Gemini API Pricing

This guide breaks down everything you need to know about Gemini API pricing: every model, every tier, and every discount. Whether you're budgeting for a side project or planning enterprise-scale usage, you'll find the exact numbers here.

At the end, we'll also show you how to access Gemini models for free using Puter.js: no API keys, no billing setup, no cost to you as a developer. Puter is the pioneer of the "User-Pays" model, which allows developers to incorporate AI capabilities into their applications while each user will cover their own usage costs.

How Gemini API pricing works

Google charges based on tokens, the pieces of text the model reads and generates. As a rough estimate, 1 token is approximately 4 characters or 0.75 words in English. You're billed separately for:

• Input tokens: the text you send to the model (your prompt, system instructions, conversation history)
• Output tokens: the text the model generates in response (including thinking tokens for reasoning models)

All text prices below are per million tokens (MTok) in USD.

A unique advantage of Google's Gemini API is that it offers a free tier with generous rate limits, making it one of the few major AI providers where you can get started at zero cost.

Pricing tiers

Google offers three access tiers:

Additionally, Batch processing is available at 50% off standard rates.

Model pricing

Gemini 3.1 Flash-Lite (latest lightweight model)

Gemini 3.1 Pro Preview (latest flagship)

Gemini 3 Flash Preview

Gemini 2.5 Pro

Gemini 2.5 Flash

Gemini 2.5 Flash-Lite

Specialized models

Legacy models

Which model should you choose?

• Gemini 2.5 Flash-Lite: The cheapest option at $0.10/$0.40 per MTok. Great for high-volume, low-complexity tasks like classification, extraction, and routing.
• Gemini 2.5 Flash: Best value for most applications. Strong reasoning at $0.30/$2.50 per MTok, with a free tier available.
• Gemini 2.5 Pro: The most capable current production model. Best for complex reasoning, research, and multi-step analysis.
• Gemini 3.1 Flash-Lite: The latest lightweight model with improved capabilities at $0.25/$1.50 per MTok.
• Gemini 3.1 Pro Preview: Latest flagship preview with top-tier performance. Use when you need the best quality available.

For most developers starting out, Gemini 2.5 Flash is the best value. It's highly capable, has a free tier, and at $0.30/$2.50 per MTok is one of the cheapest flagship-tier models available.

What does this cost in practice?

To give you a sense of real-world costs with Gemini 2.5 Flash ($0.30 input / $2.50 output per MTok):

With Gemini 2.5 Flash-Lite ($0.10/$0.40 per MTok), these costs drop by roughly 75%.

Gemini vs GPT vs Claude vs Grok: price comparison

How does Gemini stack up against competing models?

Gemini 2.5 Flash-Lite is one of the cheapest models available from any major provider, and Gemini 2.5 Flash offers an unbeatable combination of quality, price, and a 1M token context window. Plus, the free tier means you can test and prototype at zero cost.

Context caching pricing

Context caching reduces costs by reusing previously processed parts of your prompt across API calls. Cached tokens are served at a fraction of the standard input price.

Cached input is typically 90% cheaper than standard input. However, note that cache storage incurs an hourly cost, so caching is most cost-effective for frequently reused prompts.

Batch API pricing (50% off)

The Batch API processes requests asynchronously at half the standard price:

Batch processing is ideal for bulk tasks like document analysis, data extraction, or content moderation where you can tolerate some latency.

Image generation pricing

Imagen 4

Gemini 2.5 Flash (native image generation)

Video generation pricing

Music generation pricing

Audio pricing

Audio input tokens are priced at roughly 2-3x text token pricing. For example, with Gemini 2.5 Flash:

Embedding pricing

Tool and feature pricing

Google Search grounding

Google Maps grounding

$25 per 1,000 grounded prompts after free tier limits.

Code execution

Charged at the model's standard token rates, no additional per-invocation fee.

File search

$0.15 per million embedding tokens, plus standard retrieval costs.

