Use Gemini chat models, Nano Banana and Imagen for images, Veo and Gemini Omni for video, and Gemini text-to-speech — all through one Kie AI API key with pay-as-you-go billing.
Multimodal chat with adjustable thinking level and Google Search grounding.
Nano Banana and Imagen for images, Veo and Gemini Omni for video, and Gemini text-to-speech.
This table updates automatically as new Google models launch and are priced on Kie AI.
Explore all AI models on Kie AI →
| Model | Type | Launched | Price | Official price | Status |
|---|---|---|---|---|---|
| Gemini 3.8 Flash | Chat | सित॰ 2026 | $0.225 / $1.125 per 1M tokens | $0.75 / $3.75 | Latest |
| Gemini 3.7 Flash | Chat | अग॰ 2026 | $0.225 / $1.125 per 1M tokens | $0.75 / $3.75 | Available |
| Gemini 3.6 Flash | Chat | जुल॰ 2026 | $0.225 / $1.125 per 1M tokens | $0.75 / $3.75 | Available |
| Gemini 3.5 Flash | Chat | मई 2026 | $0.45 / $2.7 per 1M tokens | $1.5 / $9 | Available |
| Gemini 3.1 Pro | Chat | मार्च 2026 | $0.5 / $3.5 per 1M tokens | $2 / $12 | Available |
| Gemini 2.5 Pro | Chat | जन॰ 2026 | $0.38 / $3.00 per 1M tokens | $1.25 / $10 | Available |
| Gemini 3 Pro | Chat | नव॰ 2025 | $0.50 / $3.5 per 1M tokens | $2 / $12 | Available |
| Nano Banana 2.1 | Text to Image · Image to Image | अक्टू॰ 2026 | from $0.020 per image | $0.080 | Latest |
| Gemini 3.8 Flash-Lite TTS | Text to Speech | सित॰ 2026 | $0.35 / $4.20 per 1M tokens | $0.50 / $6.00 | Available |
| Gemini 3.8 Flash TTS | Text to Speech | सित॰ 2026 | $0.35 / $6.30 per 1M tokens | $0.50 / $9.00 | Available |
| Gemini Omni 1.1 Flash | Text to Video · Image to Video · Video Editing · Video to Video | अग॰ 2026 | from $0.315 per video | Available | |
| Gemini 3.1 Flash TTS | Text to Speech | जुल॰ 2026 | $0.7 / $14 per 1M tokens | $1 / $20 | Available |
| Gemini 2.5 Pro Preview TTS | Text to Speech | जुल॰ 2026 | $0.7 / $14 per 1M tokens | $1 / $20 | Available |
| Nano Banana 2 Lite | Text to Image · Image to Image · Image Editing | जुल॰ 2026 | from $0.02 per image | $0.0336 | Available |
| Gemini Omni | Text to Video · Image to Video · Video to Video | मई 2026 | from $0.315 per video | Available | |
| Nano Banana 2 | Text to Image · Image to Image | फ़र॰ 2026 | from $0.04 per image | $0.08 | Available |
| Nano Banana Pro | Text to Image · Image to Image | नव॰ 2025 | from $0.09 per image | $0.15 | Available |
| Veo 3.1 | Text to Video · Image to Video | अक्टू॰ 2025 | from $0.025 per video | Available | |
| Veo 3 | Text to Video · Image to Video | अक्टू॰ 2025 | See pricing | Available | |
| NanoBanana-Gemini 2.5 Flash Image Preview | Text to Image · Image to Image | अग॰ 2025 | from $0.02 per image | $0.039 | Available |
| Imagen 4 | Text to Image · Image to Image | अग॰ 2025 | from $0.02 per request | Available |
Kie AI serves Gemini chat models through the same API key as Nano Banana and Veo. Here is what the Gemini chat API supports today, based on the Kie AI API documentation.
Call Gemini models through the native Gemini format (streamGenerateContent) or an OpenAI-compatible chat/completions endpoint, using the model ID from the table above, such as gemini-3-8-flash; check the Kie AI API docs for the supported request fields.
Send text together with images, video, audio or PDF files in the same request.
Define your own functions for the model to call, or turn on Google Search grounding for up-to-date answers.
