OpenAI GPT-6 Luna: Pricing, Specs and Limits
OpenAI GPT-6 Luna: fast, cost-efficient model in the GPT-6 series, 1M context, 0.10 in / 0.50 out per 1M tokens. Specs, limits and test prompts.
By ShilpBot Team · Published · 3 min read
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. The listing says it suits high-volume and latency-sensitive workloads such as chat, classification and lightweight agentic work.
At $0.10 per million input tokens and $0.50 per million output tokens it is the cheapest OpenAI model here, with the same 1.05M-token context window as its larger siblings.
Prices and specifications checked against the public OpenRouter catalogue on 2026-11-16. See the live model page for current limits.
OpenAI GPT-6 Luna quick facts
| Detail | Value |
|---|---|
| Developer | OpenAI |
| Model ID | openai/gpt-6-luna |
| Added to the catalogue | 2026-09-22 |
| Type | Fast, cost-efficient model in the GPT-6 series |
| Parameters | Not listed |
| Context window | about 1M tokens (1,050,000) |
| Maximum output | 128,000 tokens |
| Input types | file, image, text |
| Price | 0.10 in / 0.50 out per 1M tokens (cached input 0.010) |
Feature support from the catalogue: Tool calling: listed; JSON / structured output: listed; Adjustable reasoning effort: listed.
What OpenAI GPT-6 Luna is good for
- Chat, classification and lightweight agent tasks at high volume.
- Latency-sensitive apps where cost per request matters.
- File and image input at low price.
Limits of OpenAI GPT-6 Luna
- Luna Pro looks the same price but uses far more reasoning tokens.
- It is the small model in the series, so hard reasoning belongs to Sol or Terra.
- No audio or video input.
How OpenAI GPT-6 Luna compares
- Anthropic Claude Haiku 5.5: It has a larger context window (1,050,000 against 1,000,000 tokens); both cap output at 128,000 tokens; it costs 0.10 input and 0.50 output per million tokens against 0.10 and 0.50.
- OpenAI GPT-6.1 Terra: Both have a 1,050,000-token context window; both cap output at 128,000 tokens; it costs 0.10 input and 0.50 output per million tokens against 1.00 and 5.00.
- OpenAI GPT-6.1 Sol: Both have a 1,050,000-token context window; both cap output at 128,000 tokens; it costs 0.10 input and 0.50 output per million tokens against 2.00 and 10.00.
Calling OpenAI GPT-6 Luna from code
Use the model ID openai/gpt-6-luna with any OpenAI-compatible client pointed at OpenRouter:
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "openai/gpt-6-luna", "messages": [{"role": "user", "content": "Explain what you can do in two sentences."}]}'Prompts that show what OpenAI GPT-6 Luna can do
- Classify 100 messages into five categories and compare with your own labels.
- Use it as a fast front-end that decides when to call a bigger model.
- Compare with Claude Haiku 5.5 on the same classification set.
What OpenAI GPT-6 Luna costs
The catalogue lists 0.10 per million input tokens and 0.50 per million output tokens, with cached input at 0.010 per million. Sending 1 million input tokens and receiving 100,000 output tokens would cost about 0.15. A single coding-agent step with a 150,000-token prompt and a 10,000-token answer would cost about $0.020 before caching. If your client reuses the same prompt prefix, cached input at 0.010 per million tokens can cut the input side of that bill by about 90 percent. GPT-6 Luna Pro is the same underlying model served with reasoning mode set to pro. It has the same listed per-token price, but pro mode spends far more tokens, so each request can cost much more. Prices are set by the provider, can change, and may differ between hosting providers, so check the live model page before you budget.
Keep reading
Compare every paid model by price in our AI model pricing roundup, or see the free models roundup. New to terms like mixture-of-experts? Start with how neural networks learn.
Frequently asked questions
Is GPT-6 Luna Pro just a different model?
No. It is the same underlying model as Luna with reasoning mode set to pro. It gives higher quality on complex tasks but uses many more tokens per request.
What are the cost and limits of OpenAI GPT-6 Luna?
As of 2026-11-16 the catalogue lists 0.10 per million input tokens and 0.50 per million output tokens. About 1M tokens (1,050,000) context window, up to 128,000 output tokens, model ID openai/gpt-6-luna. Prices can change, so check the live model page.
