🤖

AI API Cost Calculator

How much will GPT-4o / Claude cost at scale?

AI API costs can spiral fast at scale. Compare GPT-4o, Claude Sonnet, Gemini Flash, and 12 other models across your specific use case — see cost per request, daily, and monthly — so you can price your product with real numbers.

Select model

OpenAI

Anthropic

Google

Groq / Together

Mistral

How much you charge above API cost

%

GPT-4o800 tokens avg

Cost per request

$0.00575

Cost per 1,000 requests

$5.750

Daily (1,000 reqs)

$5.75

Monthly

$172.50

Yearly

$2099

Model$/req$/mo (1000/day)Context
GPT-4o OpenAI$0.00575$172.50128K
GPT-4o mini OpenAI$0.00034$10.35128K
GPT-4.1 OpenAI$0.00460$138.001000K
o3 OpenAI$0.02300$690.00200K
o4-mini OpenAI$0.00253$75.90200K
Claude Opus 4 Anthropic$0.04200$1260.00200K
Claude Sonnet 4 Anthropic$0.00840$252.00200K
Claude Haiku 3.5 Anthropic$0.00224$67.20200K
Gemini 2.5 Pro Google$0.00538$161.251000K
Gemini 2.5 Flash Google$0.00034$10.351000K
Llama 3.3 70B Groq / Together$0.00057$17.16128K
Mistral Large Mistral$0.00360$108.00128K

Input vs output tokens

Input tokens = everything in the prompt (system prompt + user message + context). Output tokens = the model's response. Output is always 3–5× more expensive than input.

Cost optimization

Switch to GPT-4o mini or Gemini 2.5 Flash for simple tasks — they're 10–20× cheaper and 90% as good. Use expensive models only for complex reasoning or long outputs.

Pricing your AI SaaS

Cover API cost + 200–500% margin. If GPT-4o costs you $0.10/request, charge $0.30–$0.50. Build usage limits per plan to protect your margin.

RAG cost optimization

RAG input costs are high (lots of context). Cache repeated context with OpenAI's prompt caching ($0.5/1M cached tokens vs $2.5/1M uncached). 80% savings for repeated system prompts.

Ready to build it for real?

We ship production-ready MVPs in 15–21 days at a fixed price. No surprises, no hourly billing.

More free tools