YA DISPONIBLESeedance 2.5 ya está disponible en I2V.aiProbar ahora
i2v.aii2v.aii2v.ai
  • Studio
  • Comparar modelos
  • Market
  • Precios
  • Documentación

How to integrate

Create an API key, then give the integration prompt to Claude Code, Cursor, or Codex. You can also call the API directly from your server.

Create API key
Claude Code · Integration demo
Connect i2v.ai to this project. Start with one product image.
# .env.local
I2V_API_KEY=YOUR_API_KEY
I2V_BASE_URL=https://i2v.ai

Example workflow and asset. Query the accepted task until it succeeds to get the media URL.

From setup to your generated result

  1. 1

    Copy the prompt into your AI coding tool.

  2. 2

    Sign in to i2v.ai and create an API key.

  3. 3

    Set the key in your server environment.

    I2V_API_KEY
  4. 4

    Confirm the model and budget, submit a task, then query its result.

Keep the key on your server. Verify model settings and prices in the docs and catalog, and confirm the budget before paid generation.

Read the API docs
Read the integration prompt

Help me integrate i2v.ai image/video generation into this project. Read the existing code and identify its framework, server-side environment configuration, and request patterns first. Read https://i2v.ai/docs and https://i2v.ai/docs/models to verify public model IDs, required inputs, pricing, and the current API contract. List published generation models at https://i2v.ai/api/v1/generation-models when needed. Use https://i2v.ai as the base URL and Authorization: Bearer with the server-side environment variable I2V_API_KEY. I will create my key at https://i2v.ai/me?section=api-keys and configure it locally. Ask whether it is configured, without asking me to paste the secret into chat. Keep the key on the server and out of source code, browser bundles, and logs. POST /api/v1/jobs/createTask with a body that includes the verified model ID and inputs; it returns a taskId. Use a unique Idempotency-Key for each new task and reuse it with the same body when retrying the same submission. Poll GET /api/v1/jobs/recordInfo?taskId=... with backoff. Continue waiting for waiting/generating, read output[].url for success, and surface error.code/error.message for fail. Handle authentication, balance, rate-limit, and network errors according to the docs. Propose the smallest integration that fits this project and explain the chosen model, settings, estimated cost, and files to change. Ask me to confirm the model and budget before any paid generation. After confirmation, implement server-side submission, result polling, and loading/success/error states, then verify with isolated responses before any authorized live call.

Keep what you generate.

Successful generations return media URLs that remain reachable for at least 90 days, and every result appears in a visual asset library — whether it came from Studio or the API.

  • Media URLs valid for at least 90 days.
  • Studio and API generations in one library.
  • Download anything you need to keep permanently.
Read the media retention policyOpen my works
Multi-shot narrative sample
Character consistency sample
Product ad sample
Video sample

Questions developers ask first.

?

i2v.ai is a creative AI API platform: one catalog and one API for image and video models, plus Studio for visual work and a shared library for everything you generate.

We provide model services through official APIs. For selected models, we work closely with official platforms such as Alibaba and BytePlus to secure better pricing. Limited-time promotions can also lower prices. See the model page for current prices and offers.

You pay for successfully generated results at the price of your selected model and configuration, shown before submission. The estimated amount is reserved before processing and settled when generation succeeds. Failed generations release the reservation, and requests that fail parameter validation incur no generation charge.

Yes. Both expose the same model IDs and share one account and one USD balance, so a model you test in Studio is the model you ship.

Successful generations return URLs that remain reachable for at least 90 days. Download anything you need for permanent use; the media retention policy has the full rules.

The model market shows real samples, specifications, and per-configuration pricing without an account. Generating requires signing in.

The API is HTTPS and JSON, so any HTTP client works. An OpenAI-compatible chat endpoint is available for agent use cases.

Build your next creative product.

Create an account, pick a model, and ship the first generation today.

