Get started
Pricing and limits
This page describes the pricing and limits of Pinecone Assistant.
Beyond the monthly minimum, customers are charged for what they use each month.
Examples
See Pricing for up-to-date pricing information.
The following file limits apply to each assistant:
Minimum usage
The Standard and Enterprise pricing plans include a monthly minimum usage committment:| Plan | Minimum usage |
|---|---|
| Standard | $50/month |
| Enterprise | $500/month |
Usage below monthly minimum
Usage below monthly minimum
- You are on the Standard plan.
- Your usage for the month of August amounts to $20.
- Your usage is below the $50 monthly minimum, so your total for the month is $50.
Usage exceeds monthly minimum
Usage exceeds monthly minimum
- You are on the Standard plan.
- Your usage for the month of August amounts to $100.
- Your usage exceeds the $50 monthly minimum, so your total for the month is $100.
Customers who signed up for the Standard or Enteprise plan before July 1, 2025 will continue to pay a monthly platform fee until September 1, 2025. After that date, the minimum usage commitment explained above will replace the platform fee.
Usage credits do not roll over from month to month. Platform fees do not apply to organizations on the Starter plan or with annual commits.
| Plan | Platform fee | Usage credits |
|---|---|---|
| Standard | $25/month | $15/month |
| Enterprise | $500/month | $150/month |
Usage cost
The cost of using Pinecone Assistant is determined by the following factors:| Invoice line item | Description |
|---|---|
| Assistants Context Tokens Processed | Number of tokens processed for context retrieval. |
| Assistants Evaluation Tokens Out | Number of tokens used to calculate evaluation metrics. |
| Assistants Evaluation Tokens Processed | Number of tokens used to prompt evaluation metrics. |
| Assistants Hourly Count | Number of hours the assistant is available. |
| Assistants Input Tokens | Number of tokens processed by the assistant. |
| Assistants Output Tokens | Number of tokens output by the assistant. |
| Assistants Total Storage GB/Hours | Total size of files stored in the assistant per month. |
Token usage
Pinecone Assistant usage is measured in tokens, with different counts and cost for input and output tokens.For chat, tokens are defined as follows:
-
Input tokens are based on the messages sent to the assistant and the context snippets retrieved from the assistant and sent to a model. Messages sent to the assistant can include messages from the chat history in addition to the newest message.
Input tokens appear as
prompt_tokensin API responses and as Assistants Input Tokens on invoices. -
Output tokens are based on the answer from the model.
Output tokens appear as
completion_tokensin API responses and as Assistants Output Tokens on invoices.
You can use API response details to monitor ongoing token usage, and you can control the size of context snippets retrieved from the assistant to limit token usage.
Limits
Pinecone Assistant limits vary based on pricing plan. The following limits apply to each project:| Metric | Starter plan | Standard plan | Enterprise plan |
|---|---|---|---|
| Max number of assistants | 3 | Unlimited | Unlimited |
| Max file storage | 1 GB | Unlimited | Unlimited |
| Max tokens per minute (TPM) input | 30,000 | 150,000 | 150,000 |
| Max number of total LLM processed tokens | 1,500,000 | Unlimited | Unlimited |
| Max input tokens per query | 64,000 | 64,000 | 64,000 |
| Max total output tokens | 200,000 | Unlimited | Unlimited |
| Region | United States | Any | Any |
| Metric | Starter plan | Standard plan | Enterprise plan |
|---|---|---|---|
| Max file size (.docx, .json, .md, .txt) | 10 MB | 10 MB | 10 MB |
| Max file size (.pdf) | 10 MB | 100 MB | 100 MB |
| Max metadata size per file | 1 KB | 1 KB | 1 KB |
| Max files uploaded | 10 | 10,000 | 10,000 |