---
title: "GPT-6 Luna API Pricing & Context | RZ Automate"
description: "GPT-6 Luna costs $0.10 per 1M input and $0.50 per 1M output tokens. See the 1.05M context window, long-context rates, a cost calculator and alternatives."
url: https://rzautomate.com/models/gpt-6-luna
---

[All AI models](https://rzautomate.com/models)

[OpenAI](https://rzautomate.com/models?provider=OpenAI#models)

Small model

# GPT-6 Luna API pricing and specs

GPT-6 Luna is OpenAI's cheapest and fastest GPT-6 model, built for focused, high-volume tasks. GPT-6 Luna costs $0.10 per million input tokens and $0.50 per million output tokens. It reads up to 1.05 million tokens, writes up to 128,000, and can skip reasoning for instant replies.

[Try the cost calculator](#calculator)
[Compare models →](#compare)

* Tool calling
* Vision
* Reasoning
* Structured output

Input

$0.10 / 1M

Output

$0.50 / 1M

Context

1.05M tokens

Max output

128K tokens

Pricing

## GPT-6 Luna API pricing

Output costs 5× input, so long answers drive the bill. Even so, a thousand typical requests cost well under a dollar.

Prices checked November 14, 2026 on OpenAI's pricing page.

__GPT-6 Luna API pricing per 1M tokens in US dollars__
| Price type              | Per 1M tokens |
| ----------------------- | ------------- |
| Input                   | $0.10         |
| Cached input            | $0.01         |
| Cache write (30 min)    | $0.125        |
| Cache write (12 hours)  | $0.25         |
| Output                  | $0.50         |
| Batch or Flex input     | $0.05         |
| Batch or Flex output    | $0.25         |
| Input over 272K tokens  | $0.20         |
| Output over 272K tokens | $0.75         |
| Fast mode input         | $0.20         |
| Fast mode output        | $1.00         |

Calculator

## GPT-6 Luna cost calculator

Pick a job or type your own numbers. We use the standard rate.

Start from a job

1,000 support emails100 invoices500 leads

Requests per monthInput tokens per requestOutput tokens per requestShare of input from cache (%)

Uses standard rates. Ignores tax, batch discounts and long-context surcharges.

Per month

$0.40

Cost per request

$0.0004

Per year

$4.80

Same job on other models

* [Claude Haiku 5.5$0.40](https://rzautomate.com/models/claude-haiku-5-5)
* [Gemini 3.8 Flash$3.00](https://rzautomate.com/models/gemini-3-8-flash)
* [GPT-6.1 Terra$4.00](https://rzautomate.com/models/gpt-6-1-terra)

* [AI customer support agents](https://rzautomate.com/services/ai-customer-support-agents)
* [AI document processing](https://rzautomate.com/services/ai-document-processing)
* [AI lead generation & CRM automation](https://rzautomate.com/services/ai-lead-generation)

Want this costed on your real data? [Book a free 30-min call](https://rzautomate.com/book?service=support-agents&source=models&model=gpt-6-luna)

Specs

## GPT-6 Luna context window and specs

Context window

1,050,000 tokens

Max output

128,000 tokens

__GPT-6 Luna specifications__
| Spec              | Details                                      |
| ----------------- | -------------------------------------------- |
| Max input         | 922,000 tokens                               |
| Input types       | Text, images                                 |
| Output types      | Text                                         |
| Tool calling      | Yes, best through the Responses API          |
| Structured output | Yes                                          |
| Reasoning         | Optional, six effort levels from none to max |
| Knowledge cutoff  | May 18, 2026                                 |
| Release date      | September 22, 2026                           |
| Open weights      | No                                           |
| API model ID      | gpt-6-luna                                   |

Availability

## Where to access GPT-6 Luna

The price is the same on every major platform. Regional endpoints add 10%.

__Platforms that offer GPT-6 Luna__
| Platform                       | Model ID          | Input $/1M | Output $/1M |
| ------------------------------ | ----------------- | ---------- | ----------- |
| OpenAI API                     | gpt-6-luna        | $0.10      | $0.50       |
| Amazon Bedrock (global)        | openai.gpt-6-luna | $0.10      | $0.50       |
| Microsoft Azure                | —                 | $0.10      | $0.50       |
| Google Cloud (private preview) | gpt-6-luna        | —          | —           |
| OpenRouter                     | openai/gpt-6-luna | $0.10      | $0.50       |

Free access

## Is GPT-6 Luna free?

Yes in ChatGPT, no on the API. ChatGPT Free and Go users get GPT-6 Luna at no cost. API use is paid per token, but it is very cheap.

* Free in ChatGPT Free and Go
* No free API tier
* Batch and Flex cut the price in half

Alternatives

## GPT-6 Luna vs alternatives

GPT-6 Luna and Claude Haiku 5.5 tie on price for short prompts. On long prompts GPT-6 Luna stays cheaper, because Haiku charges 5× past 100K tokens.

