K tokens
$0.2
$0.02
$1.2
>272K tokens
$0.4
$0.04
$1.8
+ $0.010 per search
Get Started
Azure
Context: 1.1M
Deactivating on Jan 11, 2028
Input
$0.2
/M tokens
Cached
$0.02
/M tokens
Output
$1.2
/M tokens
Tiered Pricing
IN
CACHED
OUT
≤272K tokens
$0.2
$0.02
$1.2
>272K tokens
$0.4
$0.04
$1.8
+ $0.010 per search
Get Started
aws-mantle
Context: 278.5k
Input
$0.22
/M tokens
Cached
$0.022
/M tokens
Output
$1.32
/M tokens
Get Started