Show HN: CostPerPrompt – Live AI API pricing and real-workload cost calculators

CostPerPrompt, a new web tool launched on Hacker News, provides live pricing for 232+ AI models and calculators that estimate real-world costs for chatbots, agents, RAG, voice AI, and GPU rental, with data updated as of 2026-08-02. The tool includes calculators for API, chatbot, agent, RAG, voice AI, GPU rental, and image API costs, plus guides on prompt caching and batch processing, which can reduce costs by up to 90% and 50% respectively. CostPerPrompt aims to address the gap in cost estimation accuracy, noting that many articles' estimates can be 2–3× off.

What will AI actually cost you? Live pricing for 232+ models, refreshed automatically — plus calculators that turn token prices into real answers: what your chatbot, agent, or API workload will cost per month. Every cost question, answered $ API Cost Calculator Any workload, compared across all 232 models — with caching & batch discounts. /api-cost-calculator 💬 Chatbot Cost Simulates real conversations — growing history, resent context, cache hits. /chatbot-cost-calculator 🤖 Agent Cost Multi-step loops, tool schemas, retries — see why agents cost 10–30× more than you think. /agent-cost-calculator 📚 RAG Cost Indexing, retrieval and generation priced separately — spoiler: embeddings are pennies. /rag-cost-calculator 🎙️ Voice AI Cost STT + LLM + TTS per minute, per call, per month — the full three-part bill. /voice-ai-cost-calculator 🖥️ GPU Rental Pricing H100, A100, RTX 4090 across 10 providers — the same chip at a 5× price spread. /gpu-rental-pricing 🖼️ Image API Pricing $0.003 to $0.17 per image — three market tiers and a batch calculator. /image-api-pricing 🔢 Token Counter Paste text, get tokens and cost on any model — 100% in your browser. /token-counter ⚡ Cost-Cutting Guides Prompt caching −90% input and the Batch API −50% everything explained. /guides/prompt-caching Flagship model pricing per 1M tokens · updated 2026-08-02| Model | Vendor | Input / 1M | Output / 1M | Context | |---|---|---|---|---| | | GPT-5.5 /models/openai-gpt-5-5 GPT-5.4 /models/openai-gpt-5-4 Claude Fable 5 /models/anthropic-claude-fable-5 Claude Opus 5 /models/anthropic-claude-opus-5 Claude Sonnet 5 /models/anthropic-claude-sonnet-5 Kimi K3 /models/moonshotai-kimi-k3 DeepSeek V4 Pro /models/deepseek-deepseek-v4-pro DeepSeek V4 Flash 0731 /models/deepseek-deepseek-v4-flash-0731 Gemini 3.1 Pro Preview /models/google-gemini-3-1-pro-preview Gemini 3.6 Flash /models/google-gemini-3-6-flash Grok 4.5 /models/x-ai-grok-4-5 Grok 4.3 /models/x-ai-grok-4-3 GLM 5.2 /models/z-ai-glm-5-2 How AI API pricing works — the 60-second version Every major AI provider bills the same way: you pay per token roughly ¾ of a word , with separate rates for input what you send and output what the model writes back . Output is usually 3–5× more expensive than input. A model listed at $5 / $25 per million tokens costs $5 for every million tokens you send and $25 for every million it generates. Two discounts change the math dramatically: prompt caching cuts repeated input costs by up to 90% critical for chatbots that resend conversation history , and batch processing takes ~50% off when you can wait for results. Our calculators account for both — most "how much will this cost" articles don't, which is why their estimates run 2–3× too high or too low.