How much does the Wan2.2-S2V-14B (Presenter / Talking Head) API cost?

Video generation is priced by output resolution and by whether you supply a reference video, so Wan2.2-S2V-14B (Presenter / Talking Head) has no single token rate. The full matrix is on the EcoHash pricing page (/pricing#video-pricing); every rate there comes live from the EcoHash billing system.

Wan2.2-S2V-14B (Presenter / Talking Head) vs Seedance 2.5: which should I use?

Both are video models on the same EcoHash API, so moving between them is a change of model id and nothing else. Both prices come live from the EcoHash billing system; the comparison table on this page carries the current figures.

Can I use Wan2.2-S2V-14B (Presenter / Talking Head) commercially through EcoHash?

EcoHash hosts Wan2.2-S2V-14B (Presenter / Talking Head) under the model publisher's own licence and does not change its terms, so whether your use is permitted is decided by that licence — read it on the model card at https://huggingface.co/Wan-AI/Wan2.2-S2V-14B. The EcoHash Terms of Service additionally require you to comply with each model's licence and acceptable-use policy. Your EcoHash bill for API usage is separate from, and does not grant, any right under the model's licence.

Wan2.2-S2V-14B (Presenter / Talking Head)

ReadyVideoby Alibaba

Overview

About this model

Speech-to-video: animates a portrait to speak driving audio.

View model card on HuggingFace

Specifications

Model details

Provider: Alibaba
Modality: Video
Pricing: from $0.05 / sec

Modalities: text, image, audio → video

API

Call it in code

Use the EcoHash HTTP endpoint shown below with your API key. This endpoint has no matching OpenAI SDK method.

Python

import time

import requests

BASE_URL = "https://api.ecohash.com/v1"
HEADERS = {"Authorization": "Bearer YOUR_API_KEY"}

job = requests.post(
    f"{BASE_URL}/video/generations",
    headers=HEADERS,
    json={
        "model": "wan22-s2v-14b",
        "prompt": "A sunset over mountains, cinematic",
        # Self-hosted engines size the clip from these fields.
        # Provider-served engines take "resolution" and "duration" instead.
        "num_frames": 49,
        "fps": 16,
        "width": 720,
        "height": 480,
    },
).json()

while True:
    status = requests.get(
        f"{BASE_URL}/video/jobs/{job['id']}", headers=HEADERS
    ).json()
    if status["status"] in ("completed", "failed"):
        break
    time.sleep(5)

video_url = status.get("url")  # pre-signed, valid 24h

curl

# 1. submit the job — returns {"id": "..."}
curl https://api.ecohash.com/v1/video/generations \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d {
    "model": "wan22-s2v-14b",
    "prompt": "A sunset over mountains, cinematic",
    "num_frames": 49,
    "fps": 16,
    "width": 720,
    "height": 480
  }

# 2. poll until status is completed, then read .url (pre-signed, valid 24h)
curl https://api.ecohash.com/v1/video/jobs/JOB_ID \
  -H "Authorization: Bearer YOUR_API_KEY"

Compare