Google AI

Google AI APIs for Gemini, Nano Banana & Veo

Build reasoning agents and multimodal apps, generate and edit images, and use supported Google video models through one LinkModel account.

Provider overview

About Google AI

Google develops the Gemini family for language, reasoning, multimodal understanding, and agentic workflows; Nano Banana models for native image generation and editing; and Veo for high-fidelity video generation. LinkModel only presents a model as available when it appears in the live catalog.

Explore Google language, image, and video APIs

Choose Gemini for language, reasoning, coding, and multimodal understanding; Nano Banana for image generation and editing; or a listed Veo model for video. The catalog below only shows Google models currently available through LinkModel.

7 models listed

Veo video APIs

Generate high-fidelity video from text or images with the Veo models currently listed on LinkModel. Open a live model page to verify native audio, resolution, duration, frame controls, lifecycle status, and pricing.

Gemini Omni Flash Preview
GoogleText-to-Video

gemini-omni-flash-preview

Google DeepMind preview multimodal video model for 10-second generation and conversational editing from text, image, and video inputs.

Starts from$1.5 / 1M inTry it

Nano Banana image APIs

Create and edit images with Google's Gemini-native image models. Compare all-around, high-throughput, and professional production options according to the models currently listed on LinkModel.

Nano Banana Pro
GoogleText-to-Image

gemini-3-pro-image-preview

Google's flagship image generation and editing model built on Gemini 3 Pro, featuring up to 4K resolution, precise multilingual text rendering, real-time Google Search grounding, and studio-quality creative controls.

Starts from$0.0975 / imageTry it
Nano Banana
GoogleText-to-Image

gemini-2.5-flash-image

Nano Banana (`gemini-2.5-flash-image`) is Google's natively multimodal image generation and editing model designed for speed and efficiency, supporting text-to-image, conversational editing, multi-image composition, and character consistency.

Starts from$0.225 / 1M inTry it
Nano Banana2
GoogleText-to-Image

gemini-3.1-flash-image-preview

Nano Banana (gemini-3.1-flash-image-preview) is a highly multifunctional generative model designed for speed, accuracy, and creative flexibility. It excels at transforming text prompts into stunning visual effects while providing advanced composition and style transfer capabilities.

Starts from$0.05 / imageTry it

Gemini language and multimodal APIs

Compare Google models for reasoning, coding, long-context work, agents, structured outputs, and multimodal understanding across text, image, audio, video, and document inputs.

Gemini3 Flash Preview
GoogleChat

gemini-3-flash-preview

A cost-efficient ultra-fast multimodal large model developed by Google DeepMind, equipped with dynamically adjustable deep reasoning, native four-modal parsing, million-token long context and stable batch tool calling, optimized for low-latency high-concurrency scenarios including enterprise agents, high-frequency API services, coding assistance, bulk audio-video processing and consumer chat applications。

Starts from$2.25 / 1M outTry it
Gemini2.5 Flash
GoogleChat

gemini-2.5-flash

Google's next-gen lightweight multimodal model featuring ultra-fast inference, native multimodal fusion, and massive context capacity, optimized for high-frequency interactions, real-time responses, and cost-efficient data processing.

Starts from$1.875 / 1M outTry it

Compare Google models and API pricing

Among the Google models currently available on LinkModel, start with Gemini 3.1 Pro Preview for difficult reasoning and coding, Gemini 3.5 Flash for balanced production work, or Gemini 3.1 Flash-Lite for efficient high-volume tasks. Choose Gemini 3.1 Flash Image for general image generation, Flash-Lite Image for throughput, or Gemini 3 Pro Image for professional production. Use Veo only when a matching video model appears in the live catalog.

Nano Banana image APIs

Model

Nano Banana

General-purpose image generation and editing

Best for

Everyday image creation and editing that needs a strong balance of instruction following, visual quality, speed, and cost.

Key capabilities

Text-to-image · image editing · reference inputs · text rendering

Official source ↗
Model

Nano Banana 2 Lite

High-volume image generation

Best for

Interactive and high-throughput image workflows where low latency and predictable cost matter most.

Key capabilities

Fast generation · image editing · efficient throughput · broad aspect ratios

Official source ↗
Model

Nano Banana Pro

Professional image production

Best for

Complex visual instructions, text-rich assets, grounded compositions, and professional outputs that benefit from stronger reasoning.

Key capabilities

Complex composition · high-resolution output · text rendering · reference images

Official source ↗

Gemini language and multimodal APIs

Model

Gemini 3 Flash Preview

Balanced production workloads

Best for

General-purpose reasoning, automation, coding, and knowledge work that needs a balance of capability, latency, and cost.

Key capabilities

Multimodal understanding · tool use · coding · production throughput

Official source ↗
Model

Gemini 2.5 Flash

High-volume, cost-sensitive tasks

Best for

Classification, extraction, assistants, and automation where low latency and cost-efficient throughput are the priority.

Key capabilities

Low latency · high throughput · multimodal input · structured output

Official source ↗

What can you build with Google AI APIs on LinkModel?

Combine Google language, image, and video capabilities in production workflows while keeping model access, credentials, usage, and billing together.

Reasoning agents and developer tools

Use Gemini for research, coding, structured outputs, tool-driven workflows, and multimodal reasoning across large inputs. Select the live tier that matches the required intelligence, latency, and cost.

Product and campaign imagery

Generate or edit product concepts, branded visuals, diagrams, and text-rich campaign assets with a supported Nano Banana model. Choose between balanced, high-throughput, and professional tiers.

Multimodal knowledge workflows

Analyze text, images, audio, video, and documents with a supported Gemini model, then combine retrieval, structured outputs, and tools in a production application.

Image-to-video creative pipelines

Create or edit a source image with Nano Banana, then animate it with Veo when a compatible video model is listed. The video workflow appears only when the live catalog exposes Google video generation.

Why run Google models through LinkModel?

Use supported Google model families alongside other leading providers without adding another account, credential, or billing workflow.

One key across Google model families

Use one LinkModel API key for the supported Gemini, Nano Banana, and Veo models enabled in the live catalog.

Google alongside other providers

Compare or combine Google models with other language, image, and video providers without maintaining a separate platform account for each family.

Centralized usage and billing

Review usage and pay-as-you-go charges from one LinkModel account while selecting the model that fits each workload.

Integrate Google AI models

Use one LinkModel credential to select a listed Google model, submit the matching request, and track usage from the same account.

  1. Authenticate with one API key

    Create a LinkModel API key and use it to authenticate requests for the Google models enabled for your account.

  2. Choose a live model and request schema

    Select a Gemini, Nano Banana, or listed Veo model, then open its model page to confirm the current identifier, supported task, inputs, and pricing units.

  3. Submit, observe, and iterate

    Send the request, handle the response or generation task, and compare usage before moving the workflow into production.

FAQ

Frequently asked questions.

Sources and editorial information

Editorial review

Model capabilities and selection guidance are reviewed against the official Google sources listed here.

Editorial content reviewed: September 1, 2026

Google and its model names belong to their respective owners. LinkModel is an independent API aggregation platform and does not imply a formal relationship.