We use cookies to keep the site working and, with your permission, to measure traffic and show relevant ads. Affiliate links set tracking cookies on the retailer's site when you click them. Cookie policy · Your privacy choices
Best Gemini API offer right now FREE TIERFree Gemini 3.8 Flash and Flash-Lite calls with no cardStart FreeSee all 4 offers
Checked on the official page
Billing explained in plain English
You sign up on Gemini API, not here
Nothing resold, ever
Gemini API free credits, trials and programs for November 2026
We may earn a commission when you sign up through links here. It never changes what you pay. Details
Gemini API does not issue public promo codes. There are no Gemini API promo codes. Sites listing a $300 Gemini code are repackaging the Google Cloud trial, which stopped applying to AI Studio for accounts opened after March 2, 2026. Real savings come from the free tier, the Batch API at half price, the Flex tier, context caching and startup credits spent through Vertex AI.
$0 on Flash, Flash-Lite and embedding models, rate limitedVerified Nov 2Sample
See details
Who qualifies: Any Google account holder 18 or over in a supported country, no billing account needed
Every active project in Google AI Studio starts on the free tier, where Gemini 3.8 Flash, 3.6 Flash, 3.5 Flash-Lite, 3.1 Flash-Lite, 3 Flash Preview and both Gemini Embedding models cost nothing. Per-project rate limits apply and are shown inside AI Studio.
Free tier prompts and responses may be used to improve Google products and reviewed by humans, except in the EEA, UK and Switzerland. Pro models, Gemini 4 Argon and Omni Flash are paid only. Limits change without notice.
Who qualifies: Any project on a paid tier with a linked billing account
Batch jobs run asynchronously at half the standard rate: Gemini 3.8 Flash drops to $0.375 per million input and $1.875 per million output tokens through December 31, 2026. Enqueued token limits scale by tier, from 3 million at Tier 1 to 1 billion at Tier 3 for 2.5 Flash.
Not available on the free tier. Jobs complete asynchronously and count toward tier spend caps.
$10 a month on AI Pro, $100 a month on AI UltraVerified Nov 2Sample
See details
Who qualifies: Active Google AI Pro or Google AI Ultra subscribers who activate Developer Program benefits
Since January 27, 2026 Google Developer Program premium benefits come bundled with Google AI Pro and Ultra subscriptions, including monthly Google Cloud credits usable on the Gemini API, Vertex AI and Cloud Run. Activate through the Developer Program benefits page.
Requires a paid Google AI subscription. Credits are issued monthly and follow Google Cloud credit terms. Subscription prices are set by Google and may change.
$0.75 input, $3.75 output per 1M tokensVerified Nov 2Ends Dec 31Sample
See details
Who qualifies: All paid tier projects, standard inference
Gemini 3.8 Flash and 3.6 Flash cost $0.75 per million input tokens and $3.75 per million output tokens through December 31, 2026, with standard pricing of $1.50 and $7.50 from January 1, 2027. Front-load evaluation and backfill work before the step up.
Standard tier prices. Flex, Priority, Batch and caching have their own rates on the same page.
Last checked November 2, 2026. 0 codes, 4 credits, programs and tips live.
Official Gemini API programs
Every way Gemini API itself hands out credits or free usage, checked on its own pages. The offers above are the ones worth acting on today.
Free Gemini Flash, Flash-Lite and embedding calls, rate limited
Any Google account holder aged 18 or over in a supported country, with an active project in Google AI Studio. No billing account needed. Gemini 3.1 Pro Preview, Gemini 4 Argon and Omni Flash are paid only.
Funded startups accepted into the Scale tier. Program credits attach to a Cloud Billing account and cover Google models on Vertex AI; they do not pay for AI Studio prepay balances.
Google AI Pro and Google AI Ultra subscribers who activate Google Developer Program benefits. The January 27, 2026 announcement names the Gemini API, Vertex AI and Cloud Run as eligible uses.
Any paid tier project. Batch jobs run asynchronously with per-tier limits on enqueued tokens, from 5 million at Tier 1 to 1 billion at Tier 3 for Gemini 2.5 Pro.
