Gemini API free tier
Gemini API free tier: models, limits and data use
The Gemini API free tier charges $0 for input and output on Gemini 3.8 Flash, 3.6 Flash, 3.5 Flash-Lite, 3.1 Flash-Lite and 3 Flash Preview, with no billing account. Gemini 4 Argon and 3.1 Pro Preview are paid only. Limits apply per project and daily quotas reset at midnight Pacific.
- Price on free models
- $0 input and output
- Billing account needed
- No
- Gemini 4 Argon
- Paid tier only
- Daily quota reset
- Midnight Pacific time
Updated
Which Gemini models are free
The table below shows each main text model's free-tier status and the paid price it falls back to when you upgrade.
Free models still need an API key from Google AI Studio before you can make requests.
| Model | Free tier | Paid price per 1M (input / output) |
|---|---|---|
| Gemini 4 Argon | No | $2.00 / |
| Gemini 3.1 Pro Preview | No | $2.00 / |
| Gemini 3.8 Flash | Yes | $0.75 / |
| Gemini 3.6 Flash | Yes | $0.75 / |
| Gemini 3.5 Flash-Lite | Yes | $0.30 / |
| Gemini 3.1 Flash-Lite | Yes | $0.25 / |
| Gemini 3 Flash Preview | Yes | $0.50 / |
What the free tier includes
- You get free input and output tokens on Gemini 3.8 Flash, Gemini 3.6 Flash, Gemini 3.5 Flash-Lite, Gemini 3.1 Flash-Lite and Gemini 3 Flash Preview.
- Context caching is also free of charge on Gemini 3.8 Flash.
- Other models with a free tier include Gemini 3.8 Flash TTS, Gemini 3.8 Flash-Lite TTS, the Gemini 3.8 Live models, Gemini 3.5 Transcribe, Gemini 3.5 Live Translate, Gemini Embedding 2, Gemma 4 and Gemini Robotics ER 2 Preview.
- Gemini 2.5 Pro, 2.5 Flash and 2.5 Flash-Lite have a free tier too, though since September 18, 2026 Google limits access to the 2.5 models to users who have actively used them before.
- Batch and Flex are not available on the free tier for Gemini 3.8 Flash, 3.6 Flash or 3 Flash Preview.
- On the five free text models, Grounding with Google Search and Google Maps is not available on the free tier through the API, though Google notes it can be tested in Google AI Studio. The exceptions are the Gemini 3.8 Live models, which support Search grounding on the free tier, and Gemini 2.5 Flash and 2.5 Flash-Lite, which get up to 500 free grounded requests per day for Search (shared between the two) and 500 per day for Maps.
How free-tier rate limits work
Google measures Gemini free tier rate limits in requests per minute (RPM), input tokens per minute (TPM) and requests per day (RPD). Some models also enforce tokens-per-day limits, and built-in tools have their own separate quotas.
These limits apply per project rather than per API key, which means creating extra keys inside the same project won't give you any extra quota. Daily RPD quotas reset at midnight Pacific time, and going over any of these limits returns an HTTP 429 RESOURCE_EXHAUSTED error.
Google doesn't publish fixed per-model free-tier numbers, so check your project's live limits at https://aistudio.google.com/rate-limit (and note that Google states specified rate limits are not guaranteed and actual capacity may vary).
Moving from free to paid
The table below shows how Google's usage tiers and spend caps scale once you move off the free tier, and you can check full Gemini API pricing for per-model token rates.
- You leave the free tier by linking a Cloud Billing account; new users default to Prepay and buy at least $5 of credits, while some eligible accounts can choose or are assigned Postpay instead.
- Upgrading from Free to Tier 1 usually takes effect instantly, while later upgrades to Tier 2 or Tier 3 take effect within 10 minutes.
