Cloudflare Vectorize vs Upstash Vector

Cloudflare Vectorize is a globally distributed vector database for AI applications built with Cloudflare Workers. It supports semantic search, recommendations, classification, anomaly detection, and supplying context to large language models. Vectors can come from Workers AI models or services such as OpenAI. Workers connect to indexes through a Vectorize binding configured in Wrangler or the Cloudflare dashboard, while a REST API can insert and query vectors. Search results can reference images in R2, documents in KV, and user profiles in D1. Metadata filters support indexed string, number, and boolean properties, with up to 10 metadata indexes per index. Each index can hold up to 20 million vectors, with a maximum of 1,536 dimensions at 32-bit precision. Queries return up to 50 results with values or metadata, or 100 without them. Cloudflare lists a free plan and paid usage from $5/mo. The Workers Free plan includes stated monthly queried and stored dimension allowances. Cloud deployment is available through API and web access.

Upstash Vector is a serverless cloud vector database for applications that need vector search, including NLP, RAG, recommendations, image recognition, clustering and classification. It uses DiskANN for approximate nearest-neighbor queries and also lists FreshDiskANN as an index type. Developers can use its REST API and SDKs, with first-class Python and TypeScript support and additional SDKs for Go and PHP. Similarity options include Euclidean distance, cosine similarity and dot product. Vectors can carry metadata, and query filters can restrict matches using metadata expressions. Hybrid indexes combine dense semantic search with sparse exact-token search and fuse the results. Documented integrations include Vercel AI SDK, Flowise, LangChain, Langflow, LlamaIndex and LlamaParse. The pricing page lists a default top-k limit of 1,000, up to 48 KB of metadata and 1 MB of data per vector. The Free plan allows 10K daily queries or updates and up to 1 GB of data and metadata. Pay as You Go costs $0.40 a month, billed per 100K requests, with separate storage and bandwidth terms. Region availability varies by plan.