Free tier details

Most Gemini models include a free tier with limited rate limits. Key details:

• Available for Gemini 2.5 Pro, 2.5 Flash, 2.5 Flash-Lite, 3 Flash Preview, and 3.1 Flash-Lite
• Rate limits vary by model (typically lower RPM and TPM than paid tiers)
• Content may be used to improve Google products (paid tier opts out of this)
• Great for prototyping and low-volume applications

Billing and payment

• Billed monthly based on actual usage
• Payments in USD
• Free tier available for testing and low-volume use
• Paid tier requires billing setup in Google AI Studio or Google Cloud
• Enterprise tier available with custom support and compliance

Tips to reduce your Gemini API costs

Here are practical ways to keep your bill down:

1. Start with Flash-Lite. At $0.10/$0.40 per MTok, Gemini 2.5 Flash-Lite handles many tasks well. Only upgrade to Flash or Pro when quality demands it.

2. Use the free tier for prototyping. Test your application logic without spending anything, then switch to paid when you're ready for production.

3. Leverage context caching. If you're sending the same system prompt or reference documents with every request, enable caching. Cached input is ~90% cheaper than standard input.

4. Batch non-urgent work. Use the Batch API for 50% off on bulk processing. Document analysis, data extraction, and analytics don't need real-time responses.

5. Stay under the 200K input threshold. For Pro models, input and output pricing jumps at 200K tokens. Keep prompts under this threshold when possible.

6. Trim your inputs. Remove unnecessary conversation history, compress system prompts, and avoid sending entire documents when a relevant excerpt will do.

7. Choose the right image quality. Imagen 4 Fast ($0.02/image) is 67% cheaper than Ultra ($0.06/image). Only use higher quality when you need it.

The free alternative: Puter.js

If you're a developer building an app that uses Gemini, there's a way to skip all of the above: no API keys, no billing setup, no rate limit management, and no cost to you.

Puter.js is a JavaScript SDK that gives you access to Gemini and 400+ other AI models directly from your frontend code, including chat, text-to-speech, image generation, and more. It uses a "User-Pays" model: each user of your app covers their own AI usage through their Puter account. You, the developer, pay nothing.

Here's what that means in practice:

Try it now

Add one script tag to your HTML and start using Gemini immediately:

<html>
<body>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        puter.ai.chat("Explain quantum computing in simple terms", {
            model: "google/gemini-2.5-flash"
        }).then(response => {
            document.body.innerHTML = response.message.content[0].text;
        });
    </script>
</body>
</html>

No API key. No backend. No billing. You can also use Gemini 2.5 Pro, Gemini 2.5 Flash-Lite, and every other Gemini model the same way.

You can also stream responses for a better user experience:

<html>
<body>
    <div id="output"></div>
    <script src="https://js.puter.com/v2/"></script>
    <script>
        async function streamResponse() {
            const response = await puter.ai.chat("Write a short poem about coding", {
                model: "google/gemini-2.5-flash",
                stream: true
            });
            const output = document.getElementById('output');
            for await (const chunk of response) {
                if (chunk?.text) {
                    output.textContent += chunk.text;
                }
            }
        }
        streamResponse();
    </script>
</body>
</html>

Why developers choose Puter.js over direct API access

• $0 infrastructure cost: Your users pay for their own usage, so your app costs nothing to run regardless of scale
• No API key management: No keys to rotate, no secrets to protect, no backend needed to hide them
• No rate limit headaches: Each user has their own limits, so one user's traffic never blocks another's
• More than just chat: Text-to-speech, image generation, and other AI capabilities are all available through the same SDK, no juggling separate APIs
• Access every AI provider: Switch between Gemini, GPT, Claude, Grok, DeepSeek, and more with one line of code, no separate accounts or billing for each
• Ship faster: Go from idea to production in minutes, not days of billing setup and backend configuration

Related

• Free, Unlimited Gemini API
• How to Get a Gemini API Key
• Free, Unlimited Google AI API
• OpenAI API Pricing
• Claude API Pricing
• Grok API Pricing
• Free, Unlimited OpenAI API
• Free, Unlimited Claude API
• Free, Unlimited AI API
• Free LLM API