# Vendor Catalog

> Every third-party vendor Divinci can run a job on — vector stores, embeddings, parsers, search, scraping, voice, fine-tuning and de-identification — with what each costs you in credentials and how much of our own platform runs on it.

Divinci is a **multi-vendor platform**. Almost every step of the pipeline —
embedding a chunk, storing a vector, parsing a PDF, searching the web, speaking
a reply, fine-tuning a model, stripping PII — is a swappable *tool*, and most
steps have several vendors behind them.

There are **{catalog.toolCount} such tools** today, excluding the ~160
conversational models (those have their own live
[Model Catalog](/guides/models/)).

## Why you would care

| If you… | Look at |
| --- | --- |
| already pay a vendor and want to use that account | the **BYOK** column — attach your key and the tool becomes selectable |
| want to start with nothing | the **Divinci-managed** rows — usable with no key of your own |
| are choosing between two options | the **Divinci usage** column: what we actually run in production |

## The categories

<CardGrid>
  <LinkCard title="RAG & Vector Stores" href="/vendors/rag/" description="Where chunks live and how they are retrieved — 14 stores, from Cloudflare Vectorize to Neo4j." />
  <LinkCard title="Embeddings" href="/vendors/embeddings/" description="The models that turn chunks into vectors, and why mixing them breaks search." />
  <LinkCard title="Parsing & Chunking" href="/vendors/parsing/" description="Turning a PDF, a page or a record into chunks worth embedding." />
  <LinkCard title="Search & Scraping" href="/vendors/search-scraping/" description="Web search providers and the scraping cascade." />
  <LinkCard title="Voice & Audio" href="/vendors/voice/" description="Text-to-speech, transcription, diarization, voice cloning and voiceprints." />
  <LinkCard title="Fine-tuning" href="/vendors/fine-tuning/" description="Where a fine-tune actually trains — Vertex, OpenAI, Cloudflare LoRA, Modal, Tinker, AWS." />
  <LinkCard title="De-identification" href="/vendors/de-identification/" description="Presidio and Stanford NER, and the one that fails closed." />
  <LinkCard title="Red-teaming & Evals" href="/vendors/red-teaming/" description="First-party, and deliberately so — TrustBench probes, scorers and attested runs." />
</CardGrid>

## How vendor selection works

**Every tool has an auth provider.** A tool is selectable when credentials for
its provider are available — either Divinci's (for the runtimes we pay for) or
yours, attached as a
[Provider Key (BYOK)](/server/byok-and-skills/).

**Credentials are per workspace, and validated on save.** Each provider declares
a JSON-schema credential shape and a live validation call, so a bad key is
rejected at the point you paste it rather than at the point a customer asks a
question.

<Aside type="caution" title="A vector's tool is fixed at creation">
Vector store and embedding model are properties of the vector, not of the query.
Re-pointing an existing vector at a different embedding model does not
re-embed anything — and vectors from two models are not comparable even at the
same dimensionality, so similarity search degrades quietly rather than failing.
Create a new vector and re-ingest.
</Aside>

## About the numbers on these pages

The **Divinci usage** column is generated, not asserted: a weekly job asks the
production API for aggregate counts and commits them into these pages. It
carries **counts only** — no workspace, release, customer or corpus is
identified, and the endpoint that produces it is a `$group`-and-`$sum` with
nothing else in the projection.

Two honest caveats about reading it:

- **Zero does not mean bad.** Several vendors are supported because a specific
  customer asked for them; the rest of the platform has no reason to use them.
- **A count is a count of *configurations*, not of traffic.** A vector store
  used by one enormous corpus and one used by two hundred small ones look
  similar here.

{usage.generatedAt
  ? <p><small>Last refreshed {new Date(usage.generatedAt).toISOString().slice(0, 10)}.</small></p>
  : <p><small>The first weekly refresh has not run yet, so usage columns read <code>—</code>.</small></p>}