Skip to main content

RAG Plans

The TIR AI/ML Platform offers a robust Retrieval-Augmented Generation (RAG) solution for your AI and ML needs. This document outlines the billing structure for services utilized within the platform, enabling you to estimate costs effectively based on usage.

Billing Categories and Strategies​

Cost CategoryBilling StrategyPricing (INR)Description
Storage CostPer GB per Month8Covers the costs of storing documents and vector embeddings required for efficient retrieval.
Search & Indexing CostPer 1 Million Tokens (Input + Output)10Incurred during the retrieval of data from vector storage based on user queries.
GenAI API CostDefault GenAI API PricingDefault GenAI API PricingRefers to the standard pricing for GenAI API services such as LLM-based chat and other RAG functions.

Detailed Description of Billing Categories​

1. Storage Cost​

  • What It Covers:
    • Document storage required for RAG functionality.
    • Vector embeddings generated from the documents, enabling efficient retrieval.
  • Billing Model:
    • Calculated monthly on a per GB basis.
  • Pricing:
    • 8 INR/GB/month .

2. Search & Indexing Cost (Retrieval Cost)​

  • What It Covers:
    • Token-based retrieval and indexing processes for user queries.
    • Combines both input tokens (user query) and output tokens (retrieved data).
  • Billing Model:
    • Calculated per 1 million tokens processed (input + output).
  • Pricing:
    • 10 INR per 1 million tokens.

3. GenAI API Cost​

  • What It Covers:
    • Usage of Generative AI APIs integrated into the platform.
    • Includes large language models (LLMs) for tasks like chat, summarization, and query answering.
  • Billing Model:
    • Based on default GenAI API pricing.
  • Pricing:
    • Directly tied to the GenAI API pricing in both INR and USD.
tip

Ensure you monitor token usage and storage requirements to optimize costs.

Note

For more details or to calculate custom pricing for your use case, please contact our support team.