Beta aicost.ai cost engines are in beta. Estimates only. See Terms.

45% + 30% + 18% is not 93% off.

Each optimization lever applies to what the previous one left behind. See your real stacked saving, exactly how much the naive sum overstates it, and which lever returns the most per engineering day.

What this calculator does

Stacks routing, caching, batching and compaction the way they ACTUALLY combine — multiplicatively on the remaining base — and shows the gap between that and the naive sum vendors pitch.

Why use it
  • 40% + 30% + 20% is not 90%. Levers apply to what is left after the previous lever, and this engine prices the overstatement in dollars.
  • Order matters for attribution: impact order is the market ranking; effort order is what a two-engineer team should ship first. The order input is a validated enum.

Stack Savings Calculator

Your bill + the levers you'd pull → the compounded result, the naive-sum overstatement, and the pull-first ranking.
📊 Not sure of a value? Fields with a ▾ Typical pill offer broad industry ballparks (sourced typical ranges) so you can move forward now — your result gets more accurate as you replace them with your own measured numbers. Values marked * are rough estimates.
Hint: The bill before any of these levers.
% saving
Send each request to the cheapest model that can handle it. Published range 40-85%.
% saving
Repeated context billed at the cached rate. Published range 45-90% on the cacheable share.
% saving
Latency-tolerant traffic through the batch window, typically ~50% off that slice.
% saving
Shrink the context itself. Net of overhead - use the Context Compaction calculator for your real figure.
Hint: Order changes each step's dollar figure (later levers act on a smaller bill) - the TOTAL is the same either way.

Results

Enter your bill, tick the levers you'd realistically pull, then calculate - you get the compounded truth, the naive-sum overstatement, and which lever to pull first.
📖 Data sources & methodology 150 text models · 9 embeddings · 40 vision · 55 audio · 8 vector DBs across 10 vendor pages · last verified 2026-09-11

Methodology

  • All prices are USD per 1 million tokens, current as of 2026-09-11.
  • Vendor-published values have no mark. Inferred/extrapolated values are marked with * and listed below.
  • Batch API discounts are 50% off standard rates across providers that offer Batch mode.
  • Prompt caching discounts vary by provider (typically 80-90% off cached input tokens).
  • Regional data-residency surcharges (Anthropic 1.1x, OpenAI 1.1x, Google regional tiers) are NOT included in base rates.
  • Long-context pricing tiers apply when input exceeds model threshold.
  • Embedding prices are input-only (no output tokens generated).

Primary sources

Last-verified date is the most recent successful daily snapshot (aicost_pricing_snapshots) or, when no snapshot exists yet, the latest successful crawler run (aicost_crawler_runs). 10 of 10 vendors are currently verified. Aggregator services (TokenCost, AI Pricing Guru, etc.) are not listed.

Anthropic
2026-09-11
https://www.anthropic.com/pricing
Daily snapshot since Sep 2023 · 675 days captured
Anthropic Docs
2026-09-11
https://platform.claude.com/docs/en/about-claude/pricing
Daily snapshot since Sep 2023 · 675 days captured
OpenAI
2026-09-11
https://openai.com/api/pricing/
Daily snapshot since Sep 2023 · 676 days captured
Google AI
2026-09-11
https://ai.google.dev/gemini-api/docs/pricing
Daily snapshot since Dec 2023 · 651 days captured
Google Vertex
2026-09-11
https://cloud.google.com/vertex-ai/generative-ai/pricing
Daily snapshot since Dec 2023 · 651 days captured
DeepSeek
2026-09-11
https://api-docs.deepseek.com/quick_start/pricing
Daily snapshot since May 2024 · 590 days captured
xAI
2026-09-11
https://x.ai/api
Daily snapshot since Nov 2024 · 508 days captured
Mistral
2026-09-11
https://mistral.ai/pricing
Daily snapshot since Dec 2023 · 649 days captured
Cohere
2026-09-11
https://cohere.com/pricing
Daily snapshot since Sep 2023 · 675 days captured
Voyage AI
2026-08-11
https://docs.voyageai.com/docs/pricing

Inferred values (marked with * in calculator tables)

Derived from industry conventions, not directly published by the vendor. Typical conventions: cached input = 10% of base (90% off), Batch API = 50% of base (50% off).

