StarterFor trying out and for small applications. Pinecone Database On-Demand Pinecone Inference Pinecone Assistant Console Metrics Community Support | StandardPOPULARFor production applications at any scale. 3 week trial, $300 credit $50/month minimum usage afterYou'll be charged a minimum of $50/month. Once your usage exceeds this amount, you'll pay as you go. Pay-as-you-go for Database On-Demand, Inference, and Assistant Usage Choose your cloud and region Import from object storage Multiple projects and users SAML SSO User and API Key RBAC Backup and Restore Prometheus metrics Includes Free support Response SLAs available via Developer or Pro support add-on | EnterpriseFor mission-critical production applications. $500/month Minimum usageYou'll be charged a minimum of $500/month. Once your usage exceeds this amount, you'll pay as you go. Everything in Standard 99.95% Uptime SLA Private Networking Customer Managed Encryption Keys Audit Logs Service Accounts Admin APIs HIPAA Compliance Pro support included |
|---|---|---|
StarterFor trying out and for small applications. Pinecone Database On-Demand Pinecone Inference Pinecone Assistant Console Metrics Community Support | ||
StandardPOPULARFor production applications at any scale. 3 week trial, $300 credit $50/month minimum usage afterYou'll be charged a minimum of $50/month. Once your usage exceeds this amount, you'll pay as you go. Pay-as-you-go for Database On-Demand, Inference, and Assistant Usage Choose your cloud and region Import from object storage Multiple projects and users SAML SSO User and API Key RBAC Backup and Restore Prometheus metrics Includes Free support Response SLAs available via Developer or Pro support add-on | ||
EnterpriseFor mission-critical production applications. $500/month Minimum usageYou'll be charged a minimum of $500/month. Once your usage exceeds this amount, you'll pay as you go. Everything in Standard 99.95% Uptime SLA Private Networking Customer Managed Encryption Keys Audit Logs Service Accounts Admin APIs HIPAA Compliance Pro support included | ||
Estimate your costs with our pricing calculator |
Bring your own cloud
For organizations requiring the highest level of security and control
Bring-your-own-cloud (BYOC) allows you to deploy a private Pinecone instance into your cloud environment, giving you the security and control of a self-hosted solution while retaining the seamless experience of our fully managed SaaS product. Contact us for more information.
What you can build on the Starter plan
Recommendation engine
Given an e-commerce site with:
- 50K products
- 10KB metadata per product
- Using 1024 dimensions embeddings
Starter plan gives you:
- ~ 44K recommendations per day
- ~ 2K product updates per day
Semantic search
Given a knowledge base of:
- ~ 30K documents
- 20KB document size on average
- Using 1024 dimensions embeddings
Starter plan gives you:
- ~ 15k searches per day
- ~ 660 document updates per day
Forum answering bot (RAG)
Given a user forum with:
- ~ 10 categories
- 5KB post size on average
- Using 1024 dimensions embeddings
Starter plan gives you:
- ~ 130K category-scoped chats per day
- ~ 3K messages indexed per day
Disclaimer: Examples are illustrative only, not quotes or binding offers. Database usage only; excludes Inference (embeddings/reranking) and Assistant usage, as well as initial data import. Subject to change.
Explore products
On-Demand
The foundation for knowledgeable AI. Backed by distributed object storage for scalable, highly available serverless indexes.
DRN
Dedicated Read Nodes. Exclusive infrastructure for queries, with provisioned nodes reserved for your index – no noisy neighbors, no shared queues, no read rate limits.
Inference
Pinecone Inference is a service that gives you access to embedding and reranking models hosted on Pinecone's infrastructure.
Assistant
Pinecone Assistant is a service that allow you to build production-grade chat and agent-based applications quickly.
Support
Pinecone Support provides various tiers of assistance to ensure your application's success, from community support to dedicated engineering resources.
Usage-based pricing
$50 monthly minimum that's applied to your usage. Anything over $50 is billed pay-as-you-go.
Committed Use Contracts
The larger your usage commitments, the greater your benefits—unlock bigger discounts and support.
| Plan | Starter | Standard | Enterprise |
|---|---|---|---|
Database Features | |||
| Cloud Availability | AWS | ||
| Region Availability | us-east-1 | ||
| Dedicated Read NodesNEW | |||
| Index Types | Dense and Sparse | ||
Indexes | Up to 5 | ||
| Namespaces per Index | 100 | ||
| Embedding Models | All available models | ||
| Reranking Models | All except cohere-rerank-3.5 | ||
| Console Index Metrics | |||
| Prometheus and Datadog Monitoring | |||
| Uptime SLA | |||
Pricing Dimensions | |||
Database | |||
| Storage | Up to 2 GB | ||
| Write Units | Up to 2M/mo | ||
| Read Units | Up to 1M/mo | ||
| Import from object storage | |||
| Backups | |||
| Restore from backup | |||
Assistant | |||
| Document Limit | 100 | ||
| Storage | 1GB Storage included | ||
| Input Tokens | 1.5M included | ||
| Output Tokens | 200k included | ||
| Context Processed Tokens | 500k included | ||
| Hourly Rate | Free | ||
| Region | United States | ||
Inference - Embedding | |||
| llama-text-embed-v2 | 5M tokens/mo. included | ||
| multilingual-e5-large | 5M tokens/mo. included | ||
| pinecone-sparse-english-v0 | 5M tokens/mo. included | ||
Inference - Reranking | |||
| pinecone-rerank-v0 | 500 requests/mo. included | ||
| bge-reranker-v2-m3 | 500 requests/mo. included | ||
| cohere-rerank-v3.5 | — | ||
Org Management | |||
| Projects | 1 | ||
| Users | Up to 2 | ||
| SAML SSO | |||
| Service Accounts | |||
| Admin API | |||
| Support | |||
Security and Compliance | |||
| Encryption at rest and in transit | |||
| User RBAC | |||
| API Key RBAC | |||
| Audit Logs | |||
| Private Endpoints | |||
| Customer Managed Encryption Keys | |||
| SOC 2 | |||
| GDPR | |||
| ISO 27001 | |||
| HIPAA | |||
Start building knowledgeable AI today
Create your first index for free, then pay as you go when you're ready to scale.