OpenAI: GPT-6 Luna (batch)

GPT-6 Luna (batch) is an OpenAI model that accepts text, image, and file inputs. It offers a context window of 1,050,000 tokens and can generate up to 128,000 tokens in a single completion, which suits long documents and large multi-file inputs. It supports tool calling and reasoning. Structured output support is not listed, so confirm it before building schema-dependent pipelines. At $0.05 per million input tokens and $0.25 per million output tokens, its per-token cost is low enough to make it a candidate for high-volume workloads where price drives the decision. The trade-off is evidence: there is no independent benchmark coverage yet, so its quality relative to alternatives is unproven. Shortlist it for cost-sensitive, long-context, or tool-using tasks, and run your own evaluations on representative data before committing production traffic to it.