- You can check the Projects page in Google AI Studio to see which tier each of your projects is on.
| Tier | How a project qualifies | Monthly spend cap | Spend limit per 10 minutes |
|---|---|---|---|
| Free | No billing account | Not applicable | Not applicable |
| Tier 1 | Active billing account linked | $250 | $10 |
| Tier 2 | $100 paid and 3 days since first payment | $2,000 | $50 |
| Tier 3 | $1,000 paid and 30 days since first payment | $20,000 to $100,000+ | $200 |
What Google does with free-tier data
- On unpaid API quota, and in Google AI Studio unless your account has access to a Cloud project with active billing or is a Workspace enterprise account, Google uses your prompts and responses to improve its products.
- Human reviewers may read, annotate and process your API input and output after it is disconnected from your Google account, API key and Cloud project.
- Google tells users not to submit sensitive, confidential or personal information when using unpaid services.
- On the paid tier, your prompts and responses are not used to improve Google products, except on the invite-only Contributor tier.
- Users in the European Economic Area, Switzerland and the United Kingdom get the paid tier data terms even when using unpaid quota.
- Any app you make available to users in the EEA, Switzerland or the UK must use the paid tier.
The Gemini API and Google AI Studio are available in 230 countries and territories to users aged 18 or older.
Gemini 4 Argon without per-token billing
Google's free tier excludes Gemini 4 Argon, so calling it directly through Google requires a linked billing account. If you already pay for a Google AI Pro or Ultra plan, Plan2API turns that Gemini subscription into an API key for OpenAI-compatible Chat Completions calls, with models such as gemini/gemini-4-argon-high and gemini/gemini-3.8-flash-high, each with a 1,048,576-token context window. Requests count against your subscription's own usage limits instead of per-token charges.
You can connect your subscription on the Plan2API Free plan for $0 with no credit card required. It gives you 1 connected subscription, 2 API keys and 50 chat requests a day (resetting at 00:00 UTC) at up to 1 request per second with bursts up to 20 and 4 requests at once.
Use the AI subscriptions you already pay for as one OpenAI-compatible API key.
- Free: 1 subscription, 50 requests a day, no card
- Pro: $12 a month
FAQ
Is the Gemini API free?
Yes, the Gemini API is free for Gemini 3.8 Flash, Gemini 3.6 Flash, Gemini 3.5 Flash-Lite, Gemini 3.1 Flash-Lite and Gemini 3 Flash Preview on the free tier, and you don't need a billing account to use them. Flagship models like Gemini 4 Argon and Gemini 3.1 Pro Preview are paid only and aren't available on the free tier.
What are the Gemini API free tier rate limits?
Gemini API free limits are set per project as requests per minute (RPM), input tokens per minute (TPM) and requests per day (RPD), and you have to view your active numbers inside Google AI Studio at https://aistudio.google.com/rate-limit. Google doesn't publish fixed per-model free-tier limits and states that specified limits aren't guaranteed.
Is Gemini 4 Argon free on the API?
No, Gemini 4 Argon has no free tier on the Google API. Through November 30, 2026, it costs $2.00 per 1M input tokens and $10.00 per 1M output tokens on a paid billing account.
Does Google use free Gemini API data for training?
Yes, prompts and responses sent on unpaid quota (and in Google AI Studio, unless your account can access a billed Cloud project or is a Workspace enterprise account) are used to improve Google products and may be read and annotated by human reviewers after being disconnected from your account, key and project. Paid-tier data isn't used to improve Google products, and users in the EEA, Switzerland and the UK get the paid data terms even on unpaid quota.
When do Gemini API daily limits reset?
Requests per day (RPD) quotas on the Gemini API reset at midnight Pacific time.
Sources
- Google: Gemini API pricingai.google.dev
- Google: Gemini API rate limitsai.google.dev
- Google: Gemini API Additional Terms of Serviceai.google.dev
- Google: Gemini API billingai.google.dev
- Google: Available regionsai.google.dev
- Google: Gemini API changelogai.google.dev