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
Released July 9, 2026
Starting at $0.18/M (10% off) input tokens (tiered)
Starting at $1.08/M (10% off) output tokens (tiered)
Streaming
Vision
Tools
Reasoning
JSON Output
Structured JSON
No ratings yetSign in to rate
10% offthis model via OpenAI

Select Provider

All Providers for GPT-5.6 Luna

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

OpenAI
Context: 1.1M10% off
Input
$0.2$0.18
10% off
/M tokens
Cache Read
$0.02$0.018
10% off
/M tokens
Output
$1.2$1.08
10% off
/M tokens
Cache Write 5m
$0.25$0.225
10% off
/M tokens
Cache Write 1h
$0.25$0.225
10% off
/M tokens
Tiered Pricing
IN
CACHED
OUT
≤272K tokens
$0.2$0.18
10% off
$0.02$0.018
10% off
$1.2$1.08
10% off
>272K tokens
$0.4$0.36
10% off
$0.04$0.036
10% off
$1.8$1.62
10% off
+ $0.010$0.009 per search
Get Started
Azure
Context: 1.1M
Input
$0.2
/M tokens
Cache Read
$0.02
/M tokens
Output
$1.2
/M tokens
Cache Write 5m
$0.25
/M tokens
Cache Write 1h
$0.25
/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
Cache Read
$0.022
/M tokens
Output
$1.32
/M tokens
Cache Write 5m
$0.275
/M tokens
Cache Write 1h
$0.275
/M tokens
Get Started

Frequently asked questions

What is GPT-5.6 Luna?

Cost-optimized GPT-5.6 model for high-volume tasks like classification and data extraction. You can access it through OffRail's OpenAI-compatible API with automatic provider routing, fallback, and cost analytics.

How much does GPT-5.6 Luna cost?

Pricing for GPT-5.6 Luna on OffRail starts at $0.20 per million input tokens and $1.20 per million output tokens, depending on the provider. The pricing table above always reflects the current per-provider rates.

What is the context length of GPT-5.6 Luna?

GPT-5.6 Luna supports a context window of up to 1,050,000 tokens on its largest provider deployment.

Which providers serve GPT-5.6 Luna?

GPT-5.6 Luna is served by OpenAI, Azure, AWS Mantle through OffRail. Requests are automatically routed to the best available provider, with fallback when a provider has issues.

Does GPT-5.6 Luna support tool calling and structured outputs?

Yes. GPT-5.6 Luna supports both tool (function) calling and strict JSON output schema (upstream-enforced) through OffRail.

When was GPT-5.6 Luna released?

GPT-5.6 Luna was released on July 9, 2026.

More OpenAI models

Browse all models

GPT-5.6 Sol

1,050,000 context$5.00 in / $30.00 out per 1M

GPT-5.6 Terra

1,050,000 context$2.00 in / $12.00 out per 1M

GPT Realtime 2.1

128,000 context$4.00 in / $24.00 out per 1M

GPT Realtime 2.1 Mini

128,000 context$0.60 in / $2.40 out per 1M

GPT-5.5

1,050,000 context$5.00 in / $30.00 out per 1M

GPT-5.5 Pro

1,050,000 context$30.00 in / $180.00 out per 1M