OpenAI: GPT-6 Luna Pro (batch)

GPT-6 Luna Pro (batch) is a text model from OpenAI, identified on api14 as openai/gpt-6-luna-pro:batch. It is the same underlying model as GPT-6 Luna, served with reasoning.mode set to pro for higher-quality responses on complex tasks. The batch variant is intended for workloads where that higher-quality pro mode is acceptable, and it was released by the provider on 22 September 2026.

The model accepts text, image and file inputs, and it produces text output. Its context window is 1,050,000 tokens, and the maximum output is 128,000 tokens. Supported request parameters include max_tokens, response_format, structured_outputs, seed, tools, tool_choice, reasoning, reasoning_effort, include_reasoning and verbosity. Because reasoning is exposed as a parameter, you can control how much internal reasoning effort the model applies, and include_reasoning lets you decide whether reasoning content is returned alongside the final answer.

Those capabilities point to a fairly specific set of use cases. The large context window suits long documents, such as contracts, research papers, codebases or multi-file reports, where the model needs to reason across material that would not fit in a smaller window. Image and file inputs make it usable for tasks that mix scanned pages, diagrams or attachments with written instructions. Structured outputs, response_format and tool calling make it a reasonable fit for extraction pipelines, classification, form filling and agent-style workflows that need to call external functions. The reasoning controls are useful when a task needs careful multi-step analysis rather than a quick answer.

You call the model through api14's OpenAI-compatible API using the model id openai/gpt-6-luna-pro:batch. Because the interface follows the OpenAI chat completions shape, you send a request to the chat completions endpoint with that id in the model field, and you can pass any of the supported parameters in the same request body. Tools and tool_choice handle function calling, response_format and structured_outputs constrain the reply shape, seed supports reproducible sampling, and max_tokens caps the generated output. reasoning, reasoning_effort, include_reasoning and verbosity give you control over how the model reasons and how much it says.

One practical consideration is that pro mode spends far more than the standard mode, so the batch variant is best reserved for tasks where the extra reasoning quality matters. For simpler or high-volume work, the non-pro GPT-6 Luna may be a better fit. Also note that output is text only, so if you need generated images or audio, this model is not the right choice.