Docs·API

Voyage AI

EmbeddingFREE TIER

State-of-the-art embedding models for RAG and retrieval

voyageai.com ↗Pricing →/api/v1/latency

Operational

All systems responding normally

Last checked 21/05/2026, 9:48:28 am

633ms response

Uptime History100.00% uptime

2026-05-16Today

Uptime

100.00%

Avg Latency

672ms

P95 Latency

982ms

Fastest

350ms

Checks

150

Response Time

Last 60 checks

350ms min672ms avg1141ms max

💰 Pricing

voyage-3FREE

Embed: $0.06/1M

voyage-3-lite: $0.02/1M

50M tokens/month free

⚡ Rate Limits

free

50M tokens/month free. Then $0.06/1M.

🤖 Models (1)

Model	Task	Context	Vision	Tools	JSON
Voyage 3 State-of-the-art embeddings for RAG.	embedding	4k	—	—	—

Recent Checks

Showing last 15

Operational

633ms21 May, 09:48 am

Operational

550ms21 May, 09:16 am

Operational

611ms21 May, 08:42 am

Operational

602ms21 May, 08:00 am

Operational

475ms21 May, 07:13 am

Operational

505ms21 May, 06:28 am

Operational

738ms21 May, 05:31 am

Operational

565ms21 May, 04:36 am

Operational

387ms21 May, 03:44 am

Operational

490ms21 May, 02:42 am

Operational

853ms21 May, 01:34 am

Operational

696ms21 May, 12:16 am

Operational

435ms20 May, 11:19 pm

Operational

865ms20 May, 10:12 pm

Operational

636ms20 May, 09:18 pm

API Quick Access

Health Latency Freshness Pricing Models

Other Embedding Providers

Cohere

Command R+, Embed v3 — enterprise RAG specialist

Pinecone

Managed vector database for semantic search + RAG

Weaviate

Open-source vector database — hybrid search, multi-modal

Qdrant

High-performance vector DB — built for production AI search

Chroma

Open-source vector database — fast setup for RAG

Visit Voyage AI →View Pricing ← All Providers