Changelog

Product updates

Every release of Calcaas — new model support, pricing-engine improvements, and product features. Newest first.

v3.8.0Latest

Usage Analytics — track your real AI spend

Calcaas now closes the loop. Beyond modeling what your AI product should cost, you can track what your AI tools actually cost. Install the open-source calcaas-sync CLI, link each machine with a per-device key, and your dashboard fills with real Claude Code token usage — broken down by model, tool, and device, with daily trends, a live sync indicator, and monthly spend budgets. Only numeric aggregates ever leave your computer — never prompt content. Free for every signed-in account.

v3.7.0

Claude Fable 5 & Snowflake Cortex

Fresh from the weekly catalog sync. Anthropic's Claude Fable 5 ($10/$50 per 1M) is now in the picker across Anthropic, Vertex, AWS Bedrock, and Azure AI. We've also added Snowflake Cortex as a new provider — 19 models including Cortex-hosted Claude, DeepSeek R1, Llama 3.1/3.3/4, Mistral Large2, and OpenAI GPT-4.1 and GPT-5, plus MiniMax M3, Kimi K2.6 on Azure, and Ministral 8B. The chat-model catalog now spans 1,653 models across 46 providers.

v3.6.0

Claude Opus 4.8 & June Pricing Refresh

The latest weekly catalog sync is live. Claude Opus 4.8 is now in the picker across Anthropic, Vertex, and AWS Bedrock, alongside the GPT-5 family on Oracle Cloud, Gemini 3.1 Flash Lite, and new open-weight models like Step 3.7 Flash, Qwen3.7 Max, and Kimi K2.6. Several models also got cheaper — DeepSeek V4 Pro dropped 75% to $0.435/$0.87 per 1M, Qwen3.7 Max halved to $1.25/$3.75, plus lower cache-read rates across the Claude and GPT-4.1 families. The chat-model catalog now spans 1,626 models across 45+ providers.

v3.5.0

Model Recommendation Engine

Stop picking models blind. Tell Calcaas what you need — vision, reasoning, tool-calling, a context-window floor, a monthly budget — and it surfaces the cheapest model that qualifies at your real usage, capabilities shown at a glance. The benchmark now tags every model with what it can do, filters by Vision, Reasoning, or Tools, and sorts by newest release. Every model also carries full capability data — input modalities, context window, knowledge cutoff, and release date — under cleaner, canonical names.

v3.4.0

GPT 5.4 on Azure AI

Azure AI's GPT 5.4 family is now in the picker — GPT 5.4, GPT 5.4 Mini, and GPT 5.4 Nano, including dated snapshot variants — pulled in automatically by the weekly catalog sync. The chat-model catalog now spans 1,600+ models across 45+ providers.

v3.3.0

Branded PDF Quote Export

Hand clients a polished one-pager from inside the calculator. Pro users hit "Export PDF" to download a branded multi-page quote — summary table, per-package cards with profit and margin breakdown, full cost composition, and your assumptions. Renders entirely in the browser, en-US-locale-stable, byte-for-byte deterministic so the same inputs always produce the same PDF.

v3.2.0

Saved Scenarios, Quote History & Bookmarked Comparisons

Save full pricing configurations and reload them on any device — packages, costs, currency, and billing cycle all preserved. Every PDF you export is recorded in a quote history you can re-download anytime, byte-for-byte stable. And on /compare, signed-in users can bookmark provider pairs to revisit later.

v3.1.0

Auto Token Counter

Stop guessing average prompt sizes. Paste a real prompt — or a full system/user/assistant conversation — and get exact token counts via tiktoken for OpenAI models, plus community tokenizers for Claude, Gemini, Llama, and Mistral. One click applies the counts to your model card.

v3.0.0

Live Pricing Sync

Pricing for 1,500+ chat models, 100+ image models, and audio/video generation now syncs weekly from a continuously-updated model catalog. The picker covers AWS Bedrock, Azure OpenAI, OpenRouter, Vercel AI Gateway, and 80+ other providers — no more waiting for us to add yours.

v2.9.0

GPT-5.5 & Claude 4.7 Support

Added pricing for OpenAI's GPT-5.5, GPT-5.5 Pro, GPT-5.4 Mini and Nano (with short and long-context tiers), plus Anthropic's Claude Opus 4.7 and Sonnet 4.6.

v2.8.0

OpenAI GPT-5.4 Support

Integrated pricing models for OpenAI's latest GPT-5.4 and GPT-5.4 Pro, including context-length specific pricing tiers.

v2.7.0

Benchmark Intelligence

New interactive benchmarking suite. Compare models by cost, context, and provider with real-time charts and custom user profiles.

v2.6.0

OpenAI GPT-5.2 Support

Integrated pricing models for OpenAI's latest GPT-5.2 and GPT-5.2 Pro, enabling precise cost forecasting for advanced agentic and coding workflows.

v2.5.0

Audio Costing & VAT Control

Launched dedicated modeling for Audio workflows (TTS, STT) and comprehensive VAT controls to toggle between tax-inclusive and tax-exclusive pricing strategies.

v2.4.0

Claude Sonnet 4.6 Support

Added comprehensive pricing models for Anthropic's new Claude Sonnet 4.6 and Opus 4.6, including regional pricing variants.

v2.3.0

DeepSeek V3 & R1

Integrated DeepSeek's new efficient models including V3, R1, and distilled versions for cost-effective reasoning simulations.

v2.2.0

Custom Feature Costs

Introduced the ability to model fixed recurring costs (e.g. 'Priority Support' or 'Onboarding fees') alongside usage-based pricing.

v2.1.0

Video Generation Modeling

Added advanced calculators for video generation costs, allowing granular control over duration, audio, and per-second rates.

v2.0.0

Global Currency Expansion

Expanded real-time exchange rate support to over 35 global currencies, enabling accurate international pricing strategies.

Try the latest release.

The free tier includes every feature shipped above. Pro is a one-time $49.

Start modeling for free Try the calculator