Standard & Paid Price
| Meter | Standard Price | Paid Price | Save |
|---|---|---|---|
| Input price | $0.1000 / 1M tokens | $0.0650 / 1M tokens | -35% |
| Completion price | $0.5000 / 1M tokens | $0.3250 / 1M tokens | -35% |
| Cache read price | $0.0100 / 1M tokens | $0.0065 / 1M tokens | -35% |
| Cache creation price | $0.1250 / 1M tokens | $0.08125 / 1M tokens | -35% |
Description
OpenAI GPT-6 Luna — OpenAI's most efficient model, built for focused, high-volume tasks. It supports text and image input, a 1,050,000-token context window, up to 128,000 output tokens, and reasoning effort from none to max, with medium as the default. Use /v1/responses for tool calling: on /v1/chat/completions, function calling works only with reasoning_effort set to none. On /v1/responses, send the whole conversation in the input array on every turn; requests that carry previous_response_id or conversation are refused.
Capabilities
- Input modalities
- text, image
- Output modalities
- text
- Tasks
- chat, reasoning, vision, file-video-understanding
Decision evidence
GPT-6 Luna is OpenAI's closed-weight model for focused, high-volume tasks, released on 2026-09-22 alongside GPT-6 Sol, with a 1,050,000-token context window (922,000 input), 128,000 output tokens and text and image input. Reviewed tests find it very cheap and fast: it scored 51.99 at max reasoning on AI Coding Daily's leaderboard for about $0.03 a run, close to GPT-6 Sol, while kzhu's test gave it 40/60 and one one-prompt comparison judged its output a flop.
2026-09-25 · Markdown evidence · JSON data
API endpoints
POST /v1/chat/completions(openai)POST /v1/responses(openai-response)