One AI API for video, image, music and chat models
Switch models by changing one parameter. Pay as you go with credits that never expire, and never pay for failed tasks.
Transparent Pricing, Built for Scale
Compare featured models with their official prices. One credit balance for every model, no hidden fees, and you never pay for failed generations.
Featured Models on KIE
A selection of the most highly-requested and expressive models available directly through our API.
VIDSeedance 2.5
$0.085 / sSeedance 2.5 is ByteDance's next-gen video model, generating up to 30-second 4K clips in a single take with up to 50 multimodal references and precise region-level editing.
IMGGPT Image 2.6
$0.025 / imgGPT Image 2.6 is OpenAI's image generation and editing model, offered on KIE in three tiers — Flare, fast with stronger layouts for posters and product imagery; Sunburst, for refined output and more consistent edits; and Economy, the lowest-cost option.
IMGGPT Image 2
$0.03 / imgGPT Image 2 is OpenAI’s next-gen image model built for stronger photorealism, cleaner image editing, sharper text rendering, and more polished product photography.
IMGNano Banana 2.1
$0.02 / imgNano Banana 2.1 is Google's high-efficiency image generation and conversational editing model — an update to Nano Banana 2, with up to 10 input images, 1K to 4K output and 14 aspect ratios.
VIDVeo 3.1
$0.15 / videoGoogle DeepMind’s upgraded AI video model for realistic motion generation, extended clip duration, multi-image reference control, and synchronized audio output in up to 4K.
Grok Imagine Video 1.5
$0.012 / sGrok Imagine Video 1.5 is xAI's latest image-to-video model, turning a single image into smooth, expressive motion at up to 1080p — built for fast, high-volume creative workflows.
VIDKling 4.0
$0.085 / sKling 4.0 is Kling AI's video model for longer storytelling — 3 to 30-second videos at up to 4K with optional HDR and native stereo audio, guided by up to 15 references or 10 keyframes.
VIDSeedance 2.5
$0.085 / sSeedance 2.5 is ByteDance's next-gen video model, generating up to 30-second 4K clips in a single take with up to 50 multimodal references and precise region-level editing.
IMGGPT Image 2.6
$0.025 / imgGPT Image 2.6 is OpenAI's image generation and editing model, offered on KIE in three tiers — Flare, fast with stronger layouts for posters and product imagery; Sunburst, for refined output and more consistent edits; and Economy, the lowest-cost option.
IMGGPT Image 2
$0.03 / imgGPT Image 2 is OpenAI’s next-gen image model built for stronger photorealism, cleaner image editing, sharper text rendering, and more polished product photography.
IMGNano Banana 2.1
$0.02 / imgNano Banana 2.1 is Google's high-efficiency image generation and conversational editing model — an update to Nano Banana 2, with up to 10 input images, 1K to 4K output and 14 aspect ratios.
VIDVeo 3.1
$0.15 / videoGoogle DeepMind’s upgraded AI video model for realistic motion generation, extended clip duration, multi-image reference control, and synchronized audio output in up to 4K.
Grok Imagine Video 1.5
$0.012 / sGrok Imagine Video 1.5 is xAI's latest image-to-video model, turning a single image into smooth, expressive motion at up to 1080p — built for fast, high-volume creative workflows.
VIDKling 4.0
$0.085 / sKling 4.0 is Kling AI's video model for longer storytelling — 3 to 30-second videos at up to 4K with optional HDR and native stereo audio, guided by up to 15 references or 10 keyframes.
VIDSeedance 2.5
$0.085 / sSeedance 2.5 is ByteDance's next-gen video model, generating up to 30-second 4K clips in a single take with up to 50 multimodal references and precise region-level editing.
IMGGPT Image 2.6
$0.025 / imgGPT Image 2.6 is OpenAI's image generation and editing model, offered on KIE in three tiers — Flare, fast with stronger layouts for posters and product imagery; Sunburst, for refined output and more consistent edits; and Economy, the lowest-cost option.
IMGGPT Image 2
$0.03 / imgGPT Image 2 is OpenAI’s next-gen image model built for stronger photorealism, cleaner image editing, sharper text rendering, and more polished product photography.
IMGNano Banana 2.1
$0.02 / imgNano Banana 2.1 is Google's high-efficiency image generation and conversational editing model — an update to Nano Banana 2, with up to 10 input images, 1K to 4K output and 14 aspect ratios.
VIDVeo 3.1
$0.15 / videoGoogle DeepMind’s upgraded AI video model for realistic motion generation, extended clip duration, multi-image reference control, and synchronized audio output in up to 4K.
Grok Imagine Video 1.5
$0.012 / sGrok Imagine Video 1.5 is xAI's latest image-to-video model, turning a single image into smooth, expressive motion at up to 1080p — built for fast, high-volume creative workflows.
VIDKling 4.0
$0.085 / sKling 4.0 is Kling AI's video model for longer storytelling — 3 to 30-second videos at up to 4K with optional HDR and native stereo audio, guided by up to 15 references or 10 keyframes.
VIDWan 3.0
$0.04 / sWan 3.0 is Alibaba's omni-reference video model for longer storytelling — up to 30-second videos from text, images, video or even documents, with precise editing and immersive audio.
IMGSeedream 5.5
$0.018 / imgSeedream 5.5 is ByteDance's image model for stable multi-turn editing — unedited regions stay intact across up to 100 rounds, with native transparent PNGs, layer decomposition and more natural lighting.
AUDSuno V6
