whichdevtool?
Menu
StacksDirectory Pricing changes Glossary
VPS and cloud servers App hosting and PaaS Managed databases Transactional email APIs Email marketing and newsletters Domain registrars CDN, DNS and edge security Monitoring, uptime and error tracking Auth and identity Frontend and full-stack frameworks Backend frameworks UI component libraries AI model APIs File and object storage Payments and billing Background jobs, queues and workflows ORMs and database toolkits

AI model API (model maker) · by Google

Gemini API

Google's developer API for Gemini models, with a free tier on most Flash models (prompts used to improve Google's products) and paid tiers with spend caps.

Visit ai.google.dev ↗ Alternatives Free tier
Gemini API homepage
§1

Overview

The Gemini Developer API is Google's direct API for Gemini, separate from Vertex AI on Google Cloud. You get a key in Google AI Studio and can start on the free tier, which covers most current Flash, Flash-Lite, speech and Live models. Google states that free-tier content is used to improve its products; paid-tier content is not.

Paid pricing is per million tokens and varies by mode: Standard, Batch and Flex (both about half price) and Priority (about 1.8x). The newest Flash models (3.6, 3.7 and 3.8) are on introductory pricing of $0.75 in and $3.75 out until 31 December 2026, doubling from 1 January 2027, which matters if you are budgeting next year.

Paid accounts move through tiers that each carry a monthly spend cap and a rolling 10-minute spend limit, starting at $250 a month once a billing account is linked. New billing starts on prepaid credit before moving to pay-as-you-go. Exact free-tier rate limits are no longer listed in the docs; check the rate-limit page in AI Studio for your project.

§2

Pricing and plans

Free tier

Free input and output tokens on most Flash, Flash-Lite, TTS and Live models (not Gemini 3.1 Pro Preview), with rate limits shown per project in Google AI Studio.

At the limit Not stated The vendor does not say what happens at the limit, or we have not found it yet.

Plan Price What you get
Free $0 Limited models; content used to improve Google's products
Gemini 3.8 Flash $0.75 in / $3.75 out per 1M Introductory to 2026-12-31; $1.50 / $7.50 from 2027-01-01
Gemini 3.5 Flash-Lite $0.30 in / $2.50 out per 1M Free tier available
Gemini 3.1 Flash-Lite $0.25 in / $1.50 out per 1M Text/image/video input price; audio input costs more
Gemini 3.1 Pro Preview $2 in / $12 out per 1M Prompts up to 200K tokens; $4 / $18 above; no free tier
Batch / Flex 50% off e.g. Gemini 3.8 Flash batch at $0.375 / $1.875
Enterprise Custom Through Gemini Enterprise Agent Platform: provisioned throughput, volume discounts

Per 1M tokens in USD, read 2026-09-29. Gemini 3.6, 3.7 and 3.8 Flash are on introductory pricing that doubles on 2027-01-01. Pro prices rise for prompts over 200K tokens. Grounding with Google Search and Google Maps is not available on the free tier; paid use gets 5,000 free requests per month shared across Gemini 3.x models, then $14 per 1,000. Paid tiers carry monthly spend caps: Tier 1 $250 (linked billing account), Tier 2 $2,000 (after $100 paid and 3 days), Tier 3 $20,000 to $100,000+ (after $1,000 paid and 30 days), plus rolling 10-minute spend limits of $10, $50 and $200. Google no longer publishes exact free-tier RPM/RPD numbers in its docs; they are shown in AI Studio. Billing starts prepaid, then moves to pay-as-you-go.

Source: ai.google.dev/gemini-api/docs/pricing · prices as published, excluding tax.