Vendor / Model Field Why it’s inferred
Anthropic — Claude Sonnet 4.6 cachedInput Derived at 10% of input rate — Anthropic publishes 90% cache-hit discount on this tier.
Anthropic — Claude Sonnet 4.5 cachedInput Derived at 10% of input rate; same 90% cache-hit convention as Sonnet 4.6.
Anthropic — Claude Sonnet 4.5 batchInput Derived at 50% of standard input — Anthropic documents uniform 50% Batch discount.
Anthropic — Claude Sonnet 4.5 batchOutput Derived at 50% of standard output — Anthropic documents uniform 50% Batch discount.
Anthropic — Claude Haiku 4.5 cachedInput Derived at 10% of input rate — Anthropic 90% cache-hit discount convention.
OpenAI — GPT-5.4 Mini cachedInput Derived at 10% of input — OpenAI documents automatic 90% discount on cache hits across GPT-5.x tier.
OpenAI — GPT-5.4 Nano cachedInput Derived at 10% of input — OpenAI 90% cache-hit convention.
OpenAI — GPT-5.4 Nano batchInput Derived at 50% of input — OpenAI Batch API uniform 50% discount.
OpenAI — GPT-5.4 Nano batchOutput Derived at 50% of output — OpenAI Batch API uniform 50% discount.
OpenAI — GPT-5.4 Pro cachedInput Derived at 10% of input — OpenAI 90% cache-hit convention.
OpenAI — GPT-5.4 Pro batchInput Derived at 50% of input — OpenAI Batch API uniform 50% discount.
OpenAI — GPT-5.4 Pro batchOutput Derived at 50% of output — OpenAI Batch API uniform 50% discount.
OpenAI — GPT-5.2 cachedInput Derived at 10% of input; no residency uplift.
OpenAI — GPT-5.2 batchInput Derived at 50% of input.
OpenAI — GPT-5.2 batchOutput Derived at 50% of output.
OpenAI — GPT-5 cachedInput Derived at 10% of input.
OpenAI — GPT-5 batchInput Derived at 50% of input.
OpenAI — GPT-5 batchOutput Derived at 50% of output.
OpenAI — GPT-5.5 Pro cachedInput Derived at 10% of input — OpenAI does not publish a cached rate for *-pro models; using the family convention.
OpenAI — GPT-5.5 Pro batchInput Derived at 50% of input.
OpenAI — GPT-5.5 Pro batchOutput Derived at 50% of output.
OpenAI — GPT-5.2 Pro cachedInput Derived at 10% of input — pro-tier convention.
OpenAI — GPT-5.2 Pro batchInput Derived at 50% of input.
OpenAI — GPT-5.2 Pro batchOutput Derived at 50% of output.
OpenAI — GPT-5.1 batchInput Derived at 50% of input.
OpenAI — GPT-5.1 batchOutput Derived at 50% of output.
OpenAI — GPT-5 Pro batchInput Derived at 50% of input.
OpenAI — GPT-5 Pro batchOutput Derived at 50% of output.
OpenAI — GPT-5 Nano cachedInput Derived at 10% of input.
OpenAI — GPT-5 Nano batchInput Derived at 50% of input.
OpenAI — GPT-5 Nano batchOutput Derived at 50% of output.
Google — Gemini 3 Flash cachedInput Derived at 10% of input — Google caching discount convention ~90%.
Google — Gemini 3.1 Flash-Lite cachedInput Derived at 10% of input — Google caching convention.
Google — Gemini 3.1 Flash-Lite batchInput Derived at 50% of input — Google Batch API uniform 50% discount.
Google — Gemini 3.1 Flash-Lite batchOutput Derived at 50% of output — Google Batch API uniform 50% discount.
Google — Gemini 2.5 Pro cachedInput Derived at 10% of input.
Google — Gemini 2.5 Flash cachedInput Derived at 10% of input.
Google — Gemini 2.5 Flash-Lite cachedInput Derived at 10% of input — Google caching convention.
Google — Gemini 2.5 Flash-Lite batchInput Derived at 50% of input — Google Batch API uniform 50% discount.
Google — Gemini 2.5 Flash-Lite batchOutput Derived at 50% of output — Google Batch API uniform 50% discount.
xAI — Grok 4 (legacy) cachedInput Extrapolated at 25% of base.

Pricing is cross-verified against the LiteLLM community registry when available. Daily snapshots are kept in aicost_pricing_snapshots; every change is logged to aicost_price_changelog with old & new values for full audit trail. Read the full methodology →