# Claw Hunter Video Generation

> Claw Hunter Video Generation is a paid API for AI agents from clawhunter.fun, paid per call via x402, $0.01/call, status unknown (last checked 2026-10-12).

Generates videos from text prompts, start images, reference images, or reference clips using multiple AI video models (Kling, Seedance, MiniMax H3, Wan, Veo, Grok, and more), returning finished video URLs

## Facts

- Endpoint: POST https://clawhunter.fun/api/v1/videos/generations?utm_source=zero.xyz
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-10-12
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/claw-hunter-video-generation-568b04dd
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_-gz1eDmChN7sjGrmzxLuF

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability claw-hunter-video-generation-568b04dd -d '<json body>'
```

Example prompt: Generate a 5-second 1080p video of a golden retriever running through a sunlit meadow at sunset using Kling v3, with audio, in 16:9 aspect ratio.

## When to prefer this

Choose this endpoint when you need to generate AI video from text, images, or reference clips and want access to multiple top-tier models (Kling, Seedance, Wan, Veo, MiniMax, Grok) through a single API at or below provider list prices. Ideal when you want model flexibility, per-render pricing without subscriptions, and options for resolution, aspect ratio, duration, and audio per model. Use the clawhunter/smart model for automatic routing if you don't have a strong model preference.

## Known failure modes

- 400 Bad Request — unsupported audio/model combination or invalid parameter values
- 422 Unprocessable Entity — reference video clip failed content moderation (uncharged)
- 402 Payment Required — x402 payment flow not completed or insufficient funds
- Model-specific constraints not met (e.g. duration or resolution not supported by chosen model)
- Invalid image_url or video_url — URL not accessible or format unsupported
- Prompt content flagged by moderation policy

## How this service works

Video generation from a text prompt, a start image, reference images, or a reference clip (Kling, Seedance, MiniMax H3, Wan, Veo, Grok Imagine, more), billed at the render's actual cost — from about half provider list price, never above list. Per-model length, resolution, and audio options; the call returns finished video URLs. Menu + prices: GET /api/v1/media/models (free).

## Output

The endpoint returns finished video URLs once rendering is complete. The response includes the generated video file URL(s), model used, and associated metadata. Payment is billed at the actual render cost (at or below provider list price), charged per generation.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "audio": {
   "type": "boolean",
   "description": "true renders a soundtrack on operations marked audio; on models listing an audio_off_price_multiplier, false scales the price down by it (the with-audio render is the anchor price). Unsupported combinations return 400"
  },
  "model": {
   "enum": [
    "kling-v3",
    "kling-o3",
    "seedance-2",
    "seedance-2-fast",
    "seedance-2-mini",
    "seedance-2-5",
    "wan-3-prime",
    "wan-3",
    "wan-2-7",
    "veo-3-1-fast",
    "ltx-2-5-fast",
    "ltx-2-5-pro",
    "ltx-2-fast",
    "ltx-2-3-fast",
    "ltx-2-3-full",
    "happy-horse-1",
    "happy-horse-1-1",
    "grok-imagine-video",
    "minimax-h3",
    "minimax-h3-max",
    "minimax-h3-max-turbo",
    "flux-3-video",
    "kling-v3-pro",
    "kling-o3-pro",
    "kling-v3-4k",
    "kling-o3-4k",
    "clawhunter/smart"
   ],
   "type": "string",
   "description": "video model id (enum), or clawhunter/smart to auto-route (API key required). Prices and options at GET /api/v1/media/models."
  },
  "prompt": {
   "type": "string",
   "description": "the scene to render"
  },
  "image_url": {
   "type": "string",
   "description": "one start frame (https URL or data URL) — runs the image_to_video operation"
  },
  "video_url": {
   "type": "string",
   "description": "one reference clip (https URL, under the model's video_reference.max_seconds) — runs reference_to_video on models whose menu entry lists video_reference (Wan 3.0, Wan 3.0 Prime, MiniMax H3, Seedance 2.5). The clip is screened frame by frame before anything is spent; a clip that fails moderation returns 422, uncharged. Free on most models; where the menu marks bills_input_seconds (Seedance 2.5) the clip's seconds bill as input — the 402 quotes at the model's clip cap and the settle charges the clip's real length. Not on clawhunter/smart. Combine with input_images to condition on both."
  },
  "resolution": {
   "type": "string",
   "description": "resolution tier (480p | 720p | 1080p | 4k where listed); scales the price by the tier's listed multiplier. On clawhunter/smart, the smart entry lists each tier's values; the routed model drops a tier it doesn't offer."
  },
  "aspect_ratio": {
   "type": "string",
   "description": "per-model menu (on clawhunter/smart, the smart entry's tier menu); doesn't change the price"
  },
  "input_images": {
   "type": "array",
   "items": {
    "type": "string"
   },
   "description": "two or more conditioning imag
… (truncated)
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/claw-hunter-video-generation-568b04dd/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from clawhunter.fun](https://www.zero.xyz/host/clawhunter.fun/llms.txt)