📊 Documentation

CSV Upload Guide

Learn how to prepare your AI usage data for analysis.
Simple format. Instant insights.

Required Columns

Your CSV must include these three essential columns

🤖

model

Text (required)

The AI model name (e.g., "gpt-4", "claude-3-opus", "gemini-pro")

📥

prompt_tokens

Number (required)

Number of input tokens used

📤

completion_tokens

Number (required)

Number of output tokens generated

👥

team (Optional)

Text (optional)

Team or department name. If not provided, we auto-generate from API key, email, or customer ID.

Auto-Team Mapping

Don't have a team column? We can auto-generate it from:

api_key

Maps unique API keys to teams (Team-A, Team-B, etc.)

user_email

Extracts team from email domain (john@marketing.com → Marketing)

customer_id

Creates team names from customer IDs (Customer-123, Customer-456)

Supported AI Models

We support all major AI providers with up-to-date pricing

🔮 OpenAI

Model Name Type Input Price Output Price
gpt-4 Advanced $0.03 / 1K tokens $0.06 / 1K tokens
gpt-4-turbo Fast Advanced $0.01 / 1K tokens $0.03 / 1K tokens
gpt-3.5-turbo Budget $0.0005 / 1K tokens $0.0015 / 1K tokens

🧠 Anthropic (Claude)

Model Name Type Input Price Output Price
claude-3-opus Advanced $0.015 / 1K tokens $0.075 / 1K tokens
claude-3-sonnet Balanced $0.003 / 1K tokens $0.015 / 1K tokens
claude-3-haiku Budget $0.00025 / 1K tokens $0.00125 / 1K tokens

🌟 Google (Gemini)

Model Name Type Input Price Output Price
gemini-1.5-pro Advanced $0.00125 / 1K tokens $0.00375 / 1K tokens
gemini-1.5-flash Budget $0.000075 / 1K tokens $0.0003 / 1K tokens
gemini-pro Standard $0.00025 / 1K tokens $0.0005 / 1K tokens

☁️ Azure OpenAI

Model Name Equivalent Input Price Output Price
azure-gpt-4 GPT-4 $0.03 / 1K tokens $0.06 / 1K tokens
azure-gpt-4-turbo GPT-4 Turbo $0.01 / 1K tokens $0.03 / 1K tokens
azure-gpt-35-turbo GPT-3.5 Turbo $0.0005 / 1K tokens $0.0015 / 1K tokens

Example CSV Formats

Three ways to structure your data

Minimal Format

With auto-team mapping from API key

model,prompt_tokens,completion_tokens,api_key
gpt-4,150,250,sk_prod_123
gpt-3.5-turbo,50,100,sk_prod_456
claude-3-opus,200,300,sk_prod_123

With Team Column

Direct team attribution

model,prompt_tokens,completion_tokens,team
gpt-4,150,250,marketing
gpt-3.5-turbo,50,100,engineering
claude-3-opus,200,300,data_science

From Email Domain

Extracts team from email

model,prompt_tokens,completion_tokens,user_email
gpt-4,150,250,john@marketing.example.com
gpt-3.5-turbo,50,100,jane@eng.example.com
gemini-pro,75,150,bob@data.example.com

Tips for Best Results

Follow these guidelines for accurate analysis

Data Format Tips

  • Token counts must be whole numbers (no decimals)
  • Model names are case-insensitive (GPT-4, gpt-4, Gpt-4 all work)
  • Model name variations are supported (gpt-4-0613 → gpt-4)
  • CSV encoding should be UTF-8 for special characters
  • Maximum 100,000 rows per upload

📊 Data Quality Tips

  • Include at least 1 month of data for meaningful trends
  • Include multiple teams if comparing cost allocation
  • Include variety of models to see optimization opportunities
  • Consistent team naming helps identify patterns

⚠️ Common Errors

  • Missing required columns: Check model, prompt_tokens, completion_tokens
  • File too large: Maximum 10MB file size
  • Invalid token count: Must be whole numbers (0, 150, 250)
  • Unsupported model: Check supported models list above

What Happens After Upload?

Your analysis will include:

Total cost breakdown by team
Cost by provider (OpenAI, Claude, Gemini)
Waste patterns detected
Cost-saving recommendations
Team attribution accuracy
Downloadable PDF report

Ready to Get Started?

Download a template CSV file or upload your data directly

Upload Your CSV

Questions? Contact Support

Max file: 10MB • Max rows: 100,000 • Supported formats: CSV