GPT-6 Luna Pro: API price, context window and how to connect
GPT-6 Luna Pro by OpenAI: $0.1 per million input tokens, $0.5 per million output tokens, a 1.05M-token window. What it is good for, what to compare it with and how to connect it in SKILLOK.
In this article
In short#
GPT-6 Luna in the pro reasoning mode: a cheap model given more time to think. An answer takes noticeably more tokens than plain Luna.
Specifications#
| Provider | OpenAI |
| Released | 2026-09-22 |
| Context window | 1.05M tokens |
| Accepts | files, images, text |
| Answers with | text |
| Reasoning mode | yes |
| Tool calling | yes |
| Open weights | no |
| Identifier | openai/gpt-6-luna-pro |
Price#
| Per 1M tokens | In dollars |
|---|---|
| Input (question, context) | $0.1 |
| Output (answer) | $0.5 |
For reference: a conversation of 20 questions of ~500 tokens and answers of ~800 tokens costs about $0.009. Models in reasoning mode spend more tokens on an answer than the text shows: the reasoning is paid for too.
What it is good for#
- Medium tasks for little money
- Checking reasoning before using an expensive model
- Step-by-step study problems
Similar models#
Catalog models with the same kind of output, closest in the price of a typical request.
| Model | Input | Output | Window | Price |
|---|---|---|---|---|
| GPT-6 Luna | $0.1 | $0.5 | 1.05M | about the same |
| Claude Haiku 5.5 | $0.1 | $0.5 | 1M | about the same |
| Qwen3.8 Flash | $0.15 | $0.47 | 1M | about the same |
| Qwen3.8 Omni Flash | $0.15 | $0.47 | 1M | about the same |
| Mistral Small 4 | $0.15 | $0.6 | 262K | 1.3× more expensive |
Other OpenAI models#
How to connect in SKILLOK#
GPT-6 Luna Pro works through OpenRouter: add an OpenRouter key in Settings → AI and pick the openai/gpt-6-luna-pro model. It then becomes available in Space AI, in tasks and to the repository agent. In detail — Connecting a model in SKILLOK.
Where the data comes from#
Prices, the context window and capabilities come from the public OpenRouter catalog as of 2026-10-19. A provider may change the price — the exact figure is always on the model's OpenRouter page.
Was this helpful?