GPT-6 Luna
by OpenAI · Released 2026
OpenAI's efficient GPT-6 model for high-volume workloads where responsiveness and cost matter. Multimodal (text + vision), 1.05M context, reasoning, and tool calling at the lowest GPT-6 price.
GPT-6 Luna
Powered by OpenAI · Transformer (proprietary)
Context Window
1.05M
Parameters
Undisclosed
Max Output
128K
Category
LLM Chat
Overview
GPT-6 Luna is OpenAI's efficient GPT-6 model, designed for high-volume workloads where responsiveness and cost efficiency matter. It succeeds GPT-5.6 Luna with updated intelligence and improvements in writing quality and computer use, while keeping the full 1,050,000 token context window (128K max output) and native vision.
Luna supports reasoning with effort selectable from none through xhigh, plus structured outputs, function calling, and prompt caching, and accepts both text and image input. It is the go-to GPT-6 model for real-time chat, summarization, classification, and large-scale automation.
Priced at $0.10 per million input tokens and $0.50 per million output tokens through CallMissed (cached input $0.01; long-context tier over 272K tokens), Luna is the value leader of the GPT-6 lineup — half the price of GPT-5.6 Luna on input.
Pricing
| Metric | Price |
|---|---|
| Input /1M tokens | ₹10.0000 |
| Output /1M tokens | ₹50.0000 |
1 credit = ₹1 = $0.01 USD. Transparent per-call pricing — you pay only for what you call, with no seat fees or minimums.
Key Highlights
- Lowest-cost GPT-6 model
- Optimized for high-volume, latency-sensitive workloads
- Native vision + 1.05M token context window
- Improved writing quality over GPT-5.6 Luna
Technical Details
- Context window: 1,050,000 tokens (128K max output)
- Multimodal: accepts text and image input, returns text
- Reasoning effort: none, low, medium (default), high, xhigh
- Supports structured outputs, function calling, and prompt caching
- Knowledge cutoff: May 2026
- Available via OpenAI API and CallMissed unified gateway
Strengths
- Lowest GPT-6 price with the full 1.05M context window
- Fast responses for real-time and high-volume workloads
- Native vision at a cost-sensitive tier
- Multimodal — combines text and image input
Limitations
- Lower peak capability than GPT-6 Sol on complex tasks
- Proprietary and closed-source — no self-hosting option
Use Cases
API Example
curl https://api.callmissed.com/v1/chat/completions \
-H "Authorization: Bearer cm_YOUR_KEY" \
-d '{"model": "gpt-6-luna", "messages": [{"role": "user", "content": "Classify these support tickets by intent"}]}'Endpoint: POST /v1/chat/completions · Model ID: gpt-6-luna
Try GPT-6 Luna now
Get 1000 free API credits on signup. No credit card required.