AI cost tools
Start with tokens, then narrow by provider.
Use the general LLM token calculator as the wide entry point, then move into provider-specific tools, embedding cost, the RAG calculator, or the AI agent calculator for task-level workflow cost.
LLM Token Calculator
Estimate prompt tokens, response tokens, per-request cost, daily cost, and monthly cost across major LLM providers.
OpenOpenAI API Cost Calculator
Estimate input, cached input, output, Batch API, daily, monthly, and annual OpenAI API spend.
OpenClaude API Cost Calculator
Estimate Claude input, prompt cache write/read, output, Message Batches, daily, monthly, and annual spend.
OpenGemini API Cost Calculator
Estimate Gemini input, output, Batch prices, context caching, grounding, daily, monthly, and annual spend.
OpenDeepSeek API Cost Calculator
Estimate DeepSeek cache-hit input, cache-miss input, output, thinking-mode, daily, monthly, and annual spend.
OpenRAG Cost Calculator
Estimate RAG indexing, embedding, retrieval context, query generation, monthly, and annual knowledge-base cost.
OpenAI Agent Cost Calculator
Estimate agent task cost from model calls, tool-call overhead, retries, daily volume, monthly spend, and annual budget.
OpenEmbedding Cost Calculator
Estimate embedding cost from document count, chunks per document, tokens per chunk, model choice, and refresh frequency.
OpenFAQ
Choose the right AI cost calculator
What can I calculate with these AI cost tools?
These tools estimate token usage, per-request cost, daily cost, monthly cost, and annual API spend across major LLM providers.
Should I start with the LLM token calculator or a provider calculator?
Start with the LLM token calculator for a broad estimate, then use provider-specific calculators when you need cached input, batch pricing, grounding, or cache-hit details.
Are the estimates exact billing numbers?
No. The tools are planning calculators. Production billing should be verified against provider usage dashboards and official token-counting APIs.