# Video Generation through toolfare

> 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.

Page: https://toolfare.ai/video-generation

## Use it from your agent

Paste this into Claude Code, Codex, Cursor or any agent with a shell:

> Set up https://toolfare.ai/skill.md, then use toolfare to make a five-second 9:16 clip with kling-3 of steam rising from a cup of coffee on a café table, tell me the price first, then collect the video when it is ready

Apps without a terminal connect toolfare as an MCP server: https://toolfare.ai/docs#connect

## Use it from a script

```sh
mkdir -p ~/.local/bin
curl -fsSL 'https://toolfare.ai/toolfare/toolfare.mjs' -o ~/.local/bin/toolfare
chmod +x ~/.local/bin/toolfare
export PATH="$HOME/.local/bin:$PATH"
export TOOLFARE_MCP_URL='https://api.toolfare.ai/mcp'
toolfare login
```

Sign in once per machine; the CLI renews the sign-in itself. On a CI runner or another server,
create an API key in the toolfare console and set it as `TOOLFARE_API_KEY` instead of signing in.
Paid calls on one sign-in or key run one at a time. `--max-cost` refuses a call quoted above
that many credits (1,000 credits = $3).

## Tools

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

Tool: `video_generation`

Text-to-video generation

Required parameters: model, prompt

Optional parameters: aspect_ratio, first_frame, reference_audios, reference_images, reference_videos, resolution, seconds, seed

Cost: From $0.6

Ask:
- 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.
## Price

From $0.6 Quoted before each call; the final charge follows the returned usage. Pay per call from one balance.

Balances and top-ups are in US dollars. Quotes and `--max-cost` count credits: 1,000 credits = $3 ($0.003 each).

## 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.
- You want a presenter speaking a script to camera.
- You want a product ad built from a product page’s URL.

## 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.