LLM API Cost Calculator
Estimate GPT, Claude and Gemini API spend per call and per month.
Usage
Estimated cost
Same workload on every model
| Model | Per call | Total |
|---|---|---|
| GPT-4o | $0.007500 | $7.5000 |
| GPT-4o mini | $0.000450 | $0.4500 |
| GPT-4.1 | $0.006000 | $6.0000 |
| GPT-4.1 mini | $0.001200 | $1.2000 |
| o3 | $0.006000 | $6.0000 |
| GPT-4 Turbo | $0.0250 | $25.0000 |
| GPT-3.5 Turbo | $0.001250 | $1.2500 |
| Claude Sonnet | $0.0105 | $10.5000 |
| Claude Haiku | $0.002800 | $2.8000 |
| Claude Opus | $0.0525 | $52.5000 |
| Gemini Flash | $0.001550 | $1.5500 |
| Gemini Pro | $0.006250 | $6.2500 |
| Llama 3.3 70B | $0.000950 | $0.9500 |
| Mistral Large | $0.005000 | $5.0000 |
Prices are public list rates and are editable above — always confirm with your provider's pricing page.
About the LLM API Cost Calculator
Enter token counts or paste your prompt, set output length, call volume and prompt-cache ratio, then compare cost per call, per run and per month across every major model. Prices are editable so you can model your own negotiated rates.
Examples
1k calls
1,000 in / 500 out on GPT-4oOutput
$7.50 totalKeyboard shortcuts
- Copy the main outputCtrl / ⌘ + Shift + C
- Download the resultCtrl / ⌘ + S
- Share this toolCtrl / ⌘ + Shift + S
- Reset the inputsAlt + R
- Open the tool search paletteCtrl / ⌘ + K
Related tools
AI Token Counter
AI & LLM
Count exact LLM tokens for GPT, Claude and Gemini prompts.
LLM Context Window Calculator
AI & LLM
See if your system, context and user messages fit the model window.
AI Dataset Deduplicator
AI & LLM
Remove exact and near-duplicate rows from fine-tuning datasets.
AI Dataset Statistics Analyzer
AI & LLM
Profile a JSONL training set: token stats, roles, duplicates and cost.
AI PII & Secret Redactor
AI & LLM
Strip emails, keys, tokens and personal data before prompting an LLM.
AI Tool Schema Builder
AI & LLM
Build function-calling schemas for OpenAI, Claude, Gemini, MCP and the AI SDK.
Frequently asked questions
Read more
- How LLM tokens really work (and why your word count is a bad estimate)
BPE splits words, punctuation and whitespace into pieces. Here is how tokens are counted, why context windows overflow, and how to plan a prompt that fits.
Version 1.0.0 · Updated 2026-08-14 · Runs entirely in your browser