🎬

Hunyuan Video 1.5

Watermark notice — Video models on NovAI are served by Chinese providers (MiniMax, Tencent) and may burn a visible AI-generated label into the output under China’s labelling rules — NovAI cannot switch it off. In our tests output labelling varies by model. Text and chat models are not affected. Which models, and what it rules out →

Tencent Hunyuan · Video Generation

Tencent Hunyuan Video 1.5 generation model. Supports text-to-video and image-to-video via an asynchronous task API: submit a prompt (and optional image), poll for the mp4 URL.

📊 Specifications

Mode

Async task

Input

Text + Image

Output

Video (mp4 URL)

Capabilities

T2V + I2V

Resolution

720p / 1080p

Status

✅ Available

💰 Pricing

	NovAI	OpenRouter
Token billing Billed on actual upstream tokens (tokenhub_usage.total_tokens)	$1.54 / 1M tokens	N/A	Exclusive
Reference · per second 30,000 tokens/s at 720p / 1080p	~$0.046/s	N/A
Reference · 5s clip Typical 5-second generation	~$0.231	N/A

Billed per token on the real upstream count. Hunyuan Video 1.5 consumes ~30,000 tokens per output second, so a 5s 720p clip is ~150,000 tokens ≈ $0.231. Pre-deducted estimate is reconciled to the actual count on success.

🚀 API Usage

1. Submit — Text-to-Video

curl -X POST https://api.aiapi-pro.com/v1/video/generations \
  -H "Authorization: Bearer $NOVAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "hy-video-v1.5",
    "prompt": "A red sports car driving along a coastal road at sunset, cinematic",
    "resolution": "720p",
    "duration": 5,
    "ratio": "16:9"
  }'
# -> { "id": "", "status": "queued" }

2. Poll Task Status

curl "https://api.aiapi-pro.com/v1/video/generations/{task_id}?model=hy-video-v1.5"   -H "Authorization: Bearer $NOVAI_API_KEY"
# -> { "status": "processing" } ... then when done:
# -> { "status": "succeeded", "video_url": "https://.../out.mp4",
#      "tokenhub_usage": { "total_tokens": 30,000*duration } }

Async flow: POST /v1/video/generations returns {id, status:"queued"}. Poll GET /v1/video/generations/{id} until status is succeeded (then video_url holds the mp4) or failed (auto-refunded). An estimate is pre-deducted at submit and reconciled to the real token count on success.