$0.06 / reqSuno V6 is Suno's newest music model — full vocal and instrumental tracks with richer realism, natural-language song editing, mashups and sampling, plus V6 Mini for speed and V6 Wild for bolder results.
AUDGemini 3.8 Flash TTS
$0.35 / MGemini 3.8 Flash TTS is Google's latest expressive speech model — 100+ languages, 2,000+ ready-made voices, voice cloning from a 30-second sample, and native two-speaker dialogue.
LLMGPT-6.2 Astra
$2.40 / MGPT-6.2 Astra is OpenAI's frontier model for complex engineering, science and professional work — a 1.05M-token context, 128K-token output, cleaner code and more capable web frontends and 3D designs.
LLMClaude Opus 5.5
$1.60 / MClaude Opus 5.5 is Anthropic's newest frontier model — Fable-class intelligence at lower cost and 30%+ faster output than Opus 5, excelling at agentic coding, computer use and knowledge work.
LLMGemini 4 Hydrogen
$0.60 / MGemini 4 Hydrogen is Google's fast Gemini 4 model for coding and everyday work — a 1M-token context, four thinking levels up to xhigh, and text, image, video, audio and PDF input.
VIDWan 3.0
$0.04 / sWan 3.0 is Alibaba's omni-reference video model for longer storytelling — up to 30-second videos from text, images, video or even documents, with precise editing and immersive audio.
IMGSeedream 5.5
$0.018 / imgSeedream 5.5 is ByteDance's image model for stable multi-turn editing — unedited regions stay intact across up to 100 rounds, with native transparent PNGs, layer decomposition and more natural lighting.
AUDSuno V6
$0.06 / reqSuno V6 is Suno's newest music model — full vocal and instrumental tracks with richer realism, natural-language song editing, mashups and sampling, plus V6 Mini for speed and V6 Wild for bolder results.
AUDGemini 3.8 Flash TTS
$0.35 / MGemini 3.8 Flash TTS is Google's latest expressive speech model — 100+ languages, 2,000+ ready-made voices, voice cloning from a 30-second sample, and native two-speaker dialogue.
LLMGPT-6.2 Astra
$2.40 / MGPT-6.2 Astra is OpenAI's frontier model for complex engineering, science and professional work — a 1.05M-token context, 128K-token output, cleaner code and more capable web frontends and 3D designs.
LLMClaude Opus 5.5
$1.60 / MClaude Opus 5.5 is Anthropic's newest frontier model — Fable-class intelligence at lower cost and 30%+ faster output than Opus 5, excelling at agentic coding, computer use and knowledge work.
LLMGemini 4 Hydrogen
$0.60 / MGemini 4 Hydrogen is Google's fast Gemini 4 model for coding and everyday work — a 1M-token context, four thinking levels up to xhigh, and text, image, video, audio and PDF input.
VIDWan 3.0
$0.04 / sWan 3.0 is Alibaba's omni-reference video model for longer storytelling — up to 30-second videos from text, images, video or even documents, with precise editing and immersive audio.
IMGSeedream 5.5
$0.018 / imgSeedream 5.5 is ByteDance's image model for stable multi-turn editing — unedited regions stay intact across up to 100 rounds, with native transparent PNGs, layer decomposition and more natural lighting.
AUDSuno V6
$0.06 / reqSuno V6 is Suno's newest music model — full vocal and instrumental tracks with richer realism, natural-language song editing, mashups and sampling, plus V6 Mini for speed and V6 Wild for bolder results.
AUDGemini 3.8 Flash TTS
$0.35 / MGemini 3.8 Flash TTS is Google's latest expressive speech model — 100+ languages, 2,000+ ready-made voices, voice cloning from a 30-second sample, and native two-speaker dialogue.
LLMGPT-6.2 Astra
$2.40 / MGPT-6.2 Astra is OpenAI's frontier model for complex engineering, science and professional work — a 1.05M-token context, 128K-token output, cleaner code and more capable web frontends and 3D designs.
LLMClaude Opus 5.5
$1.60 / MClaude Opus 5.5 is Anthropic's newest frontier model — Fable-class intelligence at lower cost and 30%+ faster output than Opus 5, excelling at agentic coding, computer use and knowledge work.
LLMGemini 4 Hydrogen
$0.60 / MGemini 4 Hydrogen is Google's fast Gemini 4 model for coding and everyday work — a 1M-token context, four thinking levels up to xhigh, and text, image, video, audio and PDF input.
Developer-first Integration
Get up and running in minutes with our unified, intuitive API.
Choose your model
Select from top media models using a unified parameter schema. No need to learn different APIs.
Send Async Request
Dispatch your generation task. All models share the same predictable API gateway, making switching a breeze.
Webhook & Polling
Provide a webhook URL to be notified instantly when media is ready, or use standard status polling based on your architectural needs.
For coding agents
Let your coding agent build on KIE
Install the KIE skills once, or run the KIE CLI as a local MCP server. Claude Code, Codex, Cursor and other agents can then find the right model, read its parameters, run the task and bring back the result, without you pasting docs into the chat.
npx skills add https://kie.aikie-models
200+ modelsBuild apps with image, video, music and speech models. Your agent picks a model, checks the price, uploads input files and polls until the result is ready.
kie-chat-agents
Setup guideRun Codex, Claude Code or Grok Build on KIE chat models with your KIE credits. Covers the base URL, key and model name for each agent.
Why Developers Choose KIE
We abstract away the complexity of handling multiple generation platforms, so you can focus entirely on building your application.
Pay As You Go From One Wallet
KIE bills usage in credits from one wallet. Credits never expire, the pricing page lists every model's price, and failed tasks are never charged.

