ToolPicker
Voyage AI

Voyage AI

25/100

Voyage AI (MongoDB) high-accuracy text embeddings.

voyageai.com

// scorecard · 25/100

verified 1mo ago
methodology →
Agent-readiness11/35
Agent registration (api_key)6/9
Public API5/5
OpenAPI spec0/9
MCP server0/9
llms.txt0/3
Reliability & performance0/15
Actively maintained
Production-ready0/4
Updated recently
Pricing2/13
Itemized public pricing0/6
Free tier / trial0/4
Free-tier generosity2/3
Docs & DX2/12
Docs quality
Public API2/2
Quickstart / examples0/2
Security & compliance6/12
SOC 26/6
ISO 270010/2
GDPR0/2
Security / trust page0/2
Openness4/10
Open source0/6
Open / un-gated API4/4
Company maturity0/3
Company size
Years operating

// rankings · cost per standard workload

#4 in Embeddings$2/ 100M tokens

voyage-3-lite $0.02/1M x100 = $2/mo (voyage-3.5 $6)

docs.voyageai.com

// overview

Voyage AI provides best-in-class embedding models and rerankers for supercharging search and retrieval over unstructured data. The models power RAG pipelines by producing embeddings that feed a vector DB, followed by a reranker to surface the most relevant context for an LLM. Available model families include general-purpose, domain-specific (finance, legal, code), and company-specific fine-tunes.

Best for: RAG retrieval quality on unstructured data

// security & compliance

SOC 2 ISO 27001 GDPR HIPAA

// features

  • High accuracy retrieval
  • Low dimensionality (3x-8x shorter vectors)
  • Low latency (4x smaller model)
  • Cost-efficient inference (2x cheaper)
  • Long context (32K tokens)
  • Modular plug-and-play with any vector DB and LLM