AI Token Pricing Calculator — Compare GPT-4o, Claude, Gemini Costs
Compare token pricing across GPT-4o, GPT-4o-mini, Claude 3.5 Sonnet/Haiku, and Gemini 1.5 Pro/Flash. Estimate per-request, monthly, and annual costs with DAU scaling.
AI Token Pricing
Results update instantly as you type
Enter Values
Output Price (per 1M tokens)
$60.00
Prompt Tokens
500
Completion Tokens
150
Input Cost per Request
$0.00750000
Output Cost per Request
$0.00900000
Total Monthly Tokens
19,500
Estimated Annual Cost
$297.00K
Cost per User per Month
$2.4750
Requests per Day
50,000
All Model Comparisons
[{"id":"gpt-4o-mini","label":"GPT-4o-mini","provider":"OpenAI","inputPrice":0.15,"outputPrice":0.6,"cachedInput":0.0375,"costPerRequest":0.000165},{"id":"gemini-3-flash","label":"Gemini 3.1 Flash","provider":"Google","inputPrice":0.15,"outputPrice":0.6,"cachedInput":0.01875,"costPerRequest":0.000165},{"id":"claude-haiku-4","label":"Claude Haiku 4.5","provider":"Anthropic","inputPrice":0.25,"outputPrice":1.25,"cachedInput":0.025,"costPerRequest":0.00031249999999999995},{"id":"llama-4","label":"Llama 4","provider":"Meta","inputPrice":0.5,"outputPrice":1.5,"costPerRequest":0.000475},{"id":"deepseek-v3","label":"DeepSeek V3","provider":"DeepSeek","inputPrice":0.5,"outputPrice":2,"costPerRequest":0.0005499999999999999},{"id":"gemini-3-pro","label":"Gemini 3.1 Pro","provider":"Google","inputPrice":1.5,"outputPrice":6,"cachedInput":0.1875,"costPerRequest":0.00165},{"id":"gpt-5-mini","label":"GPT-5-mini","provider":"OpenAI","inputPrice":2,"outputPrice":8,"cachedInput":0.3,"costPerRequest":0.0021999999999999997},{"id":"gpt-4o","label":"GPT-4o","provider":"OpenAI","inputPrice":2.5,"outputPrice":10,"cachedInput":0.625,"costPerRequest":0.00275},{"id":"claude-sonnet-4","label":"Claude Sonnet 4.6","provider":"Anthropic","inputPrice":3,"outputPrice":15,"cachedInput":0.3,"costPerRequest":0.00375},{"id":"grok-3","label":"Grok 3","provider":"xAI","inputPrice":3,"outputPrice":15,"costPerRequest":0.00375},{"id":"gpt-5","label":"GPT-5","provider":"OpenAI","inputPrice":15,"outputPrice":60,"cachedInput":2.5,"costPerRequest":0.0165},{"id":"claude-opus-4","label":"Claude Opus 4.7","provider":"Anthropic","inputPrice":15,"outputPrice":75,"cachedInput":1.5,"costPerRequest":0.01875}]
Embed Code
Copy and paste this HTML snippet into any web page to embed this calculator directly.
<iframe src="http://127.0.0.1:54963/embed/engineering/ai-token-pricing?ref=embed" title="AI Token Pricing Calculator — Compare GPT-4o, Claude, Gemini Costs" width="100%" style="max-width:600px; border:none; height:500px;" loading="lazy"></iframe>
Direct Link
Share this link to let others open the calculator in their browser.
Cost Breakdown per Request
Per Request
$0.0165
Monthly
$24.75K
Annual
$297.00K
Cost per User
$2.4750
All Models — Cost for Same Request
The Formula
AI model pricing is based on token usage, split between input (prompt) tokens and output (completion) tokens. Output tokens typically cost 3-6x more than input tokens because generating tokens requires sequential compute. Prompt caching can reduce input costs by up to 90% for repeated context blocks.
Variable Definitions
Input Tokens
Tokens in the user prompt / system message. Includes system instructions, conversation history, and the user's current query.
Output Tokens
Tokens generated by the model in its response. Depends on task complexity and model's response style.
Price per 1M Input Tokens
Cost per million tokens for the prompt portion. Ranges from $0.075 (Gemini Flash) to $15.00 (GPT-5, Opus).
Price per 1M Output Tokens
Cost per million tokens for the generated response. Usually 3-6x input price.
Cached Input Price
Discounted rate for repeated prompt context blocks. Available on OpenAI, Anthropic, and Google. Typically 10-25% of standard input price.
How to Use This Calculator
- 1
Select your AI model from 12 options across 6 providers.
- 2
Paste your actual prompt text to auto-count tokens, or enter token counts manually.
- 3
Toggle prompt caching to see cached vs standard pricing.
- 4
Enter daily active users and requests per user to project monthly and annual costs.
- 5
Compare costs across all models to optimize your AI spend.
- 6
Prices are updated regularly — last updated date is shown in results.
Common Applications
- Estimating production AI costs by comparing per-request pricing across 12+ models from OpenAI, Anthropic, Google, and others
- Choosing the most cost-effective model for each task — from budget-friendly (GPT-4o-mini, Gemini Flash) to premium (GPT-5, Claude Opus)
- Budgeting monthly AI infrastructure costs with usage projections based on daily active users and requests per user
- Optimizing prompt design and implementing caching strategies to reduce token consumption and lower operational costs
Understanding the Concept
AI token pricing varies dramatically across models and providers. GPT-5 and Claude Opus 4.7 are the most capable (and most expensive) at $15/$60 and $15/$75 per million tokens respectively. For high-volume production workloads, GPT-4o-mini ($0.15/$0.60) or Gemini 3.1 Flash ($0.15/$0.60) offer the best value. Prompt caching is now a standard feature across all major providers — cached input tokens cost 75-90% less than standard input. For production deployments, enabling caching and choosing the right model tier for each task are the two most impactful cost optimization strategies. A customer support chatbot handling 10K conversations/day might cost $50/day on GPT-5 but only $1.65/day on GPT-4o-mini — a 30x difference. Use the model comparison table below to find the optimal price/performance balance for your use case.
Frequently Asked Questions
Sources & References
Related Calculators
Reviews
No reviews yet. Be the first to share your experience with AI Token Pricing Calculator — Compare GPT-4o, Claude, Gemini Costs.
Write a Review