GPT-6 Luna
Neural Network
GPT-6 Luna is a fast OpenAI GPT-6 series model for chat, classification, and high-volume lightweight agent tasks.
Specifications
- Input
- text, images, documents
- Output
- text
- Context size
- 1 050 000 tokens
- Max answer length
- 128 000 tokens
- Reasoning effort
- none, low, medium, high, extra high, max
- Capabilities
- reasoning, function calling
Prompt cost
(per 1M tokens)
Answer cost
(per 1M tokens)
How it works GPT-6 Luna?
GPT-6 Luna is a fast and cost-effective model in OpenAI's GPT-6 lineup, positioned below GPT-6 Sol. It prioritizes response speed and high-volume requests over extreme depth. Its strengths include dialogues, classification, and lightweight agent chains where low latency and predictable costs are crucial. The batch mode is convenient for queue-based processing. In BotHub, the model is available without a VPN or foreign card; payment is in rubles via Russian cards, pay-as-you-go, no subscription. Over 250 models are available in the same window with one-click switching, and a unified OpenAI-compatible API allows changing models without rewriting integrations. Chats are encrypted, and we offer contracts, invoices, and an admin panel with limits for companies. Use cases: first-line support, chatbots, categorizing feedback, data extraction, drafting emails/descriptions, and as a routine layer in multi-agent systems where complex steps are offloaded to larger models.Frequently asked questions about GPT-6 Luna
You can use generated results for commercial purposes. You own all rights to the content you create. The only restriction: make sure your prompt does not include copyrighted third-party material. You are responsible for respecting the rights to any input data.
The model works with text, accepts images and documents as input, reasons before answering, and calls functions. The context window is 1,050,000 tokens, making it suitable for analyzing large documents and codebases, analytics, debugging, refactoring, and agent scenarios with external tools.
The model generates up to 128,000 tokens per response: enough for a large documentation chapter, a detailed report, or an entire large code file. If the task is larger, break it down—the 1,050,000-token context window allows keeping the entire work history in the dialogue.
Yes, this is confirmed by our data: the model builds a chain of thought before providing an answer. The difference is noticeable in STEM, math, logic, and multi-step code analysis tasks, where it is important to arrive at the result sequentially rather than guessing.
Yes, both. The model calls functions and returns structured JSON, making it easy to integrate into agents and workflows. In BotHub, this is available via a unified OpenAI-compatible API: you can switch to another model without rewriting your integration.
The model accepts images and documents as input, including native document processing without prior recognition. Audio and video are not noted in our data, so we do not recommend planning for them in advance: it is easier to test with your own file directly in the BotHub interface.
We do not have specific data on languages, so we cannot promise accuracy in Russian—please test with your prompt. BotHub itself operates from Russia: the website and Telegram bot interface are in Russian, and payment is via Russian cards, without VPN or foreign cards.