Automatic
Free tier that matters
Gemini 3.8 Flash input and output free of charge on the free tier
Gemini 3.6 Flash and 3.5 Flash-Lite free of charge, rate limited
Gemini 3.1 Flash-Lite and 3 Flash Preview free of charge
Gemini Embedding 2 and gemini-embedding-001 free of charge
Google AI Studio usage free in all available regions
Rate limits counted per project in RPM, TPM and RPD
Daily request quotas reset at midnight Pacific time
No spend limit on the free tier, $10 per 10 minutes at Tier 1
Recent program changes
Gemini 2.5 Pro and 2.5 Flash deprecated with routing from December 1 Google’s API changelog records that Gemini 2.5 Pro and 2.5 Flash are deprecated. From December 1, 2026 their requests route to Gemini 3.8 Flash and Gemini 3.5 Flash-Lite and are billed at those models’ rates. Access to 2.5 models had been limited to past users since September 18, 2026. Source
Flex and Priority inference tiers added beside Standard The API changelog adds Flex and Priority inference options beside Standard on April 1, 2026. Google’s price list now shows separate per-token prices per tier, with Flex input on Gemini 3.8 Flash at $0.375 per million against $0.75 Standard and $1.35 Priority. Source
Prepay and Postpay billing plans roll out in AI Studio The API changelog lists Prepay and Postpay billing plans for Gemini API usage in AI Studio. Google’s billing docs set a $5 minimum and $5,000 maximum prepay balance and say all keys on a billing account stop with HTTP 402 at $0. New Gemini API terms took effect the same day. Source
Usage tiers revamped and billing account spend caps introduced The API changelog records revamped usage tiers and new spend caps at the billing account level, following project-level spend caps on March 12, 2026. Google’s rate limits docs now list Tier 1 at $250, Tier 2 at $2,000 and Tier 3 at $20,000 to $100,000 or more per month. Source
The Gemini API is the only major model API that lets you call current Flash models without entering a card. Gemini 3.8 Flash, 3.6 Flash, 3.5 Flash-Lite, 3.1 Flash-Lite and both embedding models cost nothing on the free tier. Pro-class models, Gemini 4 Argon and the Omni video model are paid only. Here we cover what’s free, what the paid tiers cost, and which credits actually land in an AI Studio balance.
Access works per project, not per key. A new user who accepts the terms in Google AI Studio gets a default Google Cloud project and an API key on the free tier. Rate limits are enforced in requests per minute, input tokens per minute and requests per day, with daily counts resetting at midnight Pacific. The exact numbers for each model live inside AI Studio rather than in the public docs, and Google has changed them repeatedly.
What runs out first is the daily request quota on whichever model you lean on, followed by your patience with 429 errors. The free tier has no spend cap because nothing is billed. Moving to Tier 1 takes a billing account and, for most accounts since March 23, 2026, a prepay balance of at least $5. Free tier prompts may be read by human reviewers and used to improve Google products, so keep anything sensitive on the paid tier.
How to claim Gemini API credits
Open AI Studio and accept the termsGo to aistudio.google.com/apikey with a Google account. You must be 18 or older. First-time users accept the Gemini API terms, and AI Studio then creates a default Google Cloud project and an API key on the free tier.
Create or import a project keyOn the API keys page click Create API key. If you already use Google Cloud, open Dashboard, select Projects, click Import projects, pick the project and click Import, then create the key inside it. Keys created since May 28, 2026 are auth keys by default.
Check your tier and limitsOpen Dashboard and then Usage to see requests and tokens per model. The Billing Tier column on the Projects page shows Free. Per-model RPM and RPD numbers for your tier appear on the AI Studio rate limit page, not in the public docs, so bookmark it.
Set up billing when you need moreClick Set up billing in the Billing Tier column. Select your country, confirm contact details and a payment method, then choose an existing billing account or Add new billing account. Prepay at least $5, or pick Postpay if your account is offered it.
Add a project spend capOn the Spend page open Monthly spend cap and click Edit spend cap; project caps need an editor, owner or admin role. Tier caps are separate: $250 at Tier 1, $2,000 at Tier 2 and $20,000 or more at Tier 3. Set yours below the tier cap.
Route credits through Vertex AIStartup program credits and any Welcome credit granted after March 2, 2026 can’t pay an AI Studio balance. Enable the Vertex AI API in the same Google Cloud project and call Gemini there if you want those credits to cover inference.
Ways to stretch your Gemini API credits
Build on Flash-Lite first
Gemini 3.1 Flash-Lite costs $0.25 per million input tokens and $1.50 per million output on the standard paid tier, and it’s free on the free tier. Gemini 3.5 Flash-Lite is $0.30 and $2.50. At those rates a million 100-token prompts costs about $25 of input. Prototype here, then promote only the prompts that measurably need 3.8 Flash or a Pro model.
Ship before the introductory price ends
Gemini 3.8 Flash is priced at $0.75 per million input and $3.75 per million output through December 31, 2026, and the standard rate of $1.50 and $7.50 applies from January 1, 2027. Gemini 4 Argon doubles from $2.00 and $10.00 on December 1, 2026. Model your 2027 bill at the higher numbers now, so January isn’t a surprise.
Queue non-urgent work through Batch
The Batch API takes 50% off across models, so 3.8 Flash drops to $0.375 input and $1.875 output. Evaluation runs, embeddings backfills and nightly summaries rarely need a synchronous response, and that’s half your bill on those jobs. Watch the enqueued token ceiling, which is 3 million at Tier 1 for 2.5 Flash and 5 million for 2.5 Pro.
Try the Flex tier for slow traffic
Since April 1, 2026 the API offers Flex and Priority inference in addition to Standard. Flex input for 3.8 Flash is $0.375 per million against $0.75 Standard and $1.35 Priority. Flex suits background agents and pipelines that can absorb slower responses. If nobody is watching the response arrive, you’re overpaying on Standard.
