AI API Cost Calculator
Plan AI API spend before production: compare Claude, GPT, Gemini, and DeepSeek pricing, separate input, output, cache-read, and multimodal billing units, then estimate per-request and monthly budgets your team can review before launch.
Choose a cost calculator by model type
AI APIs bill very differently: reasoning and text are usually token-based, while audio, image, and video can depend on duration, size, quality, and multimodal inputs. Pick the matching calculator before estimating spend.
Reasoning Models
Budget input, output, and cache costs for agents, coding, long-context, and multi-step reasoning tasks.
Open pageText Models
Estimate token costs and monthly spend for chat, summaries, translation, RAG, and batch text processing.
Open pageAudio Models
Separate input and output costs for speech, realtime voice, and audio understanding APIs.
Open pageImage Models
Estimate size, quality, and token costs for image generation, vision, and text-image requests.
Open pageVideo Models
Estimate multimodal API costs for video understanding, long-video analysis, and media agent workflows.
Open pageAI Model API Pricing
Compare providers, model categories, input/output rates, cache-read pricing, and official source links before locking budget assumptions.
Latest guides
Guides for token budgeting, cache strategy, model selection, and cost optimization.
AI API Usage Forecasting Mistakes: 7 Reasons Your Budget Is Too Low
AI API usage forecasting mistakes that make LLM budgets too low. Learn how average request cost, output token growth, cache assumptions, retries, fallback, evals, batch jobs, and agent steps can make next-month AI spend exceed the forecast.
Read guideAI API Cost Forecasting Guide: Plan Next-Month Spend Before It Spikes
AI API cost forecasting guide for teams planning next-month LLM spend. Build baseline, growth, and stress scenarios from users, requests, tokens, model mix, retries, cache hit rate, evals, agents, and batch jobs without inventing model prices.
Read guideAI API Monthly Cost Review: Find What Actually Drove the Bill
Monthly AI API cost review guide for teams using Claude, GPT, Gemini, DeepSeek, and other LLM APIs. Learn how to break down spend by feature, model, tokens, retries, cache hit rate, agents, and batch jobs, then turn the review into next-month cost governance actions.
Read guideFAQ
Are these prices accurate?
Prices are verified against official provider pricing pages. DeepSeek prices include the current 75% discount promotion. Always confirm with official dashboards for production budgets.
Does this send my prompts anywhere?
No. All calculations run in your browser. Your token counts and prompts never leave your device.
What does "cache hit" mean?
Cache hit tokens are input tokens that match a previously cached prefix. Providers charge much less for cache hits — for example, DeepSeek charges ¥0.025/1M for cache hits vs ¥3/1M for cache misses.
Why do different models show different numbers of bars?
Each provider has a different pricing model. DeepSeek has 3 components (miss/hit/output). Anthropic adds a separate cache write cost. The bars reflect each model's actual billing structure.
How do I report incorrect pricing?
Use the Report Pricing Error page to flag incorrect prices. We update data from official sources and welcome corrections.