Loading...

AI System Cost Estimator

Configure your desired architecture to get a preliminary cost estimate. ^Beta

Select LLM Provider & Model

Context window: 128k

Managed Costs (Auto-populated)

Cost per Input Token ($ / 1M tokens)

Cost for processing prompt tokens.

Cost per Output Token ($ / 1M tokens)

Cost for generating response tokens.

Enable RAG (Retrieval-Augmented Generation)

Enable Agentic Features (Orchestration, Tools)

Primary Cloud Provider

Open AWS (Amazon Web Services) Calculator

Source Data Storage Cost ($ / month)

S3, GCS, Azure Blob etc.

Data Ingestion/ETL Cost ($ / month)

Serverless functions, managed pipelines.

Preprocessing Compute Cost ($ / month)

Chunking, cleaning before embedding.

Primary Cloud/Hosting Provider

Open AWS (Amazon Web Services) Calculator

Application Hosting Cost ($ / month)

Vercel, Netlify, Lambda, EC2 etc.

API Gateway / Load Balancer Cost ($ / month)

If applicable.

Estimated Network Egress Cost ($ / month)

Data transfer out.

Primary Cloud/Monitoring Provider

Open AWS (Amazon Web Services) Calculator

Logging Cost ($ / month)

Datadog, CloudWatch Logs etc.

Metrics Cost ($ / month)

Datadog, CloudWatch Metrics etc.

Tracing Cost ($ / month)

Datadog APM, OpenTelemetry etc.

Estimated Requests per Month

Total LLM/Agent calls.

Average Tokens per Request (Input + Output)

Combined prompt and completion length.

RAG Data Volume (GB)

Size of data indexed in Vector DB.

RAG Data Update Frequency

How often RAG data needs re-indexing/embedding.