Google

Google API & Models on GPTProto

  • Lower Than Official Pricing
  • OpenRouter-Grade Stability
  • No Subscriptions — Pay As You Go

Explore Google models for agentic coding, multimodal analysis, image creation and editing, video generation, and controllable speech. Compare the live Google models collection by capability, current pricing, and task fit, then access the right route with one GPTProto API key and shared balance.

Models

ModelInput → Output
Gemini 3.7 Flash1.05M$0.45 / $2.25 per 1M— / $0.04 per 1M
Input: TextInput: ImageInput: Document
Output: Text
Gemini 3.6 Flash1.05M$0.45 / $2.25 per 1M— / $0.04 per 1M
Input: TextInput: ImageInput: Document
Output: Text
Gemini 3.5 Flash Lite1.05M$0.18 / $1.50 per 1M$0.02 / $0.02 per 1M
Input: TextInput: ImageInput: Document
Output: Text
Gemini 3.1 Flash Lite Image—$0.02 per time—
Input: TextInput: Image
Output: Image
Gemini 3.1 Flash Image—$0.04 per time—
Input: TextInput: Image
Output: Image
Gemini 3.5 Flash1.05M$0.90 / $5.40 per 1M$0.09 / $0.09 per 1M
Input: TextInput: ImageInput: Document
Output: Text
Gemini 3.1 Flash Lite Preview1.05M$0.15 / $0.90 per 1M$0.01 / $0.01 per 1M
Input: TextInput: ImageInput: Document
Output: Text
Gemini 3.1 Flash Image Preview—$0.04 per time—
Input: TextInput: Image
Output: Image
Gemini 3.1 Pro Preview1.05M$1.20 / $7.20 per 1M$0.12 / $0.12 per 1M
Input: TextInput: ImageInput: Document
Output: Text
Gemini 2.5 Flash Preview Tts—$0.30 / $6.00 per 1M—
Input: Text
Output: Audio
Gemini 2.5 Pro Preview Tts—$0.60 / $12.00 per 1M—
Input: Text
Output: Audio
Gemini 3 Flash Preview1.05M$0.30 / $1.80 per 1M$0.03 / $0.03 per 1M
Input: TextInput: Image
Output: Text
Gemini 3 Pro Image Preview—$0.08 per time—
Input: TextInput: Image
Output: Image
Veo 3.1 Fast Generate Preview——$1.20 per time—
Input: TextInput: ImageInput: Video
Output: Video
Gemini 3 Pro Preview1.05M$1.20 / $7.20 per 1M$0.12 / $0.12 per 1M
Input: TextInput: ImageInput: Document
Output: Text
Veo 3.1 Generate Preview——$3.20 per time—
Input: TextInput: ImageInput: Video
Output: Video
Gemini 2.5 Flash Image Hd—$0.03 per time—
Input: TextInput: Image
Output: Image
Veo3.1——$0.50 per time—
Input: TextInput: Image
Output: Video
Veo3.1 Pro——$2.50 per time—
Input: TextInput: Image
Output: Video
Veo3.1 Fast——$0.50 per time—
Input: TextInput: Image
Output: Video
Gemini 2.5 Flash Image—$0.02 per time—
Input: TextInput: Image
Output: Image
Gemini 2.5 Flash Nothinking1.05M$0.18 / $1.50 per 1M$0.02 / $0.02 per 1M
Input: TextInput: ImageInput: Document
Output: Text
Gemini 2.5 Pro1.05M$0.75 / $6.00 per 1M$0.07 / $0.07 per 1M
Input: TextInput: ImageInput: Document
Output: Text
Gemini 2.5 Flash1.05M$0.18 / $1.50 per 1M$0.02 / $0.02 per 1M
Input: TextInput: ImageInput: Document
Output: Text
Veo3 Pro—$1.28 per time—
Input: TextInput: Image
Output: Video
Veo3 Fast—$0.48 per time—
Input: TextInput: Image
Output: Video
Veo3—$0.48 per time—
Input: TextInput: Image
Output: Video
Gemini 2.0 Flash—$0.06 / $0.24 per 1M$0.01 / $0.01 per 1M
Input: TextInput: ImageInput: Document
Output: Text

