Skip to content

> Google AI Studio

ai.google.dev

Google AI Studio gives free API access to Gemini models — free input and output tokens under per-model rate limits, not a depleting credit. Current-generation Flash models (including Gemini 3.8 Flash) are free-tier eligible. Paid tiers unlock higher limits, context caching, the 50%-off Batch API, and the most advanced models on the same API; free-tier data is used by Google to improve its products, paid-tier data is not.

up· 1651msbest-effort probe · checked 15h ago
Official free tier API keyFreemiumLow risk· conf 90%verified
Free credits
$15.00est.
Estimated based on high free-tier rate limits (RPD) vs paid input/output rates for equivalent usage.
Cheapest input /1M
$0.070
USD per 1M input tokens, best tracked model
Cheapest output /1M
$0.340
USD per 1M output tokens, best tracked model
Models tracked
8
Canonical models with normalized pricing
// source_analysisUprouter editorial analysis

// pros

  • A genuine free tier: free input and output tokens on eligible models — a rate limit, not a credit balance that depletes.
  • Current-generation Flash models are free-tier eligible, so prototyping runs on recent quality, not a legacy lineup.
  • Same API across tiers — upgrading unlocks caching, the Batch API (50% off), higher limits and advanced models without re-integration.
  • Grounding with Google Search includes 5,000 free search requests/month on the paid tier (shared across Gemini 3.x).
  • AI Studio web environment tests prompts and serves the same key ecosystem as the API.

// cons

  • Free-tier prompts and completions are used by Google to improve its products — the terms state this explicitly; send confidential data on the paid tier only.
  • Free-tier model access is limited: the most advanced Pro models, caching, and Batch are paid-only.
  • List prices carry dated intro periods (Gemini 3.8 Flash: $0.75/$3.75 per 1M in/out through Dec 31 2026, then $1.50/$7.50) — budget at the post-intro price.
  • Free-tier rate limits are modest and change without notice — fine for development, not for production SLAs.

The strongest free tier for Gemini work: build on it, but keep anything non-public out while you're on the free tier. For production, the same keys and API move to paid — the migration is a tier change, not a rewrite.

written by Mike Fleming, Uprouter editorial · verified against official sources September 16, 2026

// free_quota
$15.00estimated value

How we estimated this: the free allowance is converted to a dollar value using the provider’s own pay-as-you-go rates for the models a typical developer would reach for. When the allowance is metered in requests, tokens or minutes rather than dollars, we assume median usage of the cheapest capable model. Because assumptions are involved, the figure carries the est. flag — treat it as an order of magnitude, not a quote.

note: Estimated based on high free-tier rate limits (RPD) vs paid input/output rates for equivalent usage.

// pricinglast verified Sep 16, 2026
PlanTypeMonthlyInput /1MOutput /1MNote
Free tier (source-reported)free———Free tier marks models 'Free of charge', needs no credit card and has no expiry; limits vary by model and time (2026 reports e.g. Gemini 2.5 Flash ~250/day, Pro ~100/day, ~250K shared TPM) — verify current quotas in the AI Studio console. No free tier in the EEA/Switzerland/UK.
Gemini 3.8 Flash (Paid)payg—$0.750$3.75Rates valid through Dec 31, 2026; 50% discount for Batch API.
Gemini 3.5 Flash-Lite (Paid)payg—$0.300$2.50—
pricing_last_verified: Sep 16, 2026official pricing page

Pricing normalized from public sources — always verify with the provider.

// model prices

ModelInput /1MOutput /1MContext
Gemma 4 26B A4B $0.070$0.340262k
Gemma 4 31B$0.090$0.340262k
Gemini 2.5 Flash Lite$0.100$0.4001.0M
Gemini 3.1 Flash Lite Preview$0.250$1.501.0M
Gemma 2 27B$0.650$0.6508k
Gemini 3.8 Flash$0.750$3.751.0M
Gemini 2.5 Flash——1.0M
Gemini 2.5 Pro——1.0M
// faq
$ Does Google AI Studio have a free tier?

Yes — Google AI Studio offers a free tier that we value at roughly $15.00 in free credits (estimate — derived from rate-limited usage at pay-as-you-go prices). Always confirm current limits on Google AI Studio's official pricing page — free tiers change without notice.

$ How much does Google AI Studio cost per 1M tokens?

The cheapest model we track at Google AI Studio is $0.070 per 1M input tokens and $0.340 per 1M output tokens. This is normalized from Google AI Studio's published pricing — verify with the provider before purchasing, since prices change frequently.

$ Is Google AI Studio safe to use?

Uprouter rates Google AI Studio as low risk. Low data-integrity risk: Google's first-party API with published per-model pricing and explicit terms. The single issue to internalize before use is documented, not hidden: on the free tier, your prompts and completions are used to improve Google's products. Upgrading to the paid tier switches that off — which should decide what you send where. Risk ratings are editorial, evidence-based, and never influenced by affiliate relationships.

// community0 reviews

Raw community sentiment, shown unblended. Votes never feed into objective data fields like price, risk, or status — and never into sort order.

No published reviews yet — be the first.

// more_informationprice history · live status · risk & confidence · code snippets

price_history

No recorded changes yet.

live_status

full history →
up · 175msup · 461msup · 246msup · 243msup · 288msup · 792msup · 565msup · 183msup · 615msup · 334msup · 253msup · 179msup · 275msup · 279msup · 441msup · 237msup · 241msup · 270msup · 240msup · 194msup · 339msup · 254msup · 664msup · 145msup · 537msup · 170msup · 448msup · 293msup · 267msup · 1651ms
100%
30-probe uptime
7/30-day charts →

best-effort probes · not a guarantee · last 15h ago

CheckedStatusLatency
15h agoup1651ms
2d agoup267ms
3d agoup293ms
5d agoup448ms
6d agoup170ms
8d agoup537ms
9d agoup145ms
11d agoup664ms
12d agoup254ms
13d agoup339ms
14d agoup194ms
15d agoup240ms
16d agoup270ms
16d agoup241ms
17d agoup237ms
18d agoup441ms
19d agoup279ms
19d agoup275ms
20d agoup179ms
21d agoup253ms
22d agoup334ms
22d agoup615ms
23d agoup183ms
24d agoup565ms
25d agoup792ms
26d agoup288ms
27d agoup243ms
27d agoup246ms
28d agoup461ms
29d agoup175ms

Uprouter runs its own probes; best-effort, not a guarantee. Probe results depend on our network location and cadence — for production, always use the provider’s own status page.

risk_&_confidence

Low risk
90%

Low data-integrity risk: Google's first-party API with published per-model pricing and explicit terms. The single issue to internalize before use is documented, not hidden: on the free tier, your prompts and completions are used to improve Google's products. Upgrading to the paid tier switches that off — which should decide what you send where.

Confidence reflects how much verifiable evidence (official docs, probe history, community reports) backs this entry. Risk is our editorial assessment of operator reliability and terms — not financial advice.

code_snippets

# Google AI Studio's own API — get a key from their dashboard
curl https://YOUR-PROVIDER-ENDPOINT/chat/completions \
  -H "Authorization: Bearer THEIR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemma-4-26b-a4b-it",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

Direct to the provider — Uprouter receives nothing; verify their current pricing before purchasing.

// similar_providersscored by Official free tier signals

Ranked by neutral similarity signals only — live status, free-tier shape and free-credit proximity. Commercial relationships never influence this list.