A student building a study chatbot
- Open Google AI Studio and create an API key
- Call gemini-3.8-flash on the free tier
- Stay within the rate limits shown in AI Studio
free plan works
Google · API platform
Gemini API and Google AI Studio
Google's developer API for Gemini models, with a free tier in Google AI Studio and paid tiers for production.
- Provider
- Latest confirmed model
- Gemini 4 Argon (gemini-4-argon)
- Pricing
- Free plan + paid
- Free plan
- Yes
- API
- Yes · free quota
- Status
- Generally available
- Last verified
- Oct 19, 2026
What is Gemini API and Google AI Studio?
The Gemini API gives developers programmatic access to Google's Gemini models for text, images, audio, video, speech and live voice. Google AI Studio is the browser workspace where you try prompts, get an API key and see your limits. A free tier covers many Flash and Flash-Lite models at lower rate limits, while paid tiers unlock higher limits and the flagship Gemini 4 Argon.
Getting started with a capable multimodal model cheaply, and scaling to production on the same API.
Why use Gemini API and Google AI Studio?
Practical benefits
- Officially documented free tier for many models
- Low-cost Flash-Lite options
- Batch API about 50% cheaper
- Wide modality coverage (live voice, TTS, transcription, image models)
Who it suits
- Students and hobbyists prototyping
- Developers needing multimodal input
- Teams wanting a free path from prototype to production
When another tool may fit better
- Sensitive data on the free tier (free-tier content is used to improve Google products)
- Users needing the flagship model for free
- Offline use
- Learning curve
- Beginner-friendly
- Skills needed
- Basic programming; AI Studio needs no code to experiment.
Example workflows
- Test a prompt in Google AI Studio, click to get an API key, call gemini-3.8-flash
- Move to Tier 1 by setting up billing when you need higher limits
What can it do?
- Free tierFree input/output tokens for selected models with lower rate limits; limits are shown in AI Studio.
- Gemini 4 Argon Depends on planFlagship reasoning model with a unified 1M context window; paid only.
- Flash and Flash-Lite modelsGemini 3.8 Flash and 3.5 Flash-Lite are recommended for new projects.
- Batch APIAbout 50% cheaper than standard pricing.
- Live API and speech modelsGemini 3.8 Live for low-latency voice, TTS and transcription models.
- Preview models PreviewIncluding Gemini 3.1 Pro Preview and Gemini Omni Flash for video.
Good for
- Prototyping AI features for free
- Multimodal analysis of images, audio and video
- Voice agents
- High-volume low-cost text processing
Where it runs
Pricing and plans
Free plan + paid Free tier for many Flash and Flash-Lite models with lower rate limits. Paid usage is per 1M tokens: Gemini 4 Argon $2 input / $10 output through Nov 30, 2026 (then $4 / $20); Gemini 3.8 Flash $0.75 / $3.75 through Dec 31, 2026 (then $1.50 / $7.50); Gemini 3.5 Flash-Lite $0.30 / $2.50. Batch is about half price.
| Plan | Price | Billing | Free trial / tier | Usage limits | Main inclusions | Model access | API access | Restrictions |
|---|---|---|---|---|---|---|---|---|
| Free tier | Free | usage-based | Free tier | Lower rate limits; exact limits shown in AI Studio, not on the docs page. |
|
e.g. Gemini 3.8 Flash, 3.6 Flash, 3.5 Flash-Lite, 3.1 Flash-Lite; not Gemini 4 Argon or 3.1 Pro Preview | Yes | Content used to improve Google products |
| Paid tiers (Tier 1-3) | Billed per 1M tokens by model; tiers upgrade automatically as the project qualifies. | usage-based | — | Higher rate limits per tier |
|
Full lineup | Yes | Requires billing set up in AI Studio |
Worked example (usage-based API pricing): sending 1,000,000 input tokens and receiving 200,000 output tokens at the listed gemini-4-argon rates ($2 and $10 per 1M) costs about $4 before tax. Real bills depend on the model, caching, batch discounts and any tier you qualify for.
API and developer access
- Official API
- Yes
- Documentation
- API docs (opens in a new tab)
- Authentication
- API key
- Pricing model
- per 1M tokens
- Free API quota
- Free tier: free input and output tokens on selected models with lower rate limits; per-model limits are shown in Google AI Studio.
