GPT-6 Luna
Neural Network
GPT-6 Luna is a fast OpenAI model for chat, classification, and lightweight agent tasks. GPT-6 Luna API is available in BotHub.
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 from OpenAI's GPT-6 line. Positioned below GPT-6 Sol, it is designed for latency-sensitive streaming tasks: dialogues, classification, and simple agent scenarios. In BotHub, the model is accessible from Russia without a VPN or foreign card: pay with Russian cards in rubles based on actual token usage, not subscriptions. Access over 250 other neural networks in one window to compare responses and switch to a more powerful model without rewriting your integration, thanks to the unified OpenAI-compatible API. Chats are encrypted via AES-GCM, and companies get access to contracts, invoices, electronic document management, and an admin panel with limits. Use GPT-6 Luna for first-line support, categorize inquiries and reviews, build lightweight agents for routine operations, prepare short texts in batches, and use the model as a fast layer in a multimodal system, leaving complex requests 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.
gpt-6-luna works with text, images, and documents: it parses long files, writes and edits code, and helps with analytics and STEM tasks. A context window of up to 1,050,000 tokens allows you to keep an entire repository or document package in a single dialogue without splitting them up.
Up to 128,000 tokens in a single response—that's dozens of pages. Enough for a large technical document, detailed code analysis, or a long translation. If the task is even larger, just ask it to continue: everything already written remains in the dialogue context.
Yes, the reasoning mode is confirmed by our data: before answering, the model breaks down the task step-by-step. This is noticeable in math, logic, code debugging, and multi-step analytics—where a verifiable solution process is more important than an instant answer.
Yes, both function calling and structured JSON output according to your schema are supported. Connect the model to internal services and databases, and receive answers in a predictable format. Through the unified OpenAI-compatible BotHub API, you can swap in another model without rewriting your integration.
Images and documents—yes: send a screenshot, diagram, table, or PDF and ask it to analyze the content. Input support for audio and video is not noted in our data, so expect to work with text, images, and files.
Our data does not specify prompt and response languages, so we won't make promises—it's easier to test it with your own task, which takes a couple of minutes. BotHub itself is Russian-friendly: accessible from Russia without a VPN or foreign card, with payment via Russian cards.