The multimodal warehouse for AI

    Turn any data
    into answers.

    Your AI agents need to understand more than text. Mixpeek turns video, images, audio, and documents into searchable intelligence, with one pipeline instead of many.

    Try it on your files Index once. Query every way.
    1. 01 Connect
      Your files
    2. 02 Understand
      Every modality
    3. 03 Ask
      Anything
    10 videos indexed
    00:12.4
    Library
    10 videos · 977 moments
    Featured case study

    A performance-video agency maps the creative DNA of its entire ad library: search any moment, cluster what works, and reuse the winners. See how

    Use Mixpeek from your agent
    Files Understand Structure Use

    Every file becomes data you can query.

    Mixpeek reads each file for what's in it: faces and objects in a frame, the layout of a document, who is speaking in a recording. It stores what it finds as fields your software and your agents can search, filter, rank and join.

    Hover or tap a card to preview the search it powers.

    Person walking past a storefront, with face, body, and handbag detectedPerson · 0.97Face · 0.95Handbag · 0.92Video · 00:04:12
    scene caption

    “A woman carrying a tan tote bag walks past a red storefront.”

    transcript · “…meet me at the corner in five.”

    search
    A printed resume with header, body, chart, and signature regions detectedHeaderChartBodySignaturePDF · resume.pdf
    layout extraction

    Header, body, charts, and signature detected as typed regions.

    OCR · 1 header · 3 sections · 1 signature

    search
    A studio microphone, with audio diarized into speaker segments
    Speaker A
    Speaker B
    Speaker A
    match · “limited time offer”
    speaker diarization

    Who spoke when, aligned to the transcript and the timeline.

    audio · 2 speakers · matched at 00:01:30

    search
    View the extractors that produce these features
    See it working

    Pick a job and watch it run on real data.

    Each template is a working pipeline for one job, from moderating footage to finding one person across an archive. Open one to see what it finds, then deploy the same pipeline on your own bucket from Studio.

    Namespace

    Sources, buckets, collections, and retrievers ship together.

    Manifest

    One YAML file mirrors the rendered flow diagram.

    Evaluation

    Thresholds and review rules are attached to the template.

    Browse templates Retriever templates
    A camera operator silhouetted against a lit setScene · 0.91Camera · 0.89Video · footage.webpillustrative
    SearchMedia

    Footage Intelligence at Archive Scale

    Find the take in an archive nobody has watched end to end.

    production_id
    the key one team groups by
    job_id
    the key the other team groups by

    Pexels / Wolrider YURTSEVEN

    Two people filming a piece to camera with a ring light on a tablePerson · 0.94Product · 0.87Video · ad_00412illustrative
    OrganizeAdvertising

    Creative DNA for Ad Archives

    Search an ad archive by what is actually in the creative.

    brand
    brand_slug carried on every document
    segments
    per-scene, each one searchable

    Pexels / ANTONI SHKRABA production

    A close-up interview frame with one face in shotPerson · 0.92Face · 0.95Video · 00:01:07illustrative
    ModerateSafety and compliance

    Video Moderation Extraction Foundation

    Cut raw footage down to the subset you can defend training on.

    age gate
    flagged for under-18 review
    decision
    routed to a person, with its reason

    Pexels / Ron Lach

    A video editing timeline with clip thumbnails on the video track and an audio waveform belowScene · 0.92Transcript · 0.89Video · scene_0007illustrative
    ClassifyAdvertising

    Contextual video match

    Place against the scene an article is actually about.

    segments
    cut where the scene changes, each embedded alone
    match
    article text against the scene, not the whole file

    Pexels / Alex Fu

    Two people at a wall-mounted touchscreen, one reaching toward the display while the other watchesParticipant · 0.93Screen · 0.90Session · clinic_04illustrative
    SearchMedia

    UX session analysis

    Ask one question across every session and get every participant's answer.

    task
    boundaries taken from the moderator's own marks
    roll-up
    grouped on participant_id, so nobody is missing

    Pexels / Darlene Alderson

    A four-camera RTSP monitoring wall with processing badges, verdict fields and an alert stripRTSP Live Monitoring Wallillustrative
    MonitorSafety and compliance

    RTSP Live Monitoring Wall

    Turn always-on RTSP cameras into a searchable monitoring wall where quiet footage is skipped before extraction, kept segments carry gate verdicts, and email alerts fire from retriever results.

    Mixpeek RTSP demo wall, ns_5349052a7f, 2026-09-08; camera stills from Pexels (Artem Zhukov, Darya Sannikova, Garrison Gao, Oscar Portan)

    A performer alone in a stage spotlightPerson · 0.96Face · 0.94Video · 00:02:41illustrative
    SearchRetriever template

    Cast Identification

    Give it one reference photo and every appearance of that person comes back.

    face_id
    cast_0417, matched across the library
    scene
    solo, stage-lit

    Pexels / Tima Miroshnichenko

    A designer pinning reference photos to a mood boardPerson · 0.95Reference · 0.88Image · ref_2208illustrative
    SearchRetriever template

    Creative Lineage Search

    Trace where a look came from, across work already in your library.

    concept
    mood board, pinned reference
    lineage
    3 earlier campaigns share it

    Pexels / Ron Lach

    A designer reviewing printed campaign layouts at a deskAsset · 0.97Layout · 0.90Asset · print_q3_07illustrative
    ClassifyRetriever template

    Brand Compliance Checker

    Score every asset against your brand criteria before it ships.