Pricing

Cost calculator

Multi-turn agent with cached context.
$0.45 / 1M$0.000675
$2.25 / 1M$0.0018
$0.045 / 1M$0.001125
Cost per request$0.0036

Top up

GPTProto vs official pricing.
40% off
Requests
You pay$100
You receive$100.00

Save$45.83 (31%)vs Google official

About Google

Google’s AI portfolio, developed by Google DeepMind, includes Gemini models for reasoning and multimodal understanding, Nano Banana models for image generation and editing, Veo for video, and Gemini TTS for speech. This page shows the Google models currently supported on GPTProto—not every model released by Google. Use the live cards to compare Model IDs, routes, capabilities, and pricing, then use the picker below to match a model to your workload. The collection is updated as GPTProto adds or changes supported routes; preview and legacy entries should be checked before production deployment.

Why Use Google Models with GPTProto?

Use Google models alongside other providers without splitting access, balance management, and model discovery across separate platforms.

One Key, Shared Balance

Use one GPTProto key and balance across supported Google models and other model providers.

Cross-Modal Catalog

Compare Gemini, Nano Banana, Veo, and speech routes in one live, task-oriented catalog.

Compatible Model Switching

Test compatible text models by changing the Model ID, then verify route-specific parameters before deployment.

Automatic Route Fallback

If an upstream service becomes unavailable, GPTProto can switch to another available route automatically.

How to Access Google Models

Get started with a Google model API through GPTProto.

  1. 1

    Create a GPTProto Account

    Sign up and open the dashboard to manage your balance, API keys, and usage.

  2. 2

    Generate an API Key

    Create a key in your dashboard and store it securely in your application or server environment.

  3. 3

    Call a Google Model

    Open a live model card, follow its route-specific documentation, and use the listed Model ID in your request.

Frequently asked questions

Which Google models are available on GPTProto?

The live catalog above is the source of truth for Google models currently supported on GPTProto. It is not a complete list of every model released by Google, and availability can change as routes are added, updated, or retired.

What is the difference between Gemini, Nano Banana, Veo, and Gemini TTS?

Gemini text-output models handle reasoning, coding, tools, and multimodal understanding. Nano Banana models generate and edit images, Veo models generate video, and Gemini TTS models turn text into speech. Always check the output modality on the selected model card.

Which Google model should I use for coding or high-volume tasks?

Use the picker above to compare stable options by workload. Coding agents usually need stronger tool use and reasoning, while extraction, parsing, and repetitive subagent tasks benefit from a Flash-Lite model’s efficiency.

Can a multimodal Gemini text model generate images, video, or speech?

Not necessarily. A model may accept images, video, audio, or PDFs while still returning text only. Choose a dedicated Image, Veo, or TTS route when your application needs generated media.

Do I need a separate Google API key?

No. Use your GPTProto API key and balance for supported Google models. Follow the selected model’s GPTProto documentation rather than copying a Google-native request without checking route differences.

How should I treat Preview or Legacy Google models?

Preview models can change and may have more restrictive limits. Legacy models may be retained only for compatibility. Check the live status and Model ID before production deployment, and prefer a stable model when one fits the workload.

Do all Google models use the same endpoint and request format?

No. Text, image, video, and speech routes can use different endpoints, payloads, parameters, and polling flows. Open the selected model page for the current request format and supported fields.

How does GPTProto handle data sent through the API?

GPTProto processes API inputs and outputs to complete requests and may retain them temporarily for transaction processing and error debugging. Technical usage metadata may also be logged. Data sent to an upstream model provider is subject to that provider’s policies.

Start with Google

One GPTProto API key for Google and other providers.

Get API Key