// scorecard · 35/100
verified 1mo agoAgent-readiness14/35
Agent registration (api_key)6/9
Public API5/5
OpenAPI spec0/9
MCP server0/9
llms.txt3/3
Reliability & performance0/15
Actively maintained—
Production-ready0/4
Updated recently—
Pricing6/13
Itemized public pricing6/6
Free tier / trial0/4
Free-tier generosity—
Docs & DX2/12
Docs quality—
Public API2/2
Quickstart / examples0/2
Security & compliance8/12
SOC 26/6
ISO 270010/2
GDPR0/2
Security / trust page2/2
Openness4/10
Open source0/6
Open / un-gated API4/4
Company maturity0.5/3
Company size0.5/2
Years operating—
// rankings · cost per standard workload
#2 in Rerankers$0.25/ 1k rerank searches
zerank-2 $0.025/1M tokens x10M = $0.25/mo (per-token)
zeroentropy.dev/pricing// overview
ZeroEntropy trains state-of-the-art rerankers (zerank-2 and variants), embeddings (zembed-1), and custom models for production AI systems. Models are lightweight and focused on retrieval/RAG accuracy and low latency where generalist models fall short. Solutions target industries including legal, healthcare, finance, and e-commerce with options for on-prem and enterprise SLAs.
Best for: production AI systems and Search/RAG pipelines needing high-accuracy reranking and embeddings
// pricing
zerank-2$0.025 / MM Tokens
- Ratelimits: 2,500,000 UTF-8 bytes per minute
- Weights on HuggingFace
- Slack community support
zembed-1$0.050 / MM Tokens
- State-of-the-art embedding model
- Weights available upon request
- White glove fine-tuning and evaluation
ze on-premContact Us
- Model licensing and deployment
- White glove and priority support
- Optional evaluations and fine-tuning
Search API Pay-As-You-GoUsage-Based
- OCR: $1.75 / 1,000 pages
- Indexing: $0.50 / MB
- Storage: $0.10 / MB / month
- Queries: $1.50 / TB queried
- Reranking: $0.025 / MM tokens
- Embeddings: $0.05 / MM tokens
EnterpriseContact Us
- Volume discounts
- On-prem
// security & compliance
✓ SOC 2✗ ISO 27001✗ GDPR✗ HIPAA
// features
- zerank-2 reranker
- zembed-1 embedding model
- context compression
- query rewriting
- fine-tuning
- on-prem deployment