D

calculator

Free LLM API Cost Calculator

Project your monthly LLM API spend across GPT-5, GPT-5 mini, Claude Opus 4.6, Claude Sonnet 4.5, Claude Haiku 4.5, Gemini 2.5 Pro, Gemini 2.5 Flash, and Llama 3.3 405B (via Together AI). Models input + output token costs, prompt caching savings, and routing strategies. Includes annual projections and per-request cost.

Inputs

%

Results

Monthly Input Tokens (Millions)

1,250

Monthly Output Tokens (Millions)

300

GPT-5 ($5 in / $15 out)

$8,500

GPT-5 mini ($0.30 in / $1.20 out)

$600

Claude Opus 4.6 ($15 in / $75 out)

$34,500

Claude Sonnet 4.5 ($3 in / $15 out)

$6,900

Claude Haiku 4.5 ($0.80 in / $4 out)

$1,840

Gemini 2.5 Pro ($2.50 in / $10 out)

$5,188

Gemini 2.5 Flash ($0.30 in / $2.50 out)

$1,013

Llama 3.3 405B via Together ($3 in / $3 out)

$4,650

Annual Savings: Haiku vs Opus

$391,920

Annual Cache Savings on Sonnet 4.5

$16,200

By David Shadrake · Free, no signup required

AI & Machine Learning Resources

Strategic Playbooks

Roles That Use Tools Like This

Decisions to Compare

Explore Further

About the Author

David Shadrake

David Shadrake works on strategic business development and tech partnerships, with focus areas across AI, fintech, venture capital, growth, sales, SEO, blockchain, and broader tech innovation. Read more of his perspective on partnerships, market dynamics, and emerging technology at davidshadrake.com.