Offering overview
Retrieval infrastructure for AI applications is the whole business here: a managed service that stores vectors and metadata, scales automatically, and answers similarity, hybrid and full-text queries without customers running servers. Hosted inference adds embedding models (llama-text-embed-v2, multilingual-e5-large, pinecone-sparse-english) and rerankers (bge-reranker-v2-m3, pinecone-rerank, cohere-rerank), so a RAG pipeline can be assembled from one API. An Assistant product packages document ingestion and chat on top. Indexes run on AWS, Google Cloud and Azure in a choice of regions, with Enterprise customers able to deploy Bring Your Own Cloud inside their own account and VPC, use private endpoints, customer-managed keys, SCIM and HIPAA controls. Typical users range from solo developers prototyping semantic search to enterprises operating production agents. A free Starter tier includes 2 GB of storage and monthly read/write unit allowances. Paid plans begin with Builder at a flat $20 per month, Standard requires $50 per month minimum usage billed pay-as-you-go, and Enterprise starts at a $500 monthly minimum with a 99.95 percent SLA.
- Management
- Not stated
- Infrastructure
- Not stated
- Pricing model
- Not stated
- Support
- Not stated
- SLA
- Not stated
- Best for
- Vector Search, AI Applications, AI Agents, Model Inference
Technical specifications
- Containers
- Unknown
- Kubernetes
- Unknown
- Root access
- Unknown
- API access
- Unknown
- Autoscaling
- Unknown
- Persistent processes
- Unknown
AI capabilities
- Model serving
- llama-text-embed-v2, multilingual-e5-large, pinecone-sparse-english-v0, bge-reranker-v2-m3, pinecone-rerank-v0, cohere-rerank-4-fast
- AI frameworks
- Not stated
- Inference endpoints
- Unknown
- Fine-tuning
- Unknown
- Vector database
- Unknown
- Model catalog
- Unknown
- Monitoring
- Not stated
- Evaluation
- Not stated
Security & compliance
No controls are stated.
Geography
Provider headquarters are separate from offering infrastructure and availability.
Infrastructure regions
Ireland, Europe · United States, North America
Data-residency jurisdictions
Ireland, Europe · United States, North America
Service availability
Not stated
Support coverage
Not stated
Available plans
Pricing can change. Promotional prices are shown separately from standard prices.
| Plan | Price | Compute | Storage | GPU | Price checked | Actions |
|---|---|---|---|---|---|---|
| Pinecone Database & InferenceNot stated | $20.00Monthly | Unknown — RAM | Unknown | No | 7 October 2026 |
Questions & answers
- What types of search does Pinecone support?
- Pinecone supports similarity, hybrid and full-text queries using dense, sparse and full-text indexes. The managed service stores vectors and metadata and scales automatically.
- What does Pinecone's hosted inference provide?
- Hosted inference provides embedding models and rerankers so developers can assemble a RAG pipeline from one API. Models include llama-text-embed-v2 and multilingual-e5-large, while rerankers include bge-reranker-v2-m3 and pinecone-rerank.
- Can Pinecone run in a customer's own cloud account?
- Enterprise customers can use Bring Your Own Cloud inside their own account and VPC on AWS, Google Cloud or Azure. Enterprise options also include private endpoints and customer-managed keys.
- What does the Pinecone Assistant product do?
- Assistant packages document ingestion and chat on top of Pinecone's retrieval infrastructure.
Data sources & provenance
Where this information came from, how it was checked and when it was last looked at. “Last updated” records a change to the record — it does not mean the record was verified.
- Data quality
- Data quality: Unverified
- Primary source
- pinecone.io
- Sources cited
- 2
- Last reviewed
- 7 October 2026
- Last updated
- 18 October 2026