GPT-6 Luna

OpenAI's most efficient GPT-6 model, with a 1,050,000-token context window at $0.10 input and $0.50 output per 1M tokens.

OpenAI describes it as
“Our most efficient model for focused, high-volume tasks.”

Compare this model Check how your prompt fits this model’s context window

Last verified: Oct 31, 2026

Context window: 1,050,000
Max output: 128,000
Input price: $0.10
Output price: $0.50
Max input: 922,000
Released: Sep 22, 2026
Knowledge cutoff: May 18, 2026
API model ID: gpt-6-luna

OpenAI documents a 922,000-token maximum input alongside the 1,050,000-token context window.

About GPT-6 Luna

GPT-6 Luna is OpenAI's most efficient model for focused, high-volume tasks, and the lowest-priced of the four flagship models in its catalog at $0.10 input and $0.50 output per million tokens. It takes text and image input, returns text, and offers reasoning effort from none to max. EU data residency is available with Standard, Fast, Flex and Batch processing.

API pricing

Per-token API prices from the provider's pricing page. Thresholds and processing modes are shown explicitly, not folded into one number.

Standard processing · USD per 1M tokens
Rate	Prompts up to 272,000 tokens	Prompts over 272,000 tokens
Input	$0.10	$0.20
Cached input	$0.01	$0.02
Output	$0.50	$0.75
Cache write (30 minutes)	$0.125	$0.25
Cache write (12 hours)	$0.25	$0.50

Batch processing · USD per 1M tokens
Rate	Prompts up to 272,000 tokens	Prompts over 272,000 tokens
Input	$0.05	$0.10
Cached input	$0.005	$0.01
Output	$0.25	$0.375

Fast mode processing · USD per 1M tokens
Rate	Prompts up to 272,000 tokens	Prompts over 272,000 tokens
Input	$0.20	$0.40
Cached input	$0.02	$0.04
Output	$1.00	$1.50

Flex processing is priced the same as Batch.
Prompts above 272K input tokens are billed at 2x the input and cache rates and 1.5x the output rate for the whole request.
Cache writes are billed at 1.25x the uncached input rate for 30-minute retention; 12-hour retention is twice that.
Regional processing adds a 10% premium where available.
OpenAI renamed Priority processing to Fast mode on July 30, 2026.

Modalities and capabilities

What the provider documents for this model. “API tool” means it needs a provider tool or endpoint rather than being native to the model.

Input modalities: Text, Image
Output modalities: Text

ReasoningReasoning: ✓ Yes
reasoning.effort: none, low, medium (default), high, xhigh, max.
Tool / function callingTool / function calling: ✓ Yes
Chat Completions supports function calling only with reasoning_effort set to none; use the Responses API for built-in tools and function calling.
Structured outputsStructured outputs: ✓ Yes
Web searchWeb search: ✓ Yes · API tool
Responses API web_search tool.
Code executionCode execution: ✓ Yes · API tool
Responses API code_interpreter tool.
Computer useComputer use: ✓ Yes · API tool
Responses API computer_use tool.
Image generationImage generation: ✓ Yes · API tool
Through the image_generation tool; the model's own output is text.
Prompt cachingPrompt caching: ✓ Yes
Batch APIBatch API: ✓ Yes
Batch endpoint v1/batch.

Benchmarks

Individual named benchmarks only: there is no overall score. Vendor-reported results come from the model maker's own launch materials. Scores from different sources, versions or settings are not directly comparable.

No benchmark results are listed for this model yet.

Availability and API identifiers

Where GPT-6 Luna is available and the identifier used there
Surface	Identifier
OpenAI APIThe ID is both the alias and the only snapshot; OpenAI lists no dated snapshots.	gpt-6-luna
Responses API	v1/responses
Chat Completions APIFunction calling in Chat Completions requires reasoning_effort none.	v1/chat/completions
Batch API	v1/batch

Limitations and caveats

API vs. apps. These limits and prices describe the OpenAI API model. ChatGPT and Codex can apply different limits and are billed through subscriptions, not per token.

Fine-tuning is not supported for this model.
OpenAI's model pages do not carry an explicit current/preview label; the model is listed in the catalog's flagship section and is not marked deprecated.
OpenAI's launch page was not readable when this record was checked, so no vendor-reported benchmarks are listed.

Sources

Last verified against these sources on Oct 31, 2026. Prices and limits change; follow the links for the live figure.

OpenAI API docs — GPT-6 Luna
Supports: knowledge cutoff, context window, max input, max output, modalities, capabilities, pricing
OfficialChecked Oct 31, 2026
OpenAI API pricing
Supports: pricing
OfficialChecked Oct 31, 2026
OpenAI API model catalog
Supports: status, modalities
OfficialChecked Oct 31, 2026
OpenAI API changelog
Supports: release date
OfficialChecked Oct 31, 2026

Key facts