OpenAI API Pricing Calculator
Business & AIEstimate OpenAI, Anthropic and Gemini API costs instantly. Compare GPT-4o, o1, Claude 3.5 Sonnet and Gemini pricing, toggle batch discounts and project monthly spend.
Usage Assumptions
Projected monthly cost — GPT-4o
$150.00
Input
$60.00
Output
$90.00
Per request
$0.0050
Yearly
$1,800.00
24.00M prompt + 9.00M completion tokens/month at $2.50 / $10.00 per 1M tokens.
Token Estimator
0 words · 0 chars · ≈ 0 tokensModel Comparison — monthly cost at current usage
| Model | Vendor | Input / 1M | Output / 1M | Context | Monthly cost |
|---|---|---|---|---|---|
| GPT-4o | OpenAI | $2.50 | $10.00 | 128K | $150.00 |
| GPT-4o mini | OpenAI | $0.1500 | $0.6000 | 128K | $9.00 |
| o1 | OpenAI | $15.00 | $60.00 | 200K | $900.00 |
| o3-mini | OpenAI | $1.10 | $4.40 | 200K | $66.00 |
| Claude 3.5 Sonnet | Anthropic | $3.00 | $15.00 | 200K | $207.00 |
| Gemini 1.5 Pro | $1.25 | $5.00 | 1M | $75.00 | |
| Gemini 1.5 Flash | $0.0750 | $0.3000 | 1M | $4.50 |
Prices are public list prices per 1M tokens (standard tier; batch toggle applies each vendor's ~50% asynchronous discount where offered). Always confirm current pricing on the vendor's pricing page — everything on this page computes locally in your browser.
cURL to Python Converter
Convert any cURL command into clean Python code. Get ready-to-run requests, httpx and FastAPI snippets with headers, auth, JSON and form data preserved — free and private.
cURL to JSON Converter
Turn cURL commands into structured JSON request objects, or generate a ready-to-paste n8n HTTP Request node. Headers, auth, query strings and bodies preserved — 100% local.
Slack Webhook Builder
Build Slack messages visually — headers, markdown, buttons and image blocks. Live preview, generated JSON payload and one-click test delivery to your webhook URL.
CSV to PDF Converter
Turn any CSV into a clean, styled PDF table in seconds. Choose portrait or landscape orientation with repeated headers on every page — runs 100% in your browser.
How to Use
Three steps from raw data to finished output — no account required.
- 1
Paste sample text into the token estimator, or set average prompt and completion tokens per request directly.
- 2
Set your average requests per day and pick a model — GPT-4o, o1, Claude 3.5 Sonnet, Gemini 1.5 and more.
- 3
Compare the per-model table, toggle Batch API pricing (typically 50% off) and read your projected monthly cost.
Frequently Asked Questions
Everything you need to know about the openai api pricing calculator.
The estimator uses the widely accepted rule of thumb of roughly 4 characters (or about 0.75 words) per token for English text. Paste any prompt to see word, character and estimated token counts, then use those numbers in the cost projection.
OpenAI, Anthropic and Google all offer batch endpoints that process jobs asynchronously within 24 hours at around 50% of the standard per-token price. Toggle the batch switch to see discounted rates applied to every model in the comparison table.
GPT-4o, GPT-4o-mini, o1 and o3-mini from OpenAI, Claude 3.5 Sonnet from Anthropic, and Gemini 1.5 Pro and 1.5 Flash from Google — each with input and output per-million-token prices and context window sizes.
Monthly cost = requests per day × days per month × (prompt tokens × input price + completion tokens × output price) ÷ 1,000,000. Everything computes live in your browser — no data ever leaves this page.