OpenAI: GPT-6 Luna
Try GPT-6 Luna for free in your browser, and add it to your app for free with Puter.js AI API.
Try it free Add to your app// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "openai/gpt-6-luna"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "openai/gpt-6-luna"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
GPT-6 Luna is OpenAI's fast, low-cost model in the GPT-6 family, released September 22, 2026 alongside GPT-6 Sol as smaller, cheaper counterparts to the flagship GPT-6 Astra. OpenAI built both on the training methods behind Astra, carrying over its factuality and alignment gains into models meant for high-volume use.
Luna targets tightly scoped, high-volume work such as summarizing documents, extracting information, and answering straightforward questions. On DeepSWE 1.1, a coding benchmark, OpenAI reports Luna scoring 66.6%, close behind Sol's 68.8%. OpenAI also says that at higher reasoning-effort settings, Luna can match GPT-5.6 Sol's quality at roughly a hundredth of the cost.
At $0.10 per million input tokens and $0.50 per million output tokens, it costs 50% less on input and 58% less on output than GPT-5.6 Luna, positioning it for applications that run at scale rather than tasks needing peak accuracy.
Context Window 1M
tokens
Max Output 128K
tokens
Input Cost $0.1
per million tokens
Output Cost $0.5
per million tokens
Input text, image
modalities
Tool Use Yes
Knowledge Cutoff May 18, 2026
Release Date Sep 22, 2026
Output Speed 114
tokens / sec
Latency 120.04s
time to first token
Try GPT-6 Luna for free
Try GPT-6 Luna instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How GPT-6 Luna performs on standard evaluations.
| Benchmark | Score |
|---|---|
| Humanity's Last Exam Cross-domain reasoning | 38.5% |
| SciCode Scientific programming | 54.6% |
| LCR Long-context reasoning | 83.3% |
Scores sourced from Artificial Analysis.
Find other OpenAI models →
GPT Image 2.6 Flare
GPT Image 2.6 Flare is OpenAI's speed-oriented image generation and editing model, released November 4, 2026 in the GPT Image 2.6 family alongside GPT Image 2.6 Sunburst. OpenAI says both 2.6 models generate images 50% faster than before, and Flare can produce an image in as little as six seconds at low quality. OpenAI positions Flare for posters, product imagery, and other layout-focused work. The API supports image markup, so requests can mark specific areas to change, and a complexity setting that controls how much planning the model does. OpenAI recommends low complexity for most quick edits and medium or high for scenes with many elements or constraints. At low quality and 1024x1024 resolution, an image costs $0.0247.
ImageGPT Image 2.6 Sunburst
GPT Image 2.6 Sunburst is an image generation and editing model from OpenAI, released November 4, 2026 as part of the GPT Image 2.6 family alongside GPT Image 2.6 Flare. It takes text and image input and returns generated or edited images. OpenAI positions Sunburst for higher-quality generation and stronger consistency across edits, while Flare focuses on speed and layout quality. OpenAI says the 2.6 models generate images 50% faster than GPT Image 2.5. It is available through the OpenAI API and suits developers building campaign creative, product imagery, or multi-step editing workflows. At low quality and 1024x1024 resolution, an image costs $0.0247.
ChatGPT-6.1 Terra
GPT-6.1 Terra is a mid-tier OpenAI model that follows GPT-5.6 Terra in the Terra line. We found no official OpenAI announcement or published benchmarks for it, so details here come from the provider listing and press reports. It accepts text, image, and file input and returns text. It has a 1,050,000-token context window, 128,000 max output tokens, and supports tool calling. Pricing is $1 per million input tokens and $5 per million output tokens, lower than GPT-6.1 Sol's $2 and $10. The Information reports that OpenAI intends Terra to outperform GPT-6.1 Sol at a lower price, though we could not verify this. It suits cost-sensitive agentic and document workloads.
Frequently Asked Questions
You can access GPT-6 Luna by OpenAI through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
GPT-6 Luna is free to try with a Puter account. Every account includes a free AI allowance, and you can chat with it in the playground on this page. You can upgrade your account anytime for a larger allowance.
GPT-6 Luna is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.
| Price per 1M tokens | |
|---|---|
| Input | $0.1 |
| Output | $0.5 |
GPT-6 Luna was created by OpenAI and released on Sep 22, 2026.
GPT-6 Luna supports a context window of 1M tokens. For reference, that is roughly equivalent to 2,100 pages of text.
GPT-6 Luna can generate up to 128K tokens in a single response.
GPT-6 Luna has a knowledge cutoff date of May 18, 2026. This means the model was trained on data available up to that date.
GPT-6 Luna accepts the following input types: text, image. It produces: text.
Yes, GPT-6 Luna supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
GPT-6 Luna scores 27.9 on the Artificial Analysis Intelligence Index, outperforming 42% of tracked models.
Yes — the GPT-6 Luna API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Add GPT-6 Luna to your app for free
Developers can integrate GPT-6 Luna for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.