Weaviate through Squiid
Vector database with built-in vectorization modules and hybrid search. Weaviate is on the Squiid roadmap.
What Weaviate is
Weaviate is an open-source vector database that stores objects and their embeddings together in a schema you define. Vectorizer modules call an embedding provider for you at insert and query time, so a text field can be indexed without your application ever computing a vector, and generative modules can run a retrieval-augmented answer inside the database query itself. Hybrid search blends BM25 keyword scoring with vector similarity using a tunable weight, and multi-tenancy isolates collections per customer. Replication and backup are handled by the cloud service, and collections can be configured with different distance metrics per named vector.
In an AI-coded application Weaviate is attractive when you want the retrieval logic to live in one place rather than spread across your code. A query can filter by properties, blend keyword and semantic scoring, and return a generated summary in one round trip, which is a lot less glue for an agent to write and get wrong. The schema-first design also gives generated code something to validate against. Generative modules keep the prompt template next to the data it queries, which is easier to reason about than a prompt buried in application code.
Why connect it through Squiid
Weaviate Cloud is on the Squiid roadmap. When it lands, Squiid will provision the cluster, hold the API key and pass requests through https://api.squiid.io/v1/weaviate/... with Authorization: Bearer $SQUIID_API_KEY, with official clients working by base URL swap (gateway convention). Because vectorizer modules call a model provider, that provider can be another service on the same Squiid key, which means one credential covers both halves of the pipeline and both show up as line items on the same monthly invoice at list price.
- One account, one key, one bill, one dashboard. Weaviate sits beside every other service your project uses, on the same invoice and the same credit balance.
- Key custody. Squiid holds the Weaviate credentials. Your code carries
SQUIID_API_KEY, so WEAVIATE_URL, WEAVIATE_API_KEY, WEAVIATE_CLASS never land in a repository, a preview deployment or an agent’s context. - Metering you can see. Every call is counted per service and per day, so you know what Weaviate costs before the month ends.
- Pause on zero. When prepaid credits run out the gateway stops authorizing usage instead of running up a bill you did not fund.
- One rotation. Rotating the Squiid key cuts off every agent, worker and deployment at once, with no provider key to hunt down.
What you get
- A provisioned Weaviate cluster
- Vectorizer modules that embed on insert and query
- Hybrid BM25 and vector search with a tunable alpha
- Multi-tenancy for per-customer isolation
- Weaviate list pricing, no markup
How to connect Weaviate
One variable replaces the provider credentials this service would normally need. Requests go to the gateway and the official SDKs work by pointing their base URL at it (gateway convention).
# .env
# replaces WEAVIATE_URL, WEAVIATE_API_KEY, WEAVIATE_CLASS
SQUIID_API_KEY=sq_live_xxxxxxxxxxxxxxxxxxxxxxxx
# every request: https://api.squiid.io/v1/weaviate/...
# header: Authorization: Bearer $SQUIID_API_KEY
Add it in your dashboard
Open the Squiid catalog, add Weaviate and fund credits. Squiid provisions the project and keeps the provider keys.
Put the one key in your env
Add SQUIID_API_KEY to .env and delete WEAVIATE_URL, WEAVIATE_API_KEY, WEAVIATE_CLASS. Nothing else from Weaviate needs to exist in your project.
Point your agent at it
Claude Code, Cursor and Codex read the same variable and call https://api.squiid.io/v1/weaviate/. Agents lean on Weaviate's vectorizer modules so the application code inserts plain text and never handles embedding calls itself.
Pricing through Squiid
Weaviate Cloud charges based on stored dimensions and the service tier you choose, at the provider's listed price. Squiid passes that through at par: one dollar of prepaid credit is one dollar of Weaviate usage, with no markup and no per-request margin.
Weaviate has no subscription attached on Squiid today. If a plan is required for a feature you need, it passes through at the provider’s listed price with no Squiid fee.
Squiid adds no markup to provider prices. There is a free plan at $0 a month with a 15% fee when you top up credits, Solo at $19.97 a month with a top-up fee that starts at 8% and falls to 3.5% as your spend grows, Team from $29.97 a seat a month with the same ladder one point lower, and Custom with a rate of 3% or less. Credits are prepaid, so Weaviate usage stops when the balance reaches zero rather than producing an invoice you did not fund. Auto top-up with a cap keeps production running without handing anyone an open-ended card.
If you leave
Export: records, vectors and index settings are exported and re-imported into an index in your own Weaviate account. Squiid never owns your code, your schema or your domain, and the gateway speaks Weaviate's own API, so the client change is a base URL. The handover page lists what happens for every provider in the catalogue.
Works with every coding agent
Weaviate through Squiid is just an HTTP call with a bearer token, so every agentic coding tool can use it with the single key already in your environment:
- Claude Code
- Cursor
- ChatGPT
- Codex
- Grok
- Gemini CLI
- GitHub Copilot
- Windsurf
- Perplexity
- Devin
- Replit
- v0
- Lovable
- Cline
Vibe coding a feature on Weaviate usually means asking for it in plain language and letting the agent write the integration. Because the key is Squiid’s rather than the provider’s, it can do that without ever holding a credential that could be leaked, logged or committed.
Related services
Pinecone
Vector and searchManaged vector database for retrieval augmented generation at scale
Next upProvisionedQdrant Cloud
Vector and searchOpen-source vector search with rich payload filtering and quantization
RoadmapProvisioned COCohere
LLM APIsEnterprise models with strong embeddings, rerank and RAG tooling
RoadmapInstantOpenAI
LLM APIsGPT models, embeddings, images and realtime voice over one API
LiveInstant TYTypesense
Vector and searchOpen-source instant search with a managed cloud and vector support
RoadmapProvisionedQuestions people ask
Is Weaviate connectable through Squiid?
Not yet. It is on the roadmap as a provisioned managed cluster.
What is hybrid search good for?
Queries where an exact term matters, such as a product code or a name, alongside semantic similarity. The alpha parameter controls the blend.
Do I still need a separate embedding provider?
Weaviate can call one for you through a vectorizer module. That provider can be another service on the same Squiid key.
How is multi-tenancy handled?
Weaviate supports tenants within a collection, which keeps one customer's vectors physically separate from another's.
Will Squiid mark up Weaviate?
No. Cluster and usage cost pass through at the provider's listed price on one invoice.
Connect Weaviate with one key.
Weaviate stores objects with their vectors and can generate embeddings itself through model modules, with hybrid keyword and vector search and a GraphQL query interface. Planned for Squiid.