GPT-6 Luna

GPT-6 Luna is OpenAI's most efficient model for focused, high-volume tasks. It is part of the gpt-luna line, succeeding GPT-5.6 Luna. It has a context window of 1,050,000 tokens and a maximum output of 128,000 tokens. It accepts image, PDF, and text inputs and returns text. It supports reasoning mode and tool calling. Weights are not open. Pricing starts at $0.08 per million input tokens and $0.40 per million output tokens, with cached input at $0.008 per million tokens.

Against GPT-5.6 Luna: input $0.06 to $0.08, output $0.37 to $0.40, cached input $0.02 to $0.008.

Range across the hosts that serve it: up to $0.20 per 1M input tokens.

• ·1,050,000-token context window
• ·128,000-token max output
• ·Accepts image, PDF, and text inputs
• ·Supports reasoning mode and tool calling
• ·Cached input at $0.008 per million tokens

• Reach for it for high-volume text processing
• Reach for it for long-document analysis with 1M+ token context
• Reach for it for multimodal input handling (image, PDF, text)
• Reach for it for tasks needing reasoning and tool calls

22 hosts serve this model at the price above · the maker's documentation

• 8Arena Review: GPT-6 Luna (Max) Ranks 23rd on Agent Arena with a Single Task Cost of Only $0.052026-09-29
• 9Back to Claude2026-09-25
• 9OpenAI Releases GPT-6 Sol and GPT-6 Luna, API Prices 50% Lower Than GPT-5.62026-09-23
• 8Claude Opus 5.5, GPT-6 Sol, GPT-6 Luna, and a new price war2026-09-23

4 signals of the archive mention this model, each scored against the published bar. This list is rebuilt from the archive at every build, so it cannot go stale.

The registry keeps the six most recent versions of a line. Older ones stay in the file and can be surfaced without a rebuild.

What is the context window of GPT-6 Luna?

The context window is 1,050,000 tokens, and the maximum output is 128,000 tokens.

Does GPT-6 Luna accept image inputs?

Yes, it accepts image, PDF, and text inputs, and returns text output.

What is the pricing for GPT-6 Luna?

Input starts at $0.08 per million tokens, output at $0.40 per million tokens, and cached input at $0.008 per million tokens.