Cohere
EmbeddingFREE TIERCommand R+, Embed v3 — enterprise RAG specialist
Operational
All systems responding normally
Last checked 21/09/2026, 9:43:17 am
337ms response
Uptime History100.00% uptime
2026-09-19Today
Uptime
100.00%
Avg Latency
329ms
P95 Latency
416ms
Fastest
192ms
Checks
150
Response Time
Last 60 checks192ms min329ms avg795ms max
💰 Pricing
command-r-plusFREE
Input: $2.5/1MOutput: $10/1M
command-r: $0.15/$0.60
1000 API calls/month
embed-v3FREE
Embed: $0.1/1M
1000 calls/month
⚡ Rate Limits
free
RPM: 20
1000 API calls/month total on trial.
🤖 Models (1)
| Model | Task | Context | Vision | Tools | JSON |
|---|---|---|---|---|---|
| Command R+ RAG-optimised. Best for enterprise retrieval | llm | 128k | — | ✅ | — |
Recent Checks
Showing last 15Operational
337ms21 Sept, 09:43 am
Operational
365ms21 Sept, 09:34 am
Operational
280ms21 Sept, 09:21 am
Operational
273ms21 Sept, 09:09 am
Operational
285ms21 Sept, 08:52 am
Operational
195ms21 Sept, 08:42 am
Operational
338ms21 Sept, 08:34 am
Operational
317ms21 Sept, 08:22 am
Operational
360ms21 Sept, 08:09 am
Operational
389ms21 Sept, 07:53 am
Operational
340ms21 Sept, 07:42 am
Operational
313ms21 Sept, 07:34 am
Operational
318ms21 Sept, 07:21 am
Operational
318ms21 Sept, 07:09 am
Operational
381ms21 Sept, 06:52 am
Other Embedding Providers
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
Voyage AI
State-of-the-art embedding models for RAG and retrieval