💰

AI Cost Estimator

Calculate API costs for GPT-4, Claude, Gemini — per request and monthly

⚠️ Fallback pricing — retry
Per Request$0.007500
Daily (100 reqs)$0.7500
Monthly Estimate$22.50

Cost Breakdown

Input (1000 tokens)$0.002500
Output (500 tokens)$0.005000
Total per request$0.007500

All Models — Live Pricing (per 1M tokens)

10 models
ModelProviderInput / 1MOutput / 1MContext
GPT-4oOpenAI$2.5$10128K
GPT-4o MiniOpenAI$0.15$0.6128K
GPT-4 TurboOpenAI$10$30128K
o1OpenAI$15$60200K
Claude Opus 4Anthropic$15$75200K
Claude Sonnet 4Anthropic$3$15200K
Claude Haiku 3.5Anthropic$0.25$1.25200K
Gemini 2.0 FlashGoogle$0.1$0.41M
Gemini Pro 1.5Google$1.25$51M
Llama 3.3 70BMeta$0.12$0.3128K

Frequently Asked Questions

Where does the pricing data come from?

Pricing is fetched live from the OpenRouter public API which aggregates pricing from OpenAI, Anthropic, Google, Meta, and more. Data is cached for 24 hours. Click "Refresh Prices" to force an update.

How do I know my token count?

Use our Token Counter tool to estimate tokens from your actual prompts. A rough rule of thumb: 1 token ≈ 4 characters in English.

Why does the model list vary?

OpenRouter's catalogue changes as providers release new models and deprecate old ones. The list you see reflects what's currently available via their API.