OpenAI: GPT-5.4 (batch)

GPT-5.4 (batch) is a text generation model from OpenAI, listed on api14 under the model id openai/gpt-5.4:batch. It belongs to OpenAI's GPT-5.4 line, which the provider describes as its latest frontier model and as a unification of the Codex and GPT lines into a single system. The batch variant is the version you call through api14's OpenAI-compatible endpoint.

The model accepts text, images and files as input, and it returns text. Its context window is 1,050,000 tokens, and the maximum output is 128,000 tokens. That combination of a very large context and a large output budget means you can supply long documents, codebases or mixed text and image material in a single request and still leave room for a substantial generated response.

Because it handles text, images and files together, the model suits work where the input is not a single clean string. Document analysis and summarisation over long files, question answering grounded in a set of uploaded references, and extraction of structured data from reports or scanned material are all natural fits. The reasoning and tool parameters make it usable for agent style workflows, where the model decides when to call a function and how much internal reasoning to spend. The large output ceiling also helps for tasks that produce long artefacts, such as detailed reports or extended code changes, rather than short answers.

To call it, send a request to api14's OpenAI-compatible chat completions endpoint with the model id openai/gpt-5.4:batch. The supported request parameters are include_reasoning, max_tokens, reasoning, reasoning_effort, response_format, seed, structured_outputs, tool_choice, tools and verbosity. In practice, tools and tool_choice cover function calling, response_format and structured_outputs cover JSON and schema constrained output, seed supports reproducible sampling, and reasoning, reasoning_effort, include_reasoning and verbosity control how much reasoning is exposed and how the model paces its effort.

Keep the output limit in mind: 128,000 tokens is generous but finite, so tasks that need to emit more than that in one pass have to be split. The model outputs text only, so anything requiring generated images or audio needs a different model. If your workload is small, latency sensitive and does not benefit from a million token context or from reasoning controls, a lighter text model may be a better fit.