OpenAI: GPT-6 Luna (batch)

OpenAI's GPT-6 Luna (batch) accepts text, image, and file inputs. It offers a context window of 1,050,000 tokens and can return up to 128,000 tokens in a single completion, which makes it a practical fit for long documents or large multi-file inputs. It supports tool use and reasoning. Structured output support is not listed, so confirm it before depending on schema-constrained responses. At $0.05 per million input tokens and $0.25 per million output tokens, this model is worth shortlisting for high-volume, cost-sensitive workloads that need a very large context window. Its benchmark evidence is thin; the blended score of 63.8 comes from a single independent benchmark, with an AI Index score of 62.9. That is not enough to rank it confidently against alternatives, so run it on a sample of your own tasks before committing production traffic.