NEWVectors or files. Pick a path.Start →
    Provider APIGenerationVerified 2026-11-05

    GPT-4o mini

    gpt-4o-mini

    GPT-4o mini is a text and image language model (OpenAI API terms of use). Called on Mixpeek through the provider API.

    Mixpeek calls the provider's API by name. Provider terms apply.

    Use in a new namespaceAdd to an existing namespace Record as JSON

    New opens the Designer in Studio. For an existing namespace, open it in Studio and use its Designer tab.

    No demo for GPT-4o mini yet

    A video, image, slideshow or playground goes here once we record one on our own data.

    What it is good and bad at

    Best at
    Cheap short generations such as query expansion (query_expand's default expansion_model) and the fallback chat model of the universal inference endpoint.
    Worst at
    Video and audio input (needs another model); the stage's 3 s query_expand budget leaves little room for slow provider responses.
    Task
    Generation
    Input
    Text, Image
    Output
    Text, Structured data
    Use cases
    Tagging, Captioning

    Templates that use it

    No template uses this model yet. Browse templates.

    Input and output

    Input

    text
    chat messages
    image
    image URLs (universal__api converts base64 media to data URIs)

    Output

    text
    chat completion

    How Mixpeek wires it

    Extractors
    None today
    Feature URIs
    None today
    Vector indexes
    None
    Retriever stages
    query_expand, llm_enrich
    Combines with
    • query_expand (gpt-4o-mini) -> several feature_search calls fused
    • llm_enrich with legacy inference_name openai:gpt-4o-mini resolves to universal/api with model gpt-4o-mini

    How it runs

    Status
    Provider API Provider API. universal__api uses it when a request names no model (params.get('model', 'gpt-4o-mini')); query_expand calls it through CentralLLMService.
    Serve apps
    universal__api
    Runtime
    OpenAI chat completions (shared.models.llm OpenAIProvider; universal__api _handle_chat)
    Weights
    Provider API, no remote code
    Parameters
    Not recorded
    Size on disk
    Not recorded
    Preprocessing
    Stage prompt templates ({{QUERY}}, {{NUM_EXPANSIONS}} for query_expand).
    Postprocessing
    Text, parsed into expansions or enrichment fields.
    Serving
    realtime
    Hardware
    Provider API

    Scale to zero

    Minimum replicas
    0
    Maximum replicas
    6
    Idle timeout
    600 s
    Memory
    Not recorded
    CPUs
    0.1
    GPUs
    0
    Cold start, node warm
    Not recorded
    Cold start, new node
    Not recorded

    Measured cost

    Unmeasured

    Billed per token by OpenAI; no committed measurement.

    Our evaluations

    Unmeasured

    We have not evaluated this model on our own data yet. Publisher results are in the sources below.

    Questions

    What is GPT-4o mini best at?
    Cheap short generations such as query expansion (query_expand's default expansion_model) and the fallback chat model of the universal inference endpoint.
    What are the limits of GPT-4o mini?
    Video and audio input (needs another model); the stage's 3 s query_expand budget leaves little room for slow provider responses.
    Can GPT-4o mini be used commercially?
    Yes. Paid OpenAI API under OpenAI's terms; tenants can bring their own key.
    How does GPT-4o mini run on Mixpeek?
    Provider API. universal__api uses it when a request names no model (params.get('model', 'gpt-4o-mini')); query_expand calls it through CentralLLMService.