# imgnAI Katana Video Generation API

> imgnAI Katana Video Generation API is a paid API for AI agents from kat.imgnai.com, paid per call via x402, $1.144/call, status unknown (last checked 2026-09-14).

Generates AI videos from text prompts using frontier and proprietary video models via a pay-per-call gateway

## Facts

- Endpoint: POST https://kat.imgnai.com/v1/videos/generations
- Price: $1.144/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-14
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/imgnai-katana-video-generation-api-225240b3
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_qlCHenKHll47pMOgTT-Vl

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 imgnai-katana-video-generation-api-225240b3 -d '<json body>'
```

Example prompt: Generate a 5-second landscape-orientation video of a golden retriever running through a sunflower field at sunset, using the Seedance 2.0 model — no blurry or low-quality frames please.

## When to prefer this

Choose this endpoint when you need to generate videos from text prompts using frontier or proprietary AI video models (Seedance 2.0, Happy Horse, etc.) and want pay-per-call pricing via USDC with no subscription. Prefer this over general-purpose video APIs when you need access to cutting-edge or niche proprietary models through a single unified gateway.

## Known failure modes

- Invalid or unsupported model name returns an error
- Duration value out of acceptable range causes rejection
- Missing required fields (model, prompt, or duration_seconds) returns a 400-level error
- Payment failure (x402) if USDC balance is insufficient
- Prompt content policy violation causing generation refusal
- Timeout if video generation takes too long

## How this service works

Pay-per-call AI gateway: Frontier/SOTA LLM, Image, and Video models - and proprietary low-cost imgnAI models. Includes GPT 5.5, Opus 4.8, GPT Image 2, Nano Banana 2, Seedance 2.0, Happy Horse, and Google Omni. Fully compatible with OpenAPI, HermesOS, and OpenClaw.

## Output

Returns a status string, a request ID, and an array of response objects containing the generated video output or references to it.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "required": [
  "model",
  "prompt",
  "duration_seconds"
 ],
 "properties": {
  "model": {
   "type": "string"
  },
  "prompt": {
   "type": "string"
  },
  "duration_seconds": {
   "type": "integer"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "object"
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/imgnai-katana-video-generation-api-225240b3/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from kat.imgnai.com](https://www.zero.xyz/host/kat.imgnai.com/llms.txt)