Cost Estimates
Calculate per-request and batch costs from token counts.
Token pricing estimates for model runs
LLM Cost Calculator
Estimate LLM API costs from input tokens, output tokens, request volume, and LiteLLM pricing data.
LiteLLM PricingBatch CostToken Math
LiteLLM pricing workbench
Estimate per-request and batch cost before you run.
Pricing source: LiteLLM fallback
Total batch$0.3621
1,000 requests
gpt-4o-mini
Per request$0.000362
Input cost$0.000002
Output cost$0.000360
Provideropenai
Context window128,000 tokens
Prices are read from LiteLLM token-level fields and can change upstream.
FormulaShowHide
( input_tokens × input_cost_per_token + output_tokens × output_cost_per_token ) × requests
Capabilities
What this tool handles
Use LLM Cost Calculator to check the input, tune the settings, and copy a clean output.
LiteLLM Pricing
Loads model prices from LiteLLM pricing JSON.
Prompt Token Count
Count a sample prompt and sync it into the estimate.
Workflow
Run it in three steps
Estimate model spend from LiteLLM pricing and token counts.
1
Choose Model
Select a model loaded from LiteLLM pricing data.
2
Enter Tokens
Set input tokens, output tokens, and request volume.
3
Review Cost
Copy the per-request and batch cost estimate.
Good for
Common jobs this tool supports
LiteLLM PricingUses model pricing JSON
Batch MathEstimates scaled request cost
Token InputsInput and output tokens
Copy SummaryCopy estimate details
FAQ
Answers before you run it
Practical notes about output, privacy, and common settings.
The calculator loads pricing from LiteLLM model_prices_and_context_window.json and uses a small fallback list if that source is unavailable.
Use next