Google Gemini
API for Google's Gemini models, which read text, images, audio and video, with a free tier.
- Price
- Gemini 4 Argon: $2 input / $10 output per million tokens (rising Dec 1, 2026)
- Free plan
- Yes
- Setup
- Needs a developer
- Up and running
- Minutes to get a free key; an afternoon for the first version in your app.
What Google Gemini is for
Google's Gemini API gives your app AI that reads text, images, PDFs, audio and video in the same request. Its big draw for founders is a free tier on the Flash models, so you can build and test the prototype before entering a card.
How it plugs into your product
- 1Sign in to Google AI Studio and create an API key; the free tier works right away, no billing needed.
- 2Build the prototype on a free Flash model, calling it from your server.
- 3Before real users arrive, click "Set up billing", link a billing account and prepay at least $5 (Tier 1).
- 4Turn on auto-reload and a project spend cap, since a zero balance stops every key linked to the account.
Does it fit your idea?
It fits if
- Your product reads lots of PDFs, receipts, audio or video, like a tool that turns sales-call recordings into CRM notes.
- You want to prototype and show investors or first testers before paying anything.
- You need cheap volume: Flash-Lite models start at $0.25 in per million tokens, with no increase announced.
Look elsewhere if
- You'd run real customer data on the free tier: free-tier inputs can be read by human reviewers and used to improve Google's products.
- Your margin depends on today's price for the top model: Gemini 4 Argon doubles on December 1, 2026.
- Your users are in Europe or the UK and you hoped to stay free: there, only the paid service is allowed.
What people only find out after building
Read this before you build on it. Each item links to the official page that says so.
On the free tier, Google uses what you send to improve its products and human reviewers may read it. The terms say not to send sensitive, confidential or personal information. Paid usage isn't used this way.
Official source: ai.google.devPrices are going up: Gemini 4 Argon goes from $2/$10 to $4/$20 per million tokens on December 1, 2026, and Gemini 3.8 and 3.6 Flash double on January 1, 2027.
Official source: ai.google.devTier 1 has a $250 monthly spend cap. Reaching Tier 2 ($2,000 cap) takes $100 in paid spend and 3 days after the first payment; at the cap, the API pauses until the 1st of next month.
Official source: ai.google.devPrepaid credits expire 12 months after purchase and are generally non-refundable. When the balance hits $0, every linked key stops working until you add credits.
Official source: ai.google.devGoogle Cloud welcome credits generally can't be used for the Gemini API, especially on accounts opened after March 2, 2026.
Official source: ai.google.dev
Price
Gemini 4 Argon: $2 input / $10 output per million tokens (rising Dec 1, 2026)
Free tier with rate limits on the Flash and Flash-Lite models; Gemini 4 Argon is paid only.
- Price per million tokens (main model)
- Gemini 4 Argon: $2 in / $10 out
- Models
- Gemini 4, Gemini 3.x Flash, Nano Banana
- Free tier
- Rate-limited free tier on Flash models
Checked on Oct 28, 2026 · official pricing
What it costs in practice
Estimate: 1,000 users × 30 chats a month × about 2,000 tokens per chat (1,500 in, 500 out) = 45M input and 15M output tokens. On Gemini 3.8 Flash ($0.75 / $3.75 per million): about $90/month today and $180 from January 2027. On Gemini 4 Argon: about $240 today and $480 from December 1, 2026, which is above Tier 1's $250 cap.
Estimate from the official price. Check it before you decide.
At a glance
- Free plan: yes
- Open source: no
“Not stated” means the official site doesn’t say.
Alternatives
Compare side by side
Faundr
Picked your tools? Build it with AI, safely.
Faundr keeps your project’s memory, blocks what can’t be undone and tells you if it’s safe to launch, inside Claude Code and Codex.