Which of these models does Mixpeek run today?

15 are hosted on Mixpeek as Ray Serve apps (Multilingual E5 Large Instruct, all-MiniLM-L6-v2, SigLIP Base patch16 224, InsightFace buffalo_l (SCRFD-10GF + ArcFace ResNet50 WebFace600K), InsightFace buffalo_sc (SCRFD-500MF + MobileFaceNet WebFace600K) and others). 13 are provider APIs Mixpeek calls by name. 35 can run as a custom plugin and do not run yet. 28 are blocked today; each page says why.

How is the default order decided?

By usage, the namespaces and collections that use each model, counted on 2026-11-06T13:42:25Z, then by how many templates use it, whether it runs today and whether we have our own evaluation.

What does unmeasured mean on a model?

We have not measured that model's cost or quality on our own image and data yet. Publisher benchmarks are linked from the model's sources and are not copied into the measured fields.

Can an agent read this catalog?

Yes. /models.json holds every record and /models/ .json holds one. They are the same records this page renders, generated from the catalog the Mixpeek server is built from.

How do I use a model in a namespace?

Open the model and deploy a template that already uses it, or add it to a new or existing namespace from the Designer in Studio. Inference is billed per unit you process, so a namespace is not billed for inference while it sits idle.

Models

Embedding, detection, classification, transcription and multimodal models: what each is good at, its inputs and outputs, and how it runs on Mixpeek.

For agents

Read every Mixpeek model record (inputs, outputs, license, how it runs, templates that use it) as JSON at https://mixpeek.com/models.json, or one model at https://mixpeek.com/models/<id>.json. No key needed.

Build with a model Model registry docs

Search: "convnext"

0 of 91 models

Sort:

No models match

Try a different search or clear the filters.

Or let Mixpeek choose

Not sure which model fits? Describe your data instead.

Say what your files are and what you want from them. Mixpeek writes the namespace for you, with the extractors, models and retrievers, checks it against the catalog and prices it before you apply it.

To go further, the manifest loop tries other models, settings and retriever pipelines, scores each one on labelled examples it holds back, and hands you the best as a manifest you can deploy.

How it works POST /v1/manifest/generate

Questions

Which of these models does Mixpeek run today?: 15 are hosted on Mixpeek as Ray Serve apps (Multilingual E5 Large Instruct, all-MiniLM-L6-v2, SigLIP Base patch16 224, InsightFace buffalo_l (SCRFD-10GF + ArcFace ResNet50 WebFace600K), InsightFace buffalo_sc (SCRFD-500MF + MobileFaceNet WebFace600K) and others). 13 are provider APIs Mixpeek calls by name. 35 can run as a custom plugin and do not run yet. 28 are blocked today; each page says why.
How is the default order decided?: By usage, the namespaces and collections that use each model, counted on 2026-11-06T13:42:25Z, then by how many templates use it, whether it runs today and whether we have our own evaluation.
What does unmeasured mean on a model?: We have not measured that model's cost or quality on our own image and data yet. Publisher benchmarks are linked from the model's sources and are not copied into the measured fields.
Can an agent read this catalog?: Yes. /models.json holds every record and /models/<id>.json holds one. They are the same records this page renders, generated from the catalog the Mixpeek server is built from.
How do I use a model in a namespace?: Open the model and deploy a template that already uses it, or add it to a new or existing namespace from the Designer in Studio. Inference is billed per unit you process, so a namespace is not billed for inference while it sits idle.

Hugging Face model directory

Directory pages for 428 public models. They are not in the catalog above, and Mixpeek does not run them as listed.