One API for 200+ AI Models
Access video, image, audio, and LLM models through one unified API. Switch between Veo, Kling, Seedance, Wan, Claude, GPT, Gemini, Nano Banana, Suno, and more without rebuilding your backend.

99.9% Availability. 24/7 Monitoring. Built for Stability
KIE keeps high-volume AI generation workflows moving with monitored API availability, around-the-clock task monitoring, async task tracking, webhook callbacks, and smart fallback routing across video, image, audio, and LLM models.

Free Trial AI API in Playground
Test KIE APIs directly in the Playground before writing production code. Try different prompts, compare model outputs, adjust parameters, and evaluate video, image, audio, and LLM models in a real API environment — no long setup required.

Simple AI API Integration
Integrate once and access leading models across video, image, audio, and LLMs. With clear documentation, unified task flows, and consistent API patterns, your team can switch models by changing the model_id instead of rebuilding the backend.

Robust Data Security
Secure API authentication, encrypted requests, and controlled task handling help protect your prompts, assets, and generation results across production workflows.

Private Support Channels, 365 Days a Year
KIE stays online 365 days a year to support production AI workflows. For API users, we provide dedicated private support channels on Telegram and Discord, offering one-on-one assistance for API errors, task logs, webhook callbacks, billing questions, and integration issues.

What technical teams value about KIE
Trusted by the builders powering the next generation of AI-native applications.
We've already deployed our infrastructure using the KIE API. Handling Webhook callbacks instead of long polling for Veo and Kling generation saves us massive server costs.
Frequently Asked Questions
Everything you need to know about integrating and billing with KIE.
npx skills add https://kie.aiStart Building with the World’s Top AI Models Today
Access video, image, music, and chat APIs in one platform, with pay-as-you-go credits and one integration for every model. Choose from models like Veo 3.1, Seedance 2.5, Suno and more.
Get Your Free API Key