NEWMVS for embeddings. Managed for files. Both on object storage.Vectors or files. Pick a path.Start →

Start here

Vector Store (MVS)

Bring your own vectors. Dense, sparse, and BM25 search on object storage.

Managed Indexing

Connect a bucket and auto-extract scenes, faces, OCR, transcripts, and embeddings.

Build

Compose multi-stage search in <100ms: filter, join, rerank.

Feature Extractors

Typed pipelines for faces, scenes, transcripts, OCR, fingerprints.

S3, GCS, R2, Mux, LangChain, MCP, and more. Connect your stack.

Generate and store embeddings from 50+ models, then search them.

By Industry

Map, search, and reuse the moments that perform. Plugs into iconik & Mux.

Talent search, brand safety, creative analytics.

Scene search, recommendation, archive access.

Visual search, PDP enrichment, catalog QA.

Lecture search, transcript Q&A, content safety.

View all solutions →

By Use Case

Face & Person Search

Find anyone across video libraries in milliseconds.

IP & Copyright Detection

Logos, songs, faces: one pipeline, one report.

Visual Taste & Recs

Scene-similarity ranked recommendations with RL.

Brand & Ad Safety

Pre-publish content screening at bid-time speeds.

View all use cases →

Build & evaluate

API reference, SDKs, recipes, and architecture guides.

Complete use cases as namespace configurations, with the outcome and the proof.

Browse supported HuggingFace models by task and modality.

Mixpeek vs. Pinecone, Weaviate, Twelve Labs, more.

See what teams are building with Mixpeek.

Learn

Best-of comparisons: vector DBs, embedding models, moderation APIs.

Vendor-neutral deep dives on perception, retrieval, and embeddings.

Launches, deep dives, and field notes from our engineers.

Papers behind multimodal search (MUVERA, SAM 3, and more) explained.

Every term you need: embeddings to re-rankers.

Videos, diagrams & university →

Mission, team, and the multimodal vision.

We're hiring across research, infra, and design.

Talk to sales, support, or press.

45-min working session on your data: leave with a running notebook.

Sign in Request Demo Get started →

Fill Mask Models

Browse AI models for multimodal decomposition and recomposition pipelines: plug any model into your extractors.

340 models available

Run models on your own files, free Schedule Demo Read Documentation

Showing 1-24 of 340 models

Fill Mask

google-bert/bert-base-uncased

46.5M

3,326

transformers

Fill Mask

FacebookAI/xlm-roberta-base

21.9M

914

transformers

Fill Mask

FacebookAI/roberta-base

7.7M

657

transformers

Fill Mask

distilbert/distilbert-base-uncased

7.3M

1,438

transformers

Fill Mask

FacebookAI/roberta-large

6.5M

319

transformers

Fill Mask

microsoft/mdeberta-v3-base

4.7M

239

transformers

Fill Mask

answerdotai/ModernBERT-base

4.6M

1,097

transformers

Fill Mask

google-bert/bert-base-multilingual-uncased

4.1M

160

transformers

Fill Mask

google-bert/bert-base-cased

3.6M

371

transformers

Fill Mask

FacebookAI/xlm-roberta-large

3.3M

530

transformers

Fill Mask

microsoft/deberta-v3-base

2.9M

441

transformers

Fill Mask

biohub/ESMC-6B

2.7M

32

transformers

Fill Mask

emilyalsentzer/Bio_ClinicalBERT

2.2M

440

transformers

Fill Mask

google-bert/bert-base-multilingual-cased

1.9M

603

transformers

Fill Mask

neuralmind/bert-large-portuguese-cased

1.6M

74

transformers

Fill Mask

distilbert/distilroberta-base

1.5M

180

transformers

Fill Mask

microsoft/BiomedNLP-BiomedBERT-base-uncased-abstract

1.3M

96

transformers

Fill Mask

facebook/esm2_t33_650M_UR50D

1.2M

89

transformers

Fill Mask

microsoft/deberta-v3-large

1.2M

287

transformers

Fill Mask

albert/albert-base-v2

966K

148

transformers

Fill Mask

almanach/camembert-base

956K

104

transformers

Fill Mask

Musixmatch/umberto-commoncrawl-cased-v1

763K

19

transformers

Fill Mask

google-bert/bert-large-uncased

756K

148

transformers

Fill Mask

answerdotai/ModernBERT-large

745K

481

transformers

...

1 / 15

Previous

Connectors

Next

Retrievers

What's new in models

All models

Every model page in one place, 390 in total.