OpenAI: GPT-5.6 Luna

OpenAI: GPT-5.6 Luna is a large language model from OpenAI. It costs $0.200 per million input tokens and $1.20 per million output tokens. Its context window is 1.1M tokens.

ReasoningTool callingStructured outputPrompt cachingBatch tierfile inputimage input

Input / 1M tokens: $0.200
Output / 1M tokens: $1.20
Cached input / 1M: $0.020
Context window: 1.1M

This model also charges $0.01 per search request

That is $10.00 per 1,000 requests, billed on top of the token prices above. On a typical 1,000-in / 500-out exchange the tokens cost $0.0008, so the search fee is 13× the token cost. Per-token rankings elsewhere ignore this entirely.

Who serves it cheapest

3 hosts serve GPT-5.6 Luna. Same weights, same API - the price difference is pure margin and routing.

Providers serving OpenAI: GPT-5.6 Luna, cheapest first
Provider	Input / 1M	Output / 1M	Context	Throughput	Uptime 24h
OpenAICheapest	$0.100	$0.600	1.1M	-	99.9%
Azure	$0.200	$1.20	1.1M	-	69.6%
Amazon Bedrock	$0.220	$1.32	1.1M	-	100.0%

The spread between OpenAI and Amazon Bedrock is 2.2× for identical weights. Quantization and context limits differ, so check both columns before switching.

Benchmarks

Independent scores published alongside the catalogue.

Intelligence index: 37.5
Coding index: 71.4
Agentic index: 42.7

About GPT-5.6 Luna

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic workflows, providing capable reasoning for...

Specifications

OpenAI: GPT-5.6 Luna specifications
Model ID	`openai/gpt-5.6-luna`
Provider	OpenAI
Context window	1.1M tokens
Max output	128K tokens
Input modalities	file, image, text
Output modalities	text
Knowledge cutoff	2026-02-16
Open weights	No
Released	July 9, 2026

Cheaper alternatives

Models that cost less than GPT-5.6 Luna while keeping at least half its context window and every input modality it supports.

Gemini 2.5 Flash Lite

$0.100 in · $0.400 out

2.6× cheaper

GPT-4.1 Nano

$0.100 in · $0.400 out

2.6× cheaper

Muse Spark 1.3 Contributor

$0.100 in · $0.200 out

3.6× cheaper

Muse Spark 1.2 Contributor

$0.100 in · $0.200 out

3.6× cheaper

Auto Router (Beta)

$-1000000.0000 in · $-1000000.0000 out

about the same cheaper

Frequently asked

How much does OpenAI: GPT-5.6 Luna cost?

$0.200 per million input tokens and $1.20 per million output tokens. Cached input reads cost $0.020 per million tokens.

What is the context window of OpenAI: GPT-5.6 Luna?

1.1M tokens, with up to 128K tokens of output per request.

Does OpenAI: GPT-5.6 Luna have extra fees beyond per-token pricing?

Yes. OpenAI: GPT-5.6 Luna charges $0.01 per search request - $10.00 per 1,000 requests - on top of $0.200 per million input tokens and $1.20 per million output tokens. On a typical 1,000-input / 500-output exchange the search fee alone is 13× the token cost.

Which provider serves OpenAI: GPT-5.6 Luna cheapest?

OpenAI at $0.100 per million input tokens - 2.2× cheaper than Amazon Bedrock, the most expensive of the 3 hosts serving it.

Confirm against the source: OpenAI official pricing.