Claude Cost Calculator
Estimate Anthropic Claude API spend per call, day, month and year — then compare against OpenAI and Gemini and see how much switching could save.
Inputs
Choose the model tier you plan to use in production.
Average prompt size per API call. A page of text ≈ 750 tokens.
Average completion length. Short answers ≈ 200–500 tokens.
Total API calls per month across all users / jobs.
Fraction of input tokens served from prompt cache (costs ~10× less). 0 = no caching.
Cost breakdown
| Item | Monthly | Yearly |
|---|---|---|
| Input tokens | $10,000.00 | $120,000.00 |
| Output tokens | $5,000.00 | $60,000.00 |
| Spend | $175,000.00 | $2,100,000.00 |
Comparison
| Option | Monthly | Yearly |
|---|---|---|
| OpenAI GPT-5cheapest | $62,500.00 | $750,000.00 |
| Claude Claude Opus 4.7current | $175,000.00 | $2,100,000.00 |
| Gemini Gemini 2.5 Pro | $62,500.00 | $750,000.00 |
Data updated 2026-06-30 · openai.com/api/pricing openai.com/api/pricing · platform.claude.com/docs/about-claude/pricing platform.claude.com/docs/about-claude/pricing · ai.google.dev/gemini-api/docs/pricing ai.google.dev/gemini-api/docs/pricing
Industry Benchmark
Data updated 2026-06-30 · openai.com/api/pricing openai.com/api/pricing · platform.claude.com/docs/about-claude/pricing platform.claude.com/docs/about-claude/pricing · ai.google.dev/gemini-api/docs/pricing ai.google.dev/gemini-api/docs/pricing
Trends & comparison
Trend
Comparison (monthly vs. yearly)
How to use this calculator
Choose a Claude model, enter token volumes and monthly requests, and optionally a cache hit ratio. The result compares Claude against OpenAI and Gemini comparable tiers and recommends the cheapest.
Claude pricing tiers
Opus, Sonnet and Haiku trade capability for cost. For long-context, cache-heavy workloads, prompt caching can dramatically reduce input token spend.
Benchmarks & sources
All prices come from a versioned JSON config validated at build time and shown with their update date in the page footer.
Frequently asked questions
How is Claude API cost calculated?▾
Cost = (input tokens ÷ 1,000,000 × input price) + (output tokens ÷ 1,000,000 × output price), times your monthly requests, with prompt-cache and batch discounts applied where enabled.
Which Claude model should I pick?▾
Opus is the highest-capability tier, Sonnet balances cost and quality, and Haiku is cheapest for high-volume simple tasks. The calculator shows the cost delta instantly.
Are the OpenAI and Gemini comparisons accurate?▾
They use comparable-tier pricing sourced directly from official provider documentation. Verify against official price pages; the footer shows the data version and source.