# Calcis

> Pre-flight LLM cost estimation. Know what every API call will cost before you make it. Live pricing for 28 models across OpenAI, Anthropic, and Google, with 52 dated price changes on file.

## Primary surfaces

- [Estimator](https://www.calcis.dev/estimator): Paste a prompt, get an exact token count and cost across every tracked model.
- [Pricing index](https://www.calcis.dev/pricing): The canonical price table for every model, sorted by input cost.
- [Models](https://www.calcis.dev/models): One page per model with full pricing, context window, capabilities, and lifecycle status.
- [Compare](https://www.calcis.dev/compare): Side-by-side cost and capability comparisons between any two models.
- [Calculators](https://www.calcis.dev/calculators): Workload-shaped cost calculators (chatbot, RAG, classification, embedding, coding agent, summarisation).
- [Session simulator](https://www.calcis.dev/session): Multi-turn cost projection that accounts for conversation history compounding.

## Workload calculators

- [Classification API cost calculator](https://www.calcis.dev/calculators/classification-cost): Tagging, labelling, routing, and moderation workloads. Short inputs, tiny outputs, huge volume: exactly the shape the cheapest models were built for.
- [Embedding API cost calculator](https://www.calcis.dev/calculators/embedding-cost): Compute the cost of embedding a corpus. One-off index builds, continuous indexing, and query-time embedding are all priced here.
- [Coding agent cost calculator](https://www.calcis.dev/calculators/coding-agent-cost): Agentic coding loops are the most expensive LLM workload there is: many tool calls, big context windows, long outputs. Cost yours honestly.
- [Summarisation API cost calculator](https://www.calcis.dev/calculators/summarisation-cost): Cost out a batch of document summaries across every major LLM. Long input, short output: the inverse of a chatbot.
- [Chatbot API cost calculator](https://www.calcis.dev/calculators/chatbot-cost): Estimate what a production chatbot costs per conversation and per month across every major LLM: GPT-5, Claude, Gemini: with realistic defaults.
- [RAG pipeline cost calculator](https://www.calcis.dev/calculators/rag-cost): Cost out a retrieval-augmented generation pipeline: embedding queries, retrieving chunks, and paying for the context-heavy chat call on top.

## Per-provider pricing

- [OpenAI pricing](https://www.calcis.dev/pricing/openai): GPT-5, GPT-5.4, GPT-5.5, GPT-4.1, GPT-4o, o3, o4-mini.
- [Anthropic pricing](https://www.calcis.dev/pricing/anthropic): Claude Opus 4.7, Sonnet 4.6, Haiku 4.5.
- [Google pricing](https://www.calcis.dev/pricing/google): Gemini 2.5 Pro/Flash/Flash-Lite, Gemini 3 family preview.

## Data and citations

- [Pricing changelog](https://www.calcis.dev/changelog): Every dated price change with provider source URL.
- [Q2 2026 pricing report](https://www.calcis.dev/reports/llm-pricing-q2-2026): Quarterly retrospective with cost trends and rate-of-change data.
- [Methodology](https://www.calcis.dev/methodology/session-quotas): Published methodology for the subscription-quota predictor (primary-source citations).
- [RSS feed](https://www.calcis.dev/feed.xml): Subscribe to every pricing change.
- [Sitemap](https://www.calcis.dev/sitemap.xml): Full crawl manifest.

## Distribution

- [REST API](https://www.calcis.dev/api-docs): `POST /api/v1/estimate` for programmatic cost estimation.
- [GitHub Action](https://www.calcis.dev/api-docs#github-action): Drop-in PR cost commenter (`rc397/calcis-action@v1`).
- [npm: calcis](https://www.npmjs.com/package/calcis): CLI for terminal-based estimation.
- [npm: @calcis/pricing](https://www.npmjs.com/package/@calcis/pricing): Machine-readable pricing dataset.

## About

- [What is pre-flight LLM cost estimation?](https://www.calcis.dev/what-is-preflight-llm-cost-estimation): The problem Calcis solves, in plain English.
- [Idea](https://www.calcis.dev/idea): Why this product exists and the design principles behind it.
- [Privacy policy](https://www.calcis.dev/privacy)
- [Terms of service](https://www.calcis.dev/terms)