__GPT-6 Luna compared with alternatives__
| Model                                        | Input $/1M | Output $/1M | Context | Why pick it                         |
| -------------------------------------------- | ---------- | ----------- | ------- | ----------------------------------- |
| GPT-6 Luna                                   | $0.10      | $0.50       | 1.05M   | Lowest OpenAI price for volume work |
| [GPT-6.1 Terra](https://rzautomate.com/models/gpt-6-1-terra)       | $1.00      | $5.00       | 1.05M   | Better with images and screens      |
| GPT-5.6 Luna                                 | $0.20      | $1.20       | 1.05M   | Older Luna, now twice the price     |
| [Claude Haiku 5.5](https://rzautomate.com/models/claude-haiku-5-5) | $0.10      | $0.50       | 1M      | Same price under 100K tokens        |
| [Gemini 3.8 Flash](https://rzautomate.com/models/gemini-3-8-flash) | $0.75      | $3.75       | 1M      | Google's fast model, pricier        |

[See all AI models →](https://rzautomate.com/models)

Fit

## What GPT-6 Luna is good for

### A good fit for

* Sorting and tagging emails or tickets
* Scoring and enriching leads
* Short, scripted support replies

### Not the best pick for

* Complex agents with many steps
* Messy documents and handwriting
* Hard coding work

Our take

We use GPT-6 Luna for the high-volume steps in client workflows, like routing and tagging, and hand the hard cases to GPT-6.1 Sol.

* [AI customer support agents →](https://rzautomate.com/services/ai-customer-support-agents)

History

## Luna versions

GPT-6 Luna cut the price in half from GPT-5.6 Luna. OpenAI has not released a GPT-6.1 Luna.

1. [GPT-6 Luna](https://rzautomate.com/models/gpt-6-luna)Latest  
Sep 22, 2026  
$0.10 in / $0.50 out per 1M
2. GPT-5.6 LunaPrevious  
Jun 2026 (preview)  
$0.20 in / $1.20 out per 1M

Questions

## GPT-6 Luna FAQ

Prices checked November 14, 2026.

### How much does GPT-6 Luna cost?

GPT-6 Luna costs $0.10 per million input tokens and $0.50 per million output tokens on the OpenAI API. Cached input is $0.01 per million. Batch and Flex jobs cost half. If a prompt goes over 272K tokens, GPT-6 Luna bills the whole request at $0.20 input and $0.75 output.

### Is GPT-6 Luna free?

GPT-6 Luna is free inside ChatGPT for Free and Go users. On the API it is not free, because OpenAI has no free tier for it. API use is cheap, though. A thousand support emails on GPT-6 Luna cost about $0.40 at standard rates.

### What is the GPT-6 Luna context window?

The GPT-6 Luna context window is 1,050,000 tokens. Up to 922,000 of those can be input, and GPT-6 Luna can write up to 128,000 tokens in one reply. Above 272K input tokens the whole request costs more, so trim long prompts where you can.

### When was GPT-6 Luna released?

OpenAI released GPT-6 Luna on September 22, 2026, together with GPT-6 Sol. GPT-6 Luna halved the price of GPT-5.6 Luna. Its knowledge cutoff is May 18, 2026\. OpenAI has not released a GPT-6.1 Luna, so GPT-6 Luna is still the newest Luna model.

### What is the GPT-6 Luna API model ID?

The GPT-6 Luna API model ID is gpt-6-luna. On Amazon Bedrock it is openai.gpt-6-luna, called through global.openai.gpt-6-luna, and on OpenRouter it is openai/gpt-6-luna. For tool calls with reasoning turned on, use GPT-6 Luna through the Responses API, because Chat Completions only supports tools with reasoning off.

### GPT-6 Luna vs Claude Haiku 5.5, which is cheaper?

For short prompts they cost the same, $0.10 input and $0.50 output per million tokens. For 1,000 support emails a month, both come to about $0.40\. Past 100K tokens, Claude Haiku 5.5 charges five times more, so GPT-6 Luna is cheaper for long documents.

## Want GPT-6 Luna working inside your tools?

We build AI agents and automations that let your business answer more customers without adding headcount. On the call we tell you if GPT-6 Luna can handle your volume and what it would cost each month.

* Email  
[choaib@rzautomate.com](mailto:choaib@rzautomate.com)
* Reply time  
Within two hours
* 160automations running in production
* 32businesses served
* 2,000 hrsof manual work taken off clients every month

Or book directly at [cal.com/rzautomate/30min](https://cal.com/rzautomate/30min)

Want the full picture? See [AI customer support agents](https://rzautomate.com/services/ai-customer-support-agents).

Keep comparing

## Compare more models

* [Claude Haiku 5.5Same price from Anthropic](https://rzautomate.com/models/claude-haiku-5-5)
* [GPT-6.1 TerraNext step up from OpenAI](https://rzautomate.com/models/gpt-6-1-terra)
* [Gemini 3.8 FlashGoogle's fast model](https://rzautomate.com/models/gemini-3-8-flash)

1. [Home](https://rzautomate.com/)
2. [AI Models](https://rzautomate.com/models)
3. [OpenAI](https://rzautomate.com/models?provider=OpenAI#models)
4. GPT-6 Luna