§3

What it does

Free tier
Free input and output tokens on most Flash, Flash-Lite, TTS and Live models, rate-limited per project.
Batch and Flex
Half-price asynchronous or lower-priority processing on paid tiers.
Context caching
Cached input at about a tenth of the input price plus an hourly storage fee per 1M tokens.
Grounding
Google Search and Maps grounding with 5,000 free requests per month on paid tiers, then $14 per 1,000.
Spend caps
Tier-based monthly caps ($250, $2,000, $20,000+) and 10-minute spend limits.
Multimodal models
Text, image, audio, video input plus TTS, live audio, transcription and image-generation models.
§4

Strengths and limitations

Strengths

  • An ongoing free tier on current Flash models, not just one-off signup credit.
  • Low paid prices on Flash-Lite models ($0.25 to $0.30 per 1M input tokens).
  • Spend caps and 10-minute spend limits on paid tiers limit runaway costs.
  • Batch and Flex halve prices for non-urgent jobs.

Limitations

  • Free-tier prompts and responses are used to improve Google's products.
  • Gemini 3.1 Pro Preview and image models have no free tier.
  • Introductory Flash prices double on 2027-01-01.
  • Exact free-tier rate limits are not published in the docs, only in AI Studio.
  • Tier 1 accounts are capped at $250 a month until they have paid $100 and waited 3 days.
§5

Who it suits

Good for

  • Prototypes and hobby projects that need a free model API
  • Multimodal apps handling images, audio or video
  • High-volume, low-cost tasks on Flash-Lite

Look elsewhere if

  • Free-tier use with confidential data (content is used to improve Google's products)
  • Enterprises needing contracts, regional control and provisioned throughput (use Vertex AI)
§6

Pricing history

  • Gemini 2.5 limited to existing users

    Announced 2026-09-18: access to Gemini 2.5 models is limited to active users; Google recommends newer models for new projects. Source ↗

  • Gemini 3.7 Flash launched at introductory price

    Announced 2026-08-13: Gemini 3.7 Flash at $0.75 in / $3.75 out per 1M tokens through 2026-12-31; the pricing page lists $1.50 / $7.50 from 2027-01-01 for 3.6, 3.7 and 3.8 Flash. Source ↗

  • Gemini 2.0 Flash shut down

    Effective 2026-06-01: Gemini 2.0 Flash models were shut down; Google directs users to Gemini 3.5 and 3.1 models. Source ↗

  • Gemini Flex and Priority tiers

    Announced 2026-04-01: new Flex (about half price, lower priority) and Priority (higher price) inference tiers alongside Standard and Batch. Source ↗

  • Gemini API prepay and postpay billing

    Announced 2026-03-23: Prepay and Postpay billing plans launched in Google AI Studio, affecting existing accounts; billing now starts prepaid before moving to pay-as-you-go. Source ↗

  • Gemini Batch Mode launched

    Launched 2025-07-07: asynchronous Batch Mode for the Gemini API, now priced at 50% of standard rates on paid tiers. Source ↗

§7

Alternatives to Gemini API

Tool From Free option Stages
DeepInfra Inference provider (open-weight models)
Usage-based Paid
Scaleway Generative APIs Inference provider (EU-hosted open-weight models)
Usage-based Trial
GroqCloud Inference provider (open-weight models)
Usage-based Free tier
Replicate Model hosting API (image, video, audio and LLMs)
$0.09/hr Trial
OpenRouter Model router (unified API)
— Free tier
Mistral API (Mistral Studio) AI model API (model maker)
Usage-based Free tier

All AI model APIs →

§8

Questions

Is the Gemini API free?

There is a free tier covering most Flash, Flash-Lite, speech and Live models, with per-project rate limits shown in AI Studio. Pro Preview and image models are paid only.

Does Google train on Gemini API free tier data?

Google's pricing page says free-tier content is used to improve its products, and paid-tier content is not.

How much does Gemini 3.8 Flash cost?

$0.75 per 1M input tokens and $3.75 per 1M output tokens through 31 December 2026, then $1.50 and $7.50 from 1 January 2027.

What is the difference between the Gemini API and Vertex AI?

The Gemini API is Google's developer API through AI Studio with a free tier; Vertex AI (now Agent Platform) is the Google Cloud service with enterprise controls and partner models.

Sources read for this page