OpenAI: GPT Mini Latest

GPT Mini Latest is a text model from OpenAI, published under the model id ~openai/gpt-mini-latest. The name is literal: this endpoint always redirects to the latest model in the GPT Mini family, so you are not pinning a specific snapshot but tracking whatever OpenAI currently serves as the newest Mini release. The provider release date for this entry is 2026-04-27, and the knowledge cutoff is 2025-08-31.

The model accepts text, image and file inputs, and it produces text output only. Its context window is 400,000 tokens, with a maximum output of 128,000 tokens, which leaves substantial room for long inputs alongside long generations. Supported request parameters include max_tokens and max_completion_tokens for output length, response_format and structured_outputs for controlled output shapes, tools and tool_choice for function calling, seed for reproducibility, and reasoning, reasoning_effort, include_reasoning and verbosity for tuning how much reasoning work the model does and how much of it is surfaced.

Those capabilities point to a fairly wide set of practical uses. Long documents, codebases or transcripts fit comfortably inside the 400,000 token window, so summarisation, question answering over large inputs and multi-document comparison are natural fits. Image and file inputs make it usable for tasks that mix screenshots, diagrams or uploaded documents with text instructions. Structured outputs and tool calling suit extraction pipelines, form filling, classification and agent style workflows where the model must return machine readable results or call external functions. The reasoning controls let you dial effort up for harder analytical tasks or down for simple, high volume ones.

You call it through api14's OpenAI-compatible API using the model id ~openai/gpt-mini-latest, so existing OpenAI SDKs and clients work with only a base URL and key change. In the request body you can set the parameters listed above, including max_tokens or max_completion_tokens, response_format, structured_outputs, tools, tool_choice, seed, reasoning, reasoning_effort, include_reasoning and verbosity. Because the id redirects to the latest Mini model, behaviour can shift over time as OpenAI updates the family; if you need strictly reproducible outputs across releases, pin a dated snapshot where one is available. For tasks that need output modalities other than text, this model is not the right fit, since it returns text only.