OpenAI's GPT-4O Mini-REALTIME Preview is an audio model capable of processing both audio and text inputs, with a notable context window of 128,000 tokens. It is genuinely best at handling audio input and output in real-time, also supporting function calling.
Input
Output
Context
128K
Max Output
4K
Parameters
-
Input Modalities
Output Modalities
Loading capabilities…
The creator's other models in the catalog, with their context, size and license where published.
Put this model beside its alternatives on the same evidence, or go back to the full catalog.
Answered from the entry's own fields: context, license, modalities, evidence, serving and the memory to self-host.
GPT-4O Mini-REALTIME Preview advertises a context window of 128,000 tokens, with a maximum output of 4,096 tokens in a single response. The figure is the creator's published maximum; a given host may serve less, and the gateway routes on what each host actually serves.
No. GPT-4O Mini-REALTIME Preview is a proprietary model (license: Proprietary): its weights are not distributed, and it runs only through Openai's own API or a host with access to it.
GPT-4O Mini-REALTIME Preview accepts Audio and Text and produces Text and Audio. The capabilities card on this page lists which API features each deployment honours, such as function calling and structured output, with the source each was checked against.
No published benchmark result for GPT-4O Mini-REALTIME Preview is in the catalog yet, so the model is shown as unmeasured. It is not ranked or estimated; the router treats it as unknown for every task until a suite measures it.
Not on the managed pool today; GPT-4O Mini-REALTIME Preview is listed for reference and comparison. Connect your own provider key or endpoint that serves it and the gateway runs it on your account, with routing decisions recorded the same way.
GPT-4O Mini-REALTIME Preview cannot be self-hosted: its weights are not distributed. It is used through an API, either Openai's own or the Inferbase gateway where it is served.
Fields collected from public registries, host APIs and benchmark publishers, each tagged with its source.
Last updated: Sep 11, 2026
One gateway in front of every model, with your policies applied and every decision on record. Start with $5 of credit and 5,000 routing decisions a month, no card required.