Set the thinking level to low or high, and request JSON-schema output when your app needs parseable responses. Gemini chat models currently support chat requests only and have not yet been adapted for agent use.
Access multiple Google Gemini API models through one platform. Use Gemini image API, Gemini AI API, and Gemini video API models together without managing separate providers or workflows.
Process text, images, and video through a unified Gemini API workflow. Build applications that understand and generate different types of content within one AI system.
Choose the right Gemini model API for each use case. Use lightweight models for speed, advanced models for reasoning, and specialized models for image and video generation.
Build products that need responsive performance and reliable scaling. Gemini AI API models support fast interactions and stable workloads across chat, image, and video applications.
Generate videos with realistic motion and native audio support through Veo API models. Create richer AI video experiences for creators, media tools, and production workflows.
Start testing with free credits and an online playground. Explore Gemini API capabilities and move from prototyping to production with clear documentation and easy integration.
Create image workflows with Google Gemini API models built for visual generation, editing, and content creation. Use Gemini image API models for creative tools, design products, and scalable AI applications.
Generate and edit images quickly with Nano Banana API. This Gemini image API is designed for fast visual workflows and supports prompt-based creation, image editing, and consistent outputs for creative applications.
Nano Banana 2 API improves image quality and consistency across generations. Use this Gemini model API for image workflows that need stronger subject alignment, cleaner visual details, and more stable outputs.
Nano Banana Pro API is built for more demanding creative tasks. It provides stronger detail handling and more refined results for marketing assets, visual production systems, and AI-powered design platforms.
Imagen 4 API combines high-fidelity image generation with improved text rendering and sharper visual detail. This Gemini image API works well for posters, marketing graphics, UI mockups, and branded content creation.
Gemini 2.5 Flash and Gemini 2.5 Pro API models balance speed, cost, and reasoning performance across different workloads. Use them for AI chatbots, coding assistants, document analysis, and applications that require fast responses with deeper understanding.
Gemini 3 Flash and Gemini 3 Pro API models combine multimodal understanding with stronger reasoning capabilities. Build AI agents, intelligent assistants, and scalable applications that process text, images, and complex workflows.
Gemini 3.1 Pro API is designed for advanced reasoning, larger context handling, and more demanding AI workloads. Use this Gemini model API for enterprise systems, long-document analysis, coding workflows, and sophisticated decision-making applications.
Build video products with Gemini API models designed for content generation and automated media workflows. Create scalable video experiences for creators, applications, and AI-powered platforms.
Build AI video products with Veo 3 API and Veo 3.1 API through one Gemini video API workflow. Generate high-quality videos with realistic motion, stronger scene consistency, cinematic output, and native audio generation for storytelling tools, content platforms, and scalable AI video generation applications.
Gemini Omni API combines text, image, and rich media understanding into one experience. Build interactive applications that connect video, conversation, and multimodal AI workflows in a unified system.
Use one Gemini API platform to access image, chat, and video models in a single workflow. Connect Nano Banana API, Imagen 4 API, Gemini 3 Flash API, Veo 3 API, and more without switching providers or managing separate integrations.
Test Google Gemini API models before integration with free trial credits and an online playground. Try Gemini image API, Gemini AI API, and video generation models directly to validate workflows and reduce development time.
Build with a cost-effective Gemini API that balances price, speed, and performance. Kie.ai helps teams reduce API costs while keeping low latency and reliable response times for AI image, chat, and video generation workloads.
Get access to an evolving Gemini model API ecosystem with regularly updated models. New Gemini AI API releases, image models, LLM upgrades, and video generation APIs are added to help teams stay current.
Get help whenever you need it. Our support team is available 24/7 to assist with Gemini API integration, technical questions, account issues, and deployment challenges so your projects keep moving.
Create AI image generator and image editing applications with Nano Banana API and Gemini image API models. Build design tools, content creators, and visual products with prompt-based image generation and editing workflows.
Use Gemini AI API models to build AI chatbots, virtual assistants, and conversational platforms. Support customer service, automate tasks, and create intelligent user experiences with fast responses.
Build AI video generator platforms with Veo API models for text-to-video workflows. Generate videos with realistic motion, native audio support, and scalable content creation capabilities.
Build multimodal applications that process text, images, and video in one workflow. Use Google Gemini API to create unified AI experiences across different input and output formats.
