GPT-5.6 Luna, API id gpt-5.6-luna, is a cost-sensitive OpenAI model for high-volume workloads. OpenAI's model page describes it as roughly comparable to the nano tier of earlier GPT-5 families. Its listed price is $0.20 per 1M input tokens and $1.20 per 1M output tokens, as checked on 2026-10-29.
Key Features
- Large context: 1,050,000-token context window, 922,000 max input, and 128,000 max output.
- Reasoning effort options: none, low, medium (default), high, xhigh, and max.
- Modalities: text and image input, text output.
- Knowledge cutoff: February 16, 2026.
- Tools and features: streaming, structured outputs, function calling, file search, web search, image input, and prompt caching. The Responses API tools list includes web search, file search, image generation, code interpreter, hosted shell, apply patch, skills, computer use, MCP, and tool search.
- Endpoints: Chat Completions, Responses, and Batch. Realtime, Assistants, fine-tuning, embeddings, image, video, audio, and moderation endpoints are not supported.
Pricing
| Item | Price per 1M tokens |
|---|---|
| Input | $0.20 |
| Cached input | $0.02 |
| Output | $1.20 |
Prompts over 272K input tokens cost 2x input and 1.5x output for the full request. Cache writes cost 1.25x the uncached input rate. Only the default gpt-5.6-luna snapshot is listed.
Use Cases
- High-volume classification, extraction, routing, and summarization where cost per request matters.
- Agent sub-tasks that need tool calling and structured outputs at a low price.
- Long-document jobs that benefit from the 1.05M-token window, keeping the 272K-token pricing threshold in mind.
Limitation: it targets cost, not peak capability, and OpenAI's page compares it with GPT-5.6 Terra and GPT-5.4 nano rather than naming a successor.
Getting Started
- Call
gpt-5.6-lunathrough the Responses or Chat Completions API. - Start with the default medium reasoning effort, then try
lowornonefor latency-sensitive work. - Keep prompts under 272K tokens to avoid the long-context surcharge.
FAQ
How much does GPT-5.6 Luna cost?
$0.20 per 1M input tokens, $0.02 cached input, and $1.20 per 1M output tokens on OpenAI's page.
What is its context window?
1,050,000 tokens, with up to 128,000 output tokens.
Does it support images?
Yes, image input is supported. Output is text only.
Does it support fine-tuning or Realtime?
No, both are listed as unsupported.
Alternatives
- GPT-5.6 Terra: the larger GPT-5.6 tier that OpenAI's page compares it against.
- GPT-5.6: the base GPT-5.6 entry in this catalog.
- GPT-6 Luna: the Luna tier in the GPT-6 family.
Conclusion
GPT-5.6 Luna is OpenAI's cheap, high-volume option with a very large context window. See the official model page for current numbers and the models category for comparisons.
Sources
Comments
No comments yet. Be the first to comment!
Related Tools
Related Insights

After Code Stopped Being Scarce (Part II): From AI Writing Code to AI Taking Part in Delivery
A year after leaving my previous employer, I document the delivery workflow for our financial business that we built around Claude Code and Opus 5.5: XaC, progressive rules, independent review and testing by Grok Bot, PR watch, and our actual delivery over the past three months.

Anthropic Subagent: The Multi-Agent Architecture Revolution
Deep dive into Anthropic multi-agent architecture design. Learn how Subagents break through context window limitations, achieve 90% performance improvements, and real-world applications in Claude Code.
Stop Cramming AI Assistants into Chat Boxes: Clawdbot Picked the Wrong Battlefield
Clawdbot is convenient, but putting it inside Slack or Discord was the wrong design choice from day one. Chat tools are not for operating tasks, and AI isn't for chatting.