How many tokens is my text?

English text averages about 1 token per 4 characters or 0.75 words per token. A 1000-word article is roughly 1,300 tokens. Code and non-English text may use more tokens. Use the token estimator above for accurate counts.

How much does 1 million tokens cost?

1 million tokens costs $0.075 (Gemini Flash Lite) to $30 (GPT-5.5) for input. Most mid-tier models cost $1-3 per million tokens. Output tokens cost 2-10x more. GPT-5 is $1.25/M input, $10/M output.

What is the difference between input and output tokens?

Input tokens are what you send to the API (your prompt). Output tokens are what the model generates (the response). Output tokens cost 2-10x more than input tokens. For example, GPT-5 charges $1.25/M input but $10/M output.

Token Cost Estimator

Enter your token counts and instantly see what each model would cost. Compare all 42 models side by side.

Input Tokens

Tokens sent to the model

Output Tokens

Tokens generated by the model

Requests / Month

How many API calls per month

Cost Comparison

Model	Provider	Tier	Input / 1M	Output / 1M	Monthly Cost

Cheapest

—

Most Expensive

—

Potential Savings

—

Best Budget Pick

—

Need Saved Scenarios & Cost Reports?

APIpulse Pro lets you save configurations, compare scenarios side by side, and export professional cost reports for your team.

Get Pro — $29 one-time

Related Tools

Prompt Cost Calculator — Paste any prompt, see costs across 42 models
Cost Calculator — Estimate monthly costs for any model
Cost Explorer — See all 42 models ranked by cost
Cheapest AI API Finder — Find the cheapest model for your use case
How to Estimate Tokens — Guide to token estimation