Cache long system prompts
Context caching on 3.8 Flash bills cached input at $0.075 per million tokens, a tenth of the standard input price, plus an hourly storage fee per million tokens. If the same 20,000-token instruction block prefixes every call, caching pays for itself within a few hundred requests. Clear caches you no longer use, or the storage charge keeps ticking.
Prepay only what a month needs
Prepay balances can’t be moved to other Google Cloud services, and the API returns HTTP 402 the moment the balance hits $0 across every linked project. Top up in increments that match your monthly forecast, set the auto-reload limit low, and keep a separate project with its own cap for experiments. Don’t park money there that you might need elsewhere.
Keep sensitive prompts off the free tier
Under the terms effective March 23, 2026, unpaid services content may be read by human reviewers and used to improve products, while paid services content isn’t. In the EEA, UK and Switzerland the paid rules apply to all usage. A $5 prepay is cheaper than a data incident, so bill any project that touches customer data.
Gemini API billing, explained
On the free tier nothing is billed and no card exists, so there’s no trial to expire. You pay in rate limits instead: per-project RPM, TPM and RPD ceilings that Google sets per model and shows in AI Studio. When a limit trips you get a 429 error, not a bill. Since September 18, 2026 the 2.5 models are limited to projects that already used them, and in November 2026 Google deprecated 2.5 Pro and 2.5 Flash, routing requests to 3.8 Flash and 3.5 Flash-Lite from December 1.
Setting up billing moves a project to Tier 1 immediately. Most accounts prepay: the minimum is $5, the maximum balance is $5,000, usage is deducted in near real time and every API key on the billing account stops at $0. Accounts offered Postpay accrue charges and are billed at month end or when the tier cap is hit. Tier 2 needs $100 of cumulative payments plus 3 days; Tier 3 needs $1,000 plus 30 days. Caps are $250, $2,000 and $20,000 to $100,000 or more.
Tokens are billed per million for input and output, with document pages priced as images and audio input priced higher than text on most models. Grounding with Google Search bills only for requests that return at least one web URL, with a default limit of 1,500 requests a day per project. The $300 Google Cloud Welcome credit doesn’t pay for any of this on billing accounts opened after March 2, 2026. Credits granted earlier could be spent until they expired at 90 days.
Gemini API credits FAQ
is the gemini api free to use
Yes, within rate limits. Gemini 3.8 Flash, 3.6 Flash, 3.5 Flash-Lite, 3.1 Flash-Lite, 3 Flash Preview and the Gemini Embedding models are free of charge on the free tier, with no card needed. Gemini 3.1 Pro Preview, Gemini 4 Argon and Gemini Omni Flash have no free tier. Free tier prompts may be used to improve Google products, so free isn’t quite free.
what are the gemini api free tier rate limits
Google no longer publishes a per-model table. Limits apply per project across requests per minute, input tokens per minute and requests per day, daily quotas reset at midnight Pacific, and the current values are shown inside Google AI Studio. Free tier numbers were cut sharply in December 2025 and have moved since, so check your own project rather than a blog post.
does the gemini api free tier require a credit card
No. A Google account, acceptance of the terms and an active project in AI Studio are enough. A card only enters the picture when you click Set up billing, which moves the project to Tier 1 and, for most accounts, asks for a $5 minimum prepay. Nothing on the free tier can generate a charge.
can I use google cloud $300 credits on gemini api
Not in AI Studio on billing accounts opened after March 2, 2026. From that date the Welcome credit can’t be used for Gemini API or AI Studio usage. Welcome credits granted before the change could be spent until their 90-day expiry. The credit still covers Google models called through Vertex AI, so that’s the route if you want it applied.
how much does gemini 3.8 flash cost per million tokens
On the standard paid tier, $0.75 per million input tokens and $3.75 per million output tokens through December 31, 2026. From January 1, 2027 it’s $1.50 and $7.50. Batch halves those figures, Flex input is $0.375, Priority input is $1.35, and cached input is $0.075 plus hourly storage. On the free tier the model costs nothing.
does google train on gemini api data
On the free tier, yes. The terms effective March 23, 2026 let Google use content submitted to unpaid services to provide, improve and develop its products, and human reviewers may read and annotate it. Paid services content isn’t used to improve products and is logged only briefly for abuse detection. In the EEA, UK and Switzerland the paid rules apply to free usage as well.
how do gemini api usage tiers work
Tiers are set per billing account. Free needs only an active project. Tier 1 starts when you link a billing account and carries a $250 monthly cap and a $10 spend limit per rolling 10 minutes. Tier 2 requires $100 in cumulative payments plus 3 days and caps at $2,000. Tier 3 requires $1,000 plus 30 days with caps from $20,000 to over $100,000. Upgrades are automatic; you don’t apply for anything.
what happens when gemini api prepay credits run out
Every API key in every project linked to that billing account stops at the same moment and requests fail with HTTP 402. Prepay balances are consumed in near real time and can’t be transferred to other Google Cloud services. Turn on auto-reload with a monthly limit you’re comfortable with, or keep a small reserve project on a separate billing account for critical traffic.
FREE TIERFree Gemini 3.8 Flash and Flash-Lite calls with no card
