Managed vector search — free tier

Search for meaning, not for words

Vela indexes your embeddings and answers by similarity in milliseconds. One single API for semantic search, RAG and recommendation, up to a billion vectors.


p99 latency
0 ms
Target recall
0.2 %
Maximum dimensions
0
Deployment regions
0

A keyword index only finds what you already knew how to name. It ignores synonyms, rephrasings, other languages.

A vector index compares meanings. Same query, but it brings back what you were looking for.

A vector index, without the cluster

You stay in control of your models and your data. We take care of indexing, graph traversal and holding latency in line.

  • One single API

    Create an index, send your vectors, query them. No infrastructure to size or operate.

  • Predictable latency

    The p99 stays under 12 ms on a billion-vector index, including when a query carries a filter.

  • Metadata filters

    Restrict a search to one customer, one language or one time window. The filter applies during graph traversal, not after.

  • Queryable writes

    An inserted vector becomes searchable within seconds. No reindexing window to schedule.

  • Data residency

    The region is chosen when you create the index, from eight options. Multi-region replication stays optional.

  • Your models, your vectors

    Up to 4096 dimensions, cosine similarity or dot product. Vela imposes no embedding model.

Two neighbouring vectors, two neighbouring ideas

An embedding places a text, an image or a product in a space of several thousand dimensions. Two pieces of content about the same thing end up side by side in it.

Vela walks that space with an HNSW graph and returns the k nearest neighbours of a query, without ever comparing it to the other billion vectors.

From the index to the first query

Four steps, in this order, to go from an empty index to answers in production.

  1. 01

    Indexing

    Create an index by setting its dimensions, its similarity measure and its storage region.

    • Up to 4096 dimensions
    • Cosine or dot product
    • Eight regions
  2. 02

    Ingestion

    Send your vectors in batches, along with the metadata your filters will later rely on.

    • Batch import
    • Typed metadata
    • Isolated namespaces
  3. 03

    Query

    Ask for the k nearest neighbours of a vector, with or without a filter, and get the scores back.

    • k-NN search
    • Composable filters
    • Similarity scores
  4. 04

    Operations

    Track recall and latency in production, then tune the graph parameters if you need to.

    • p50 and p99 latency
    • Per-query recall
    • Live reindexing

Three deliberate trade-offs

A vector database is judged on what it gives up. Here is what we chose.

The p99 matters more than the average. An index that answers in 3 ms nine times out of ten, then in 400 ms on the tenth, is unusable behind a conversational assistant.

Latency The p99, not the average

A highly selective filter collapses recall long before it hurts latency. We filter during graph traversal rather than after, so the neighbour list stays relevant.

Recall Filtering without degrading

A 1536-dimension vector takes roughly 6 KB in memory, graph included. Quantization cuts that cost, and a final reranking pass recovers the precision lost.

Cost Memory per vector

Your first index in five minutes

The Discovery tier is free: one index, one million vectors, no credit card. You move up a tier when your queries call for it, with no reindexing.