Start buildingRead the API docs
i2v.aii2v.aii2v.ai

I2V AI — creación de imágenes y videos con IA, con acceso por API

  • GitHub

Producto

  • Studio
  • Generación de imágenes
  • Generación de vídeos
  • Modelos
  • Precios
  • API de vídeo
  • API de imágenes

Recursos

  • Estado del servicio
  • Blog
  • Escenarios
  • Obras
  • Prompts
  • Imagen a Prompt
  • Imágenes por lotes a Prompt

Modelos de imagen

  • Qwen Image 2
  • Seedream 5.0
  • Nano Banana Pro
  • Nano Banana Flash
  • Nano Banana 2

Modelos de vídeo

  • Google Veo 3.1
  • Google Veo 3.1 Lite
  • Google Veo 3.1 Pro
  • Seedance 2.0
  • Kling v3.0
  • Kling v3.0 Pro

Empresa & Legal

  • Acerca de
  • Contacto
  • Política de privacidad
  • Términos del servicio
  • Política de reembolso
  • Retención de medios

Este sitio web es una plataforma independiente de terceros. No estamos afiliados, respaldados ni representamos oficialmente a ningún proveedor de modelos de IA mencionado en este sitio. Todas las marcas comerciales y nombres de marca pertenecen a sus respectivos propietarios.

© 2026 I2V AI. Todos los derechos reservados. Operado por CLEANCUT RAZOD LLC

support@i2v.aiprivacy@i2v.aiDiscord

See it before you build it

The same catalog, real samples, and prices live in the product. Open a tab to see what you get.

i2v.ai/app/market
Open the model market
Image
Nano Banana Pro0,09 US$ /image
Image
Seedream 5.00,0275 US$ /image
Video
Google Veo 3.10,0375 US$ /s

Real model samples. Settings and prices below each output.

Real output. Public price.

One row per model: a real sample, the supported media type, and the price you pay before you submit a task.

Open the model market
Nano Banana Pro
Real sample

Nano Banana Pro

Image · 0,09 US$ /image

Nano Banana Pro

Let your AI pick the model and the price

Paste one prompt into Claude, ChatGPT, or Gemini. It reads your project, shortlists models, and estimates the cost before you write any code.

  1. 1It reads your brief and asks only about what it cannot find.
  2. 2It checks the public catalog, sample output, settings, and prices.
  3. 3It names the models and the monthly cost; you decide what to build.
Open in ChatGPTOpen in Claude
Read the full prompt

You are helping me plan a creative AI project. I need 300 product images and 20 five-second video clips per month. Use the public i2v.ai catalog: compare real samples, supported settings, and per-configuration prices. Recommend the smallest set of models that covers the work, show the monthly volume, per-unit price, and total USD cost, and explain any tradeoff between quality, speed, and cost. Do not write code until I confirm the models and budget.

ClaudeConversation demo
I need 300 product images and 20 five-second clips a month. Which models should I use, and what will it cost?
Checking model settings and catalog prices…
Tell your AI more about your project

Example answer. Prices follow the public catalog.

Creative AI API platform/Studio + REST API · for developers and AI agents

One API for image and video models.

Discover. Compare. Create. Keep.

For developers and AI agents: find the right model, compare real output, ship it from Studio or the API, and keep every result reachable for at least 90 days.

Start buildingBrowse models and pricing

28 models · 12 image · 16 video · one USD balance

Models from Google · ByteDance · Kling · Alibaba · OpenAI

Real sampleVideo

Seedance 2.5

0,537354 US$ / 5s

One API · 28 models

One request, any model

POST /api/v1/jobs/createTask
{
  "model": "seedance2-5",
  "inputs": { "prompt": "…" }
}
200 OK{ "taskId": "…" }

See the cost before you call.

Choose a model and configuration to estimate the USD cost before submitting. Every price is public.

View full pricingOpen the model market
Danos una estrella en GitHub y llévate $1Soporte en línea 24/7

Estimated cost

0,30 US$0,30 US$

Google Veo 3.1 · 8s · 720p

Model
Duration
Resolution

Prices are shown in USD before you submit a task. Pay as you go.

What you can build

One API key connects your creative product to image, video and more AI creation capabilities.

Add text-to-video and image-to-video to your app, with media URLs available for at least 90 days to simplify short-term asset management.

Explore developer docs

Request

curl https://i2v.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "google-veo3.1",
  "inputs": {
    "prompt": "Cinematic electric SUV launch, rain-soaked city at night, slow tracking shot",
    "duration": 8,
    "resolution": "720p",
    "aspectRatio": "16:9",
    "generateAudio": false
  }
}'
AI video SaaS · Illustrative creative assetIllustrative creative asset

Google Veo 3.1 · 8s · 720p

Estimated cost 0,30 US$

Returns

{ "taskId": "YOUR_TASK_ID" }

Requests and responses are API examples; previews are existing illustrative assets. Submission returns a task ID; query the task for generated results. Costs are configuration-based estimates. Confirm the quote before submitting.