# Gemini Decisions API cost calculator: run it free, or from your agent Cost per 1,000 decisions on gemini-decision-1 next to Gemini Flash-Lite and Flash, from Google's own prices. ## Prompt Use looot to price [decisions] decisions a month on Google's gemini-decision-1 and a Gemini Flash model: [input tokens] input tokens and [output tokens] output tokens per decision. 1. Set up https://looot.ai/skill.md. 2. Read today's prices from https://aistudio.google.com/docs/pricing with the page to markdown job. 3. Work out cost per 1,000 decisions and per month: input tokens x input price, plus output tokens x output price on the generative model (gemini-decision-1 has 0 output tokens). 4. Return one table with each price's source link. ## What it needs Decisions per month, input tokens per decision, and optionally the output tokens a generative model writes back ## What comes back - cost per 1,000 decisions on gemini-decision-1 and three generative Gemini models - cost per month on each - how many times gemini-decision-1 each generative model costs - each price with a link to Google's pricing page and its read date ## Endpoints and providers None. The tool on the web page runs in the browser and calls no endpoint. ## What it costs Nothing. The tool on the web page runs in the visitor's browser: no account, no API call and no limit per hour. The prompt above runs the same job from your own looot account with current data, billed per call. ## Price a classifier switch See what moving a yes/no or routing prompt from a Flash model to the Decisions API changes on your monthly bill. ## Budget a router Type how many requests your agent routes a month and the tokens of one. The cost per 1,000 shows on every model. ## Check policy checks Count the shared input once and add each rule's own instruction tokens, then price thousands of checks a day. ## Plan a rubric grader Price scoring candidates against a rubric before you build it, with the source of every price one click away. ## How does this calculator work? Cost per decision = input tokens x the input price per 1M / 1,000,000. On a generative model, add output tokens x its output price per 1M / 1,000,000. gemini-decision-1 generates 0 output tokens, so Google bills input tokens only. The output field applies to the generative models. Per 1,000 decisions = cost per decision x 1,000. Per month = cost per decision x decisions per month. One decision here is one request with one question. Several questions about the same input in one request count the shared input once; add each question's own instruction and criteria tokens to the input. Both sides use the same input token count. Tokenizers and prompt wording differ between models, so read usage from your own responses. Generative output includes thinking tokens: Google's page bills them as output. Prices: Google's paid tier, Standard tab, read 2026-11-11. The free tier, Batch, Flex and Priority are not used. The Decisions API supports none of Batch, Flex, Priority or context caching. Cost only. The calculator says nothing about whether two models give the same answers. ## What does the Gemini Decisions API cost? Google bills gemini-decision-1 per million input tokens only. It generates 0 output tokens, so output is never billed, and text, image, video, audio and PDF input share one price. The calculator above and the Gemini Decision 1 table on /models show the paid tier price as Google's pricing page lists it, read 2026-11-11. ## Is there a free tier? Yes. Google's pricing page lists gemini-decision-1 input as free of charge on the free tier, in Google AI Studio and the Gemini API. The same page says free tier data is used to improve Google's products. Rate limits are on Google's rate limits page, linked from the model page. ## Why can a decision cost less than a generative call? Two reasons, both on Google's pricing page: gemini-decision-1 has a lower input price per million tokens than the Flash models compared here, and it writes no output. A generative model bills the label it writes back, and its thinking tokens, at its output price. The calculator shows the difference for your own token counts. ## Does asking more questions in one request cost more? Only by the tokens of each extra question. Google's Decisions API guide says the shared input counts once per request, and each question adds its own instruction and criteria tokens. A request takes 1 to 1,000 questions within 262,144 input tokens. ## Can Batch or context caching make it cheaper? Not on the Decisions API. Google's guide says it supports none of context caching, Batch API, Flex or Priority, and repeated input across requests counts in full. The Flash models have Batch and Flex prices on Google's page; this calculator uses the Standard price on every model. ## Does it give the same answers as Gemini Flash? The calculator compares cost only. Google's docs say gemini-decision-1 returns calibrated probabilities with a confidence for yes/no, choice and rubric questions. Google's guide says to set thresholds from labeled examples of your own traffic: test both models on them before you switch. ## Is the calculator free? Yes. It runs in your browser, needs no account and makes no API call. Nothing you type is sent anywhere. ## Related tools - /free-tools/llm-token-cost-calculator - /free-tools/token-counter - /free-tools/ai-model-comparison ## Last reviewed 2026-11-11.