Model provider5 models2 labs

Runware

Runware serves 5 video models on LLM API from ByteDance and Black Forest Labs.

Models and prices

Prices when Runware serves the request.

Video 5

Price per second of video; a range covers its resolutions

Sort

Video models on Runware and their prices on LLM API

Dreamina-Seedance-2.5`dreamina-seedance-2-5-260628`	$0.112–0.625	Text, Image, Reference	480p–1080p
Dreamina-Seedance-2.0-Mini`dreamina-seedance-2-0-mini-260615`	$0.036–0.081	Text, Image, Reference	480p–720p
Dreamina-Seedance-2.0-Fast`dreamina-seedance-2-0-fast-260128`	$0.06–0.13	Text, Image, Reference	480p–720p
Dreamina-Seedance-2.0`dreamina-seedance-2-0-260128`	$0.07–0.78	Text, Image, Reference	480p–4k
FLUX 3 Video`flux-3-video`	$0.17–0.29	Text, Image	720p–1080p

Send requests to Runware

Use the model ID as it is: video, audio and embedding requests take no provider prefix.

Example: Dreamina-Seedance-2.5

POST /v1/videosVideo jobs run in the background: create one, poll it, then download the file.Videos docs

import os
import time

from openai import OpenAI

client = OpenAI(
    base_url="https://api.llmapi.ai/v1",
    api_key=os.environ["LLMAPI_KEY"],
)

video = client.videos.create(
    model="dreamina-seedance-2-5-260628",
    prompt="A paper boat drifting down a rainy street",
)
while video.status in ("queued", "in_progress"):
    time.sleep(10)
    video = client.videos.retrieve(video.id)
if video.status == "failed":
    raise RuntimeError(video.error)
client.videos.download_content(video.id).write_to_file("video.mp4")

import fs from "node:fs";
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.llmapi.ai/v1",
  apiKey: process.env.LLMAPI_KEY,
});

let video = await client.videos.create({
  model: "dreamina-seedance-2-5-260628",
  prompt: "A paper boat drifting down a rainy street",
});
while (video.status === "queued" || video.status === "in_progress") {
  await new Promise((r) => setTimeout(r, 10_000));
  video = await client.videos.retrieve(video.id);
}
if (video.status === "failed") throw new Error(video.error?.message);
const content = await client.videos.downloadContent(video.id);
fs.writeFileSync("video.mp4", Buffer.from(await content.arrayBuffer()));

curl https://api.llmapi.ai/v1/videos \
  -H "Authorization: Bearer $LLMAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "dreamina-seedance-2-5-260628",
    "prompt": "A paper boat drifting down a rainy street"
  }'

# Poll GET https://api.llmapi.ai/v1/videos/{id} until "completed",
# then download GET https://api.llmapi.ai/v1/videos/{id}/content

Prices synced October 27, 2026.