🔥 Introducing the Helicone AI Gateway (in beta) - reach 100+ models with a single integration.
Calculate the cost of using AI models with Helicone's free pricing tool.
Our LLM API Pricing Calculator is a powerful tool designed to help you:
Using the latest pricing data directly from various AI providers, this calculator provides you with precise cost estimates for a wide range of LLM APIs.
Built and maintained by the Helicone team. This calculator is part of the largest fully open-source collection of LLM API pricing data, covering over 300+ models and growing.
Comprehensive model coverage
Easy comparison across providers
Up-to-date pricing information
Use the calculator to compare costs across different models and providers to find the best fit for your needs.
Experiment with different input and output token counts to estimate costs for various use cases.
Remember to factor in your expected usage volume when comparing costs across different providers.
Access the same pricing data used in this calculator programmatically through our API endpoint. Perfect for integrating cost calculations into your applications, scripts, or automated workflows.
# Get all models with costs per 1 million tokens
curl "https://helicone.ai/api/llm-costs"
# Get costs for a specific provider
curl "https://helicone.ai/api/llm-costs?provider=openai"
# Search for models containing "gpt"
curl "https://helicone.ai/api/llm-costs?model=gpt"
# Combine filters
curl "https://helicone.ai/api/llm-costs?provider=anthropic&model=claude"
# Get data as JSON (default)
curl "https://helicone.ai/api/llm-costs?provider=openai"
# Get data as CSV for spreadsheets
curl "https://helicone.ai/api/llm-costs?provider=openai&format=csv" \
--output llm-costs-per-1m.csv
The API returns structured data with metadata and cost information:
{
"metadata": {
"total_models": 250,
"note": "All costs are per 1 million tokens unless otherwise specified",
"operators_explained": {
"equals": "Model name must match exactly",
"startsWith": "Model name must start with the specified value",
"includes": "Model name must contain the specified value"
}
},
"data": [
{
"provider": "OPENAI",
"model": "gpt-4",
"operator": "equals",
"input_cost_per_1m": 30.0,
"output_cost_per_1m": 60.0,
"show_in_playground": true
}
]
}
Parameter | Type | Default | Description |
---|---|---|---|
provider | string | - | Filter by exact provider name (e.g., "OPENAI", "ANTHROPIC") |
model | string | - | Search models containing this text (e.g., "gpt", "claude") |
format | string | json | Output format: "json" or "csv" |
Field | Description |
---|---|
provider | Provider name (e.g., "OPENAI", "ANTHROPIC") |
model | Model identifier |
operator | How the model name matching works ("equals", "startsWith", "includes") |
input_cost_per_1m | Cost per 1 million input tokens (USD) |
output_cost_per_1m | Cost per 1 million output tokens (USD) |
per_image | Cost per image (USD) - if applicable |
per_call | Cost per API call (USD) - if applicable |
As an open-source project, we welcome contributions from the community to keep the pricing data accurate and up-to-date.
By contributing, you're helping to maintain the largest fully open-source collection of LLM API pricing data, covering over 300+ models and growing.