Chroma
EmbeddingFREE TIEROpen-source vector database — fast setup for RAG
Operational
All systems responding normally
Last checked 14/06/2026, 4:15:38 am
747ms response
Uptime History100.00% uptime
2026-06-07Today
Uptime
100.00%
Avg Latency
819ms
P95 Latency
1201ms
Fastest
448ms
Checks
150
Response Time
Last 60 checks448ms min819ms avg1552ms max
💰 Pricing
embedding-multilingualFREE
Embed: $0.1/1M
Open-source vector DB. Cloud: $0.10/1M embeddings + storage.
Free OSS; Cloud: free tier available
⚡ Rate Limits
free
Open-source vector DB. Self-hosted: no rate limits. Cloud: rate-limited per plan.
🤖 Models (1)
| Model | Task | Context | Vision | Tools | JSON |
|---|---|---|---|---|---|
| Multilingual Embeddings Vector DB with built-in embedding models. Not an LLM. | embedding | 8k | — | — | — |
Recent Checks
Showing last 15Operational
747ms14 June, 04:15 am
Operational
1185ms14 June, 03:42 am
Operational
683ms14 June, 03:04 am
Operational
1188ms14 June, 02:34 am
Operational
1253ms14 June, 01:54 am
Operational
588ms14 June, 01:18 am
Operational
700ms14 June, 12:37 am
Operational
787ms13 June, 11:48 pm
Operational
795ms13 June, 11:02 pm
Operational
890ms13 June, 10:22 pm
Operational
698ms13 June, 09:48 pm
Operational
1162ms13 June, 09:01 pm
Operational
1090ms13 June, 08:09 pm
Operational
962ms13 June, 07:08 pm
Operational
964ms13 June, 05:51 pm
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
Voyage AI
State-of-the-art embedding models for RAG and retrieval