# OpenAI: GPT-6 Luna (batch)

Provider: openai  
Category: llm  
Model ID: `openai/gpt-6-luna:batch`

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lightweight agentic...

## Specs

- Context length: 1050000 tokens
- Max output: 128000 tokens
- Modalities: file, image, text
- Released: 2026-09-22

## Pricing

- Input: $0.05 per million tokens
- Output: $0.25 per million tokens

## Providers

- **openai** — ctx 1050000, input $0.05/M, output $0.25/M

## Verdict

GPT-6 Luna (batch) offers OpenAI's latest reasoning architecture at 90% lower cost than real-time variants, trading response speed for economics. The 1M+ token context window handles book-length documents and complex codebases without chunking. Best for teams running high-volume analysis, research synthesis, or code review workflows where 24-hour turnaround is acceptable and cost per token matters more than instant results.

---
Last verified: 2026-10-19T02:30:34.239Z  
Canonical URL: https://switchy.build/directory/models/gpt-6-luna-batch