- Rate limits
- Tiered (Free, Tier 1, 2, 3); see AI Studio for active limits
- Context / input limits
- 1M tokens (Gemini 4 Argon); others not stated on models page
- SDKs
- Not documented
- Streaming
- Not documented
- Batch processing
- Yes
- Structured output
- Not documented
- Tool / function calling
- Not documented
- Commercial use
- See the provider terms
- Data retention & privacy
- Free-tier content is used to improve Google products; paid-tier content is not, per the pricing page.
Published API rates
| Item | Price | Unit |
|---|---|---|
| gemini-4-argon input (through Nov 30, 2026) | $2 | per 1M input tokens |
| gemini-4-argon output (through Nov 30, 2026) | $10 | per 1M output tokens |
| gemini-4-argon input (from Dec 1, 2026) | $4 | per 1M input tokens |
| gemini-4-argon output (from Dec 1, 2026) | $20 | per 1M output tokens |
| gemini-3.8-flash input (through Dec 31, 2026) | $0.75 | per 1M input tokens |
| gemini-3.8-flash output (through Dec 31, 2026) | $3.75 | per 1M output tokens |
| gemini-3.8-flash input (from Jan 1, 2027) | $1.50 | per 1M input tokens |
| gemini-3.8-flash output (from Jan 1, 2027) | $7.50 | per 1M output tokens |
| gemini-3.5-flash-lite input | $0.30 | per 1M input tokens |
| gemini-3.5-flash-lite output | $2.50 | per 1M output tokens |
A free Gemini API and Google AI Studio account is not the same thing as free API access. The API allowance above is the provider's documented developer quota.
Advantages and disadvantages
Advantages
- Genuine free tier documented by Google
- Very low Flash-Lite prices
- Broad set of multimodal and speech models
Disadvantages
- Free-tier content is used to improve Google products
- Free-tier rate limits are not published per model on the docs page
- Several prices are introductory and scheduled to rise (Argon from Dec 1, 2026; 3.8 Flash from Jan 1, 2027)
Privacy: Free-tier prompts and responses are used to improve Google products; paid-tier content is not, per the official pricing page.
Real-world examples
A startup moving a prototype to production
- Set up billing in AI Studio to move to Tier 1
- Switch heavy reasoning requests to gemini-4-argon
- Use the Batch API for non-urgent jobs
needs paid plan
A product team adding voice
- Prototype a voice flow with Gemini 3.8 Live in AI Studio
- Integrate the Live API into the app
- Monitor usage per tier
needs API key
Gemini API and Google AI Studio alternatives
OpenAI API
Pay-per-token developer access to OpenAI's GPT models for building apps, agents and automations.
Gemini API and Google AI Studio vs OpenAI APIClaude Developer Platform (Claude API)
Developer access to Anthropic's Claude models with usage-based pricing, batch discounts and prompt caching.
Gemini API and Google AI Studio vs Claude Developer Platform (Claude API)OpenRouter
One OpenAI-compatible API key for hundreds of models from many providers.
Gemini API and Google AI Studio vs OpenRouterGroqCloud
Low-latency inference API for open models running on Groq's LPU hardware.
Gemini API and Google AI Studio vs GroqCloudCompare Gemini API and Google AI Studio with these side by side
Frequently asked questions
Is the Gemini API free?
Yes, there is an official free tier with free input and output tokens on selected models (such as Gemini 3.8 Flash and 3.5 Flash-Lite) at lower rate limits. The flagship Gemini 4 Argon is not available on the free tier.
What are the free-tier limits?
Google's rate-limits page directs you to Google AI Studio to see your active limits; it does not list fixed per-model free numbers.
Is my data private on the free tier?
Google's pricing page says free-tier content is used to improve its products, while paid-tier content is not. Avoid sending sensitive data on the free tier.
How much does Gemini 4 Argon cost?
$2 input and $10 output per 1M tokens through Nov 30, 2026, rising to $4 and $20 from Dec 1, 2026.
How do I upgrade from the free tier?
Set up billing in Google AI Studio. Once the project qualifies it moves to Tier 1, usually instantly.
What is Google AI Studio?
A browser workspace for trying Gemini models, creating API keys and checking usage and limits.