RAG Pricing
πΈ RAG Pricing Guide β Eden AI
Eden AIβs Retrieval-Augmented Generation (RAG) assistant pricing is based on actual usage. You only pay for the operations you perform β such as uploading data or asking questions β and costs vary depending on the AI models and providers you choose.
π¬ Asking Questions (LLM Chat)
Each time you ask a question to your assistant, Eden AI uses an LLM (Large Language Model) to generate a response. This triggers a call to the LLM Chat API, and you are charged based on the model used.
π Check LLM Chat model pricing
You can configure which model is used when you set up your assistant.
π₯ Uploading Data (Embeddings)
When you upload text, URLs, or documents, Eden AI transforms your content into vector representations using the Embeddings API. You are charged for each embedding operation.
π Check Embedding model pricing
You can choose from a variety of embedding providers and models, each with their own pricing.
ποΈ Uploading PDFs and Audio (OCR & Speech-to-Text)
When you upload files such as:
- PDFs: Eden AI runs OCR Multipage to extract the text.
- Audio files (e.g., MP3/WAV): Eden AI performs Speech-to-Text (Async) transcription.
These actions use their respective Eden AI APIs, and pricing depends on the provider you selected in the project creation step.
π OCR Pricing
π Speech-to-Text Pricing
You only pay for what you use.
β
Summary
Action | API Used |
---|---|
Ask question | LLM Chat API |
Upload text/URL | Text Embeddings API |
Upload PDF | OCR Multipage |
Upload audio | Speech-to-Text Async |
You can always view and compare pricing by visiting the Eden AI Model Pricing Dashboard.
Updated about 10 hours ago