Start getting better AI results today

Token Calculator

Paste your prompt and instantly compare token counts and costs across 12 AI models.

Your Prompt / Text

0
Tokens
0
Characters
0
Words
Advertisement (728×90)

How token cost is calculated

1.Count tokens: Your text is split into tokens. ~4 characters = 1 token. "Hello world" ≈ 3 tokens. This is the same method used by OpenAI, Anthropic, and Google.
2.Input cost: You pay for every token in your prompt (what you send to the AI). Rate varies by model — cheaper models charge less per token.
3.Output cost: You also pay for every token the AI generates in its response. Output is usually 2–5× more expensive than input. The table below shows cost for your input only.
Cost = (your_tokens ÷ 1,000,000) × price_per_million_tokens

Cost Comparison — 12 Models

Sorted cheapest first

Input cost = cost to send your prompt. Output cost = cost per response of the same length. Real output length will vary.

🔢

Paste your text above to see costs across all models

Model Benchmarks

Public benchmark scores from official model cards and independent evaluations (2025–2026). Use these to pick the right model — not just the cheapest one.

ModelMMLU ↑HumanEval ↑GPQA ↑MATH ↑Best for
Claude Opus 4.690%92%76%90%Complex reasoning, analysis
Claude Opus 4.589%90%74%88%Long documents, nuanced writing
o3 (reasoning)87%91%78%96%Math, science, hard reasoning
Gemini 2.5 Pro89%87%75%91%Research, long context (1M tokens)
GPT-4.188%88%72%87%Coding, general tasks
Claude Sonnet 4.586%85%68%83%Balanced quality + cost
Claude Sonnet 485%84%66%81%Everyday writing, coding
DeepSeek V3.284%83%62%85%Coding, math, low cost
Gemini 2.5 Flash82%80%60%78%Fast, cheap, high volume
GPT-4.1 mini80%78%55%74%Budget tasks, high throughput
Llama 3.3 70B80%79%50%73%Open source, self-hosted
Claude Haiku 4.579%76%52%70%Fast responses, simple tasks
GPT-4o mini77%74%48%68%Cheapest OpenAI option
Amazon Nova Pro75%70%45%65%AWS-native, cost-effective
Amazon Nova Lite68%60%38%55%Ultra-low cost, simple tasks
MMLU — General knowledge across 57 subjects
HumanEval — Python coding problems
GPQA — PhD-level science questions
MATH — Competition math problems

↑ Higher is better. Scores from official model cards and public evaluations. Some values are approximate.

Advertisement (728×90)
Start getting better AI results today