    brand score
    0.82 against your rubric
    flagged
    accent colour outside the palette

    Pexels / George Milton

    A family watching television together in a living roomFace · 0.93Person · 0.91Video · 00:00:18illustrative
    ClassifyRetriever template

    Contextual Ad Targeting

    Place ads against what the content means, with nothing tracking the viewer.

    category
    IAB18, family and home
    signals used
    the content, and nothing about the viewer

    Pexels / Ketut Subiyanto

    A storyboard sketched in pen on a production deskPanel · 0.89Frame · 0.84Image · board_14illustrative
    RankRetriever template

    Storyboard Scene Builder

    Hand it a brief and get back the scenes that fit, in an order you can build from.

    brief
    three-beat opener
    returned
    scenes already in build order

    Pexels / Thijs van der Weide

    A single ceramic vessel on a plain backgroundObject · 0.98Image · sku_8841illustrative
    SearchRetriever template

    Visual Product Search

    Shop by picture: a photo in, visually similar catalogue items out.

    embedding
    image and text in one index
    returns
    catalogue items ranked by look

    Pexels / Tara Winstead

    12 templatesHover to stop the scrollSee all
    Discovered structure

    "What concepts exist in my data that nobody has labeled yet?"

    Mixpeek groups your files with no labels and builds the taxonomy for you. Every search and correction sharpens it.

    Explore clustering
    Your files, unlabeled
    Hands unboxing a small item from a package with crinkle paperHands opening a white package to reveal the contentsOpening a cardboard box with tissue-wrapped contents
    Cross-modal joins

    One query across every modality.

    Mixpeek lines up what's seen, said and shown at the same moment, so an agent gets the exact clip. Switch a feature off to see what each one adds.

    How joins work
    “Find the moment our CEO said guidance while the slide read Q4 outlook”
    ⨝ joined
    earnings_call.mp4 · 00:12:041 exact match

    The CEO says “guidance” as the slide behind her reads “Q4 outlook.”

    Quickstart

    One install. Two paths.

    Connect your files and Mixpeek builds the index. Already have embeddings? Bring them instead.

    Install
    pip install mixpeek
    Managed quickstart

    Connect your files

    Start with your files Read Managed docs
    # pip install mixpeek
from mixpeek import Mixpeek

mp = Mixpeek(api_key="YOUR_KEY")

collection = mp.collections.create(
    name="media_objects",
    source="s3://media/**/*",
    feature_extractors=[
        {"type": "visual_embedding"},
        {"type": "transcription"},
        {"type": "ocr"}
    ]
)

retriever = mp.retrievers.create(
    name="media_search",
    collections=[collection.id],
    stages=[{"type": "hybrid_search"}, {"type": "rerank"}]
)

results = retriever.search(
    "Find clips where customers discuss pricing"
)
    01Your bucket
    02Managed extraction
    03Agent retrieval
    Founded by engineers from
    MongoDBBerkeleyNVIDIAEtsyAmazon Web ServicesEquinixIAB Tech Lab
    Enterprise-ready
    SOC 2-ready Encrypted at rest BYO-Cloud Self-hosted option Audit trails SSO / SAML
    Pricing

    From $25/mo. Usage-based everything.

    Two products, one model: a flat monthly plan fee, with usage billed on top at the same published rates. MVS is priced by the vector, Managed by the unit of content.

    MVS
    $25/mo plus usage

    Bring your own embeddings and pay by the vector. Dense, sparse, and BM25 search on your own object storage. Build starts at $25/mo with up to 1M vectors; Scale ($250/mo) covers 25M.

    Start with MVS
    Managed
    $25/mo plus usage

    Bring raw files and pay per unit of content, such as video by the minute and images by the thousand. Build includes $10 of processing a month and covers 100K objects; Scale ($250/mo) includes $100 and covers 1M.

    Start with Managed
    Enterprise
    Custom

    Dedicated infrastructure, self-hosted options, SSO, SLA, security reviews, and hands-on architecture support.

    Talk to us
    See full pricing
    FAQ

    Common questions.

    What does Mixpeek do?

    Mixpeek understands what's inside your files and turns that understanding into data your software can use. It reads video, images, audio and documents where they already live, in S3, GCS or any S3-compatible bucket, and extracts faces, scenes, objects, speech, on-screen text and document layout. Your application then searches, classifies, filters, ranks and moderates that data through one API.

    Do I have to move my data?

    No. Mixpeek reads from your existing S3, GCS, R2, Azure, or S3-compatible bucket. Your storage stays the system of record, and nothing leaves your cloud.

    How fast is retrieval?

    Hybrid queries (dense, sparse, and BM25) return in well under 100ms p95, even with vectors persisted on object storage rather than held in RAM.

    Do I need embeddings to start?

    No. Bring your own vectors with MVS, or point Managed at raw files and it generates embeddings and features for you.

    What can Managed extract?

    Faces, scenes, transcripts, OCR, labels, and embeddings from video, images, audio, PDFs, and documents, all indexed at the object level.

    Can I self-host?

    Yes. Deploy in your own cloud (BYO-Cloud) with encryption, role-based access, SSO, audit trails, and namespaces. We hold no SOC 2 or HIPAA certification today; see mixpeek.com/trust.

    How does pricing work?

    Both MVS and Managed start at a $25 monthly plan fee, with usage billed on top. MVS bills vectors stored, storage, writes and queries. Managed includes $10 of processing a month on Build, then bills extraction, embedding, indexing and retrieval per unit of content.