BudgetVec is now in public beta — deploy billion-scale vector search on Cloudflare for $0.015/GB. Get started →

search every vector
at a fraction
of the cost

BudgetVec is a multi-tenant vector search platform built on Cloudflare Workers. SPTAG indexing, RaBitQ quantization, and the Pufferfish 3-tier cache deliver sub-10ms queries at 32× compression.

<10ms
Query latency (p50)
~90% less
Storage cost
32×
Compression ratio
6
Regions

Trusted by developers building the next generation of AI applications

Startup A
Startup B
Startup C
Startup D
Startup E

Estimate your cost

See how much you'd pay with BudgetVec compared to traditional vector databases.

10K100M
1001M
10010M

BudgetVec estimated monthly cost

$3.42
Storage (0.09 GB)$0.00
Write operations$1.35
Read operations$1.08
Worker compute$0.99

Estimated savings vs. traditional vector DB

88% less

~$28.32/mo on a comparable managed service

Performance at this scale

<10ms
p50 latency
<25ms
p90 latency
<50ms
p99 latency

What developers say

BudgetVec gave us sub-10ms vector search at 1/10th the cost of Pinecone. The Cloudflare Workers architecture means zero cold starts.
Alex Chen
CTO, AI Startup
The hybrid BM25 + vector search is exactly what we needed. One API call, perfectly ranked results combining semantic and keyword matching.
Maria Santos
Lead Engineer, Search Co
Multi-tenant isolation out of the box was a game-changer. Each of our customers gets their own namespace with complete data separation.
James Park
Founder, SaaS Platform

Limits & performance

Observed performance from real workloads. Limits are enforced per tenant plan.

MetricObservedLimit
Max namespaces per tenant1,000+Plan-dependent
Max vectors per namespace1B+Plan-dependent
Max vector dimensions4,0964,096
Max batch size (upsert)1,000 rows1,000 rows
Max query top_k1,00010,000
Max attribute size64 KB100 KB
p50 query latency<10ms-
p99 query latency<50ms-
Write throughput10K rows/s-