Skip to main content
Amazon Bedrock

GPT-5.6 Luna (US) pricing, context window and limits

GPT-5.6 Luna (US) costs $0.22 per million input tokens and $1.32 per million output tokens at Amazon Bedrock list price. It accepts up to 1,050,000 tokens of context and returns up to 128,000 tokens.

  • Model id bedrock/us.openai.gpt-5.6-luna
  • Snapshot

What does GPT-5.6 Luna (US) cost?​

List prices in US dollars per million tokens
Input$0.22
Output$1.32
Cached input (read)$0.022
Cache write$0.275

US dollars per million tokens. A dash means no price is published.

How much can GPT-5.6 Luna (US) read and write?​

Token limits
Context window1,050,000
Max input922,000
Max output128,000

What can GPT-5.6 Luna (US) do?​

Capabilities
Vision (image input)Yes
Tool callingYes
Structured outputYes
ReasoningYes
Inputtext, image
Outputtext

What does a request to GPT-5.6 Luna (US) cost?​

Cost of example requests at list price, in US dollars
A typical request: 1,000 tokens in, 500 out$0.00088
A long request: 10,000 tokens in, 1,000 out$0.0035
1,000 typical requests$0.88
1 million tokens in and 1 million out$1.54

Input read from the provider's prompt cache costs $0.022 per million tokens instead of $0.22, 90% less. A request that repeats a 1,000-token prompt from the cache costs $0.00068 instead of $0.00088.

Among 199 Amazon Bedrock models with a published price, GPT-5.6 Luna (US) is the 48th cheapest by input price. Its context window is the 3rd largest of 199. List prices only; discounts, batch prices and prices above 200K tokens are not shown.

How do I call GPT-5.6 Luna (US) through DVARA?​

Configure the bedrock provider in the DVARA LLM Gateway and send the model id bedrock/us.openai.gpt-5.6-luna. DVARA, the AI gateway, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.

In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set gets no cost record: its calls count against no budget and appear in no report, and the gateway records the model as unpriced. Every cost record says which price it used.

What should I check before relying on this data?​

The weekly review marked this entry. A person saw each mark and kept the model listed.

  • The provider charges more above 200K tokens of input; the table shows the base price.

Which other Amazon Bedrock models are there?​

All 199 Amazon Bedrock models · Search the full catalogue

Which models from other providers are similar to GPT-5.6 Luna (US)?​

These are the closest in context window and input price, one per provider.

Snapshot 16 October 2026. DVARA reviews every price weekly before it is published. Get the whole catalogue as llm-models.json. Prices are list prices in US dollars per million tokens; check your provider contract before you budget.