−46% vs fal.aiSeedance video for less than fal.aiNo subscription. A clip that fails is never charged.Get $1 in free credits. Top up from just $3.
toolfare
Start free
Bought by toolfare · quoted first

Ask your AI for a short video clip, and choose which model makes it.

Short clips from a text prompt, made by the model you pick — veo-3.1, kling-3, hailuo-2.3, luma-ray-3.2, pika-2.2, longcat-video, h3-video or h3-max-video — asked from Claude, ChatGPT, Codex, Cursor or your own script. No account or key with any of them: toolfare quotes each generation before it runs and charges one balance, and the clip arrives as a task your agent collects with get_result.

Start freeUse the API

1Connect your AI app

Pick the app you use. You do this once, and every API on toolfare is then available in it.

Add toolfare as a connector in Claude

Add to Claude
https://api.toolfare.ai/mcp
  1. 1Open Customize → Connectors and choose "Add custom connector".
  2. 2Paste this URL as the remote MCP server URL.
  3. 3Leave the OAuth client id and secret under Advanced settings empty.
  4. 4Complete the browser authorization, then return to your conversation.

Custom connectors are available on Free, Pro, Max, Team and Enterprise. A Free account may hold one custom connector in total.

Claude’s own instructions

2What to ask

Copy a prompt into your AI app once you’re connected. It picks the right one of the 1 tools and tells you the price first.

  • Start a clip from a prompt, on the model you choose

    From $0.6

    Text-to-video generation

    • “Make an eight-second 16:9 video of waves breaking on a rocky coast with veo-3.1.”
    • “Generate a vertical clip of a sneaker spinning on a pedestal for a story ad.”
    • “Try the same prompt on kling-3 and hailuo-2.3 so I can compare them.”

Use it when

  • You need a short generated clip for an ad, a post or a storyboard.
  • You want to compare several video models on the same prompt before committing to one.
  • You need a longer single clip: longcat-video runs up to 32 seconds.
  • You want to guide a clip with reference images, video or audio on h3-video or h3-max-video.

Look elsewhere when

  • You want ByteDance’s Seedance specifically, or to animate a product image from its first frame on a dedicated image-to-video model. Use this instead
  • You want a presenter speaking a script to camera. Use this instead
  • You want a product ad built from a product page’s URL. Use this instead

Video Generation directly, or through toolfare

Directly

  • A separate account, region access and balance with each video model’s provider
  • A key per provider to hand to an agent
  • Your own code to submit, poll and download tasks in each provider’s format

Through toolfare

  • Eight models behind one tool, each generation quoted before it runs
  • One balance for video, images and data — no key per provider
  • One task flow for every model: start, then collect with get_result

You get each model’s clips on demand, not a video editor: there is no timeline, no stitching of clips and no library of past generations, and a clip you do not like is still charged.

Limits

  • Asynchronous: the first call returns a task, and the clip is collected with get_result once it has finished.
  • Length, aspect ratio and resolution depend on the model — from 3 seconds on kling-3 up to 32 on longcat-video, and up to 1080p (2K on h3-video).
  • Reference images, video and audio are accepted only by h3-video and h3-max-video; a first frame only by h3-video.
  • Pay as you go from your toolfare balance, in US dollars; there is no subscription. A call runs when your balance covers its quote.
Video Generation documentation

Questions

veo-3.1, kling-3, hailuo-2.3, luma-ray-3.2, pika-2.2, longcat-video, h3-video and h3-max-video. You or your agent choose one on each call.

No. The models are reached through a third-party provider and toolfare holds that account. You connect toolfare once and pay per call from your balance.

Each tool’s current price is shown on this page and quoted before the call runs. The price differs by model.

No. Generation returns a task, and your agent collects the finished clip with get_result once it is ready.

Check the chosen model’s terms for your use. toolfare does not grant any rights beyond them.

Related sources