WAN 3.0 is LIVE — 30s in one shot | Try in Video Generator →

wavespeed-ai/

Cosmos Predict 2.5 Text-to-Video generates video from text prompts using NVIDIA's 2B Cosmos Post-Trained Model. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing.

text-to-video
Input

Idle

$0.3per run·~33 / $10

Next:

ExamplesView all

A woman walking along a Paris street holding an umbrella, autumn leaves falling around her.

Related Models

README

Cosmos Predict 2.5 Text-to-Video

Cosmos Predict 2.5 Text-to-Video generates video from text prompts using NVIDIA's 2B Cosmos Post-Trained Model. Describe a scene in natural language — the model creates smooth, cinematic video clips with realistic motion, lighting, and atmospheric effects.

Why Choose This?

  • NVIDIA Cosmos architecture Powered by NVIDIA's 2B parameter Cosmos Post-Trained Model for high-quality video generation.

  • Pure text-to-video Generate videos from text descriptions alone — no reference images required.

  • Cinematic quality Produces realistic scenes with natural lighting, motion, and environmental effects.

  • Prompt Enhancer Built-in tool to automatically improve your scene descriptions.

  • Simple pricing Flat $0.25 per video, no complex calculations.

Parameters

ParameterRequiredDescription
promptYesText description of the desired scene and motion

How to Use

  1. Write your prompt — describe the scene, characters, motion, and atmosphere in detail.
  2. Use Prompt Enhancer (optional) — click to automatically refine your description.
  3. Run — submit and download your generated video.

Pricing

OutputCost
Per video$0.25

Best Use Cases

  • Cinematic Scenes — Generate atmospheric street scenes, landscapes, and urban environments.
  • Storytelling — Create visual narratives from written descriptions.
  • Concept Visualization — Bring creative ideas to life without reference images.
  • Social Media Content — Produce engaging short-form videos from text.
  • Marketing & Ads — Generate promotional video content quickly.

Pro Tips

  • Be specific and descriptive — include details about characters, actions, environment, lighting, and weather.
  • Use cinematic language like "autumn leaves falling," "rainy street," or "golden hour lighting" for atmospheric results.
  • Describe camera movement if desired (e.g., "tracking shot," "slow pan").
  • Try the Prompt Enhancer to automatically improve your descriptions.
  • Include mood and atmosphere details for more evocative results.

Notes

  • Prompt is the only required field.
  • Ensure your prompts comply with content guidelines.

Related Models

Note:This website uses AI models provided by third parties. Documentation prices are for reference and may be outdated. The Generate button shows an estimate; the final task charge prevails.

Cosmos Predict 2.5 Text To Video API — Quick start

Grab a WaveSpeedAI API key, then call POST https://api.wavespeed.ai/api/v3/wavespeed-ai/cosmos-predict-2.5/text-to-video with your input as JSON. The endpoint returns a prediction id. Start polling the result endpoint around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. On completed, read output values from data.outputs. Examples for Cosmos Predict 2.5 Text To Video below.

HTTP example
set -euo pipefail

: "${WAVESPEED_API_KEY:?Set WAVESPEED_API_KEY}"

REQUEST_BODY=$(cat <<'JSON'
{
    "prompt": "A cinematic shot of a city at sunset, soft golden light"
}
JSON
)

# 1. Submit the prediction.
SUBMIT_RESPONSE=$(curl --silent --show-error --fail-with-body \
  -X POST "https://api.wavespeed.ai/api/v3/wavespeed-ai/cosmos-predict-2.5/text-to-video" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $WAVESPEED_API_KEY" \
  -d "$REQUEST_BODY")

TASK=$(printf '%s' "$SUBMIT_RESPONSE" | jq 'if has("data") then .data else . end')
PREDICTION_ID=$(printf '%s' "$TASK" | jq -r '.id')
if [ -z "$PREDICTION_ID" ] || [ "$PREDICTION_ID" = "null" ]; then
  printf 'Submission response did not contain a prediction id
' >&2
  exit 1
fi
RESULT_URL=$(printf '%s' "$TASK" | jq -r '.urls.get // empty')
if [ -z "$RESULT_URL" ]; then
  RESULT_URL="https://api.wavespeed.ai/api/v3/predictions/$PREDICTION_ID/result"
fi

# 2. Poll until the prediction finishes.
while true; do
  RESPONSE=$(curl --silent --show-error --fail-with-body "$RESULT_URL" \
    -H "Authorization: Bearer $WAVESPEED_API_KEY")
  RESULT=$(printf '%s' "$RESPONSE" | jq 'if has("data") then .data else . end')
  STATUS=$(printf '%s' "$RESULT" | jq -r '.status')
  case "$STATUS" in
    completed) printf '%s\n' "$RESULT" | jq '.outputs'; break ;;
    failed|cancelled|timeout) printf '%s\n' "$RESULT" | jq . >&2; exit 1 ;;
    created|processing) sleep 2 ;;
    *) printf 'Unexpected status: %s
' "$STATUS" >&2; exit 1 ;;
  esac
done
Node.js example
const submitUrl = "https://api.wavespeed.ai/api/v3/wavespeed-ai/cosmos-predict-2.5/text-to-video";
const apiKey = process.env.WAVESPEED_API_KEY;
if (!apiKey) throw new Error('Set WAVESPEED_API_KEY');

async function requestJson(url, options = {}) {
  const response = await fetch(url, options);
  if (!response.ok) throw new Error(await response.text());
  return response.json();
}

// 1. Submit the prediction.
const body = await requestJson(submitUrl, {
  method: "POST",
  headers: {
    "Authorization": `Bearer ${apiKey}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
        "prompt": "A cinematic shot of a city at sunset, soft golden light"
}),
});
const task = body.data ?? body;
if (!task.id) throw new Error("Submission response did not contain a prediction id");
const resultUrl = task.urls?.get ||
  `https://api.wavespeed.ai/api/v3/predictions/${task.id}/result`;

// 2. Poll until the prediction finishes.
while (true) {
  const resultBody = await requestJson(resultUrl, {
    headers: { "Authorization": `Bearer ${apiKey}` },
  });
  const result = resultBody.data ?? resultBody;
  if (result.status === "completed") {
    console.log(result.outputs);
    break;
  }
  if (["failed", "cancelled", "timeout"].includes(result.status)) throw new Error(JSON.stringify(result));
  if (!["created", "processing"].includes(result.status)) throw new Error("Unexpected status: " + result.status);
  await new Promise(resolve => setTimeout(resolve, 2000));
}
Python example
import json
import os
import time
from urllib.request import Request, urlopen

api_key = os.environ["WAVESPEED_API_KEY"]
headers = {"Authorization": f"Bearer {api_key}", "Content-Type": "application/json"}
payload = {
    "prompt": "A cinematic shot of a city at sunset, soft golden light"
}

def request_json(url, data=None):
    request = Request(url, data=data, headers=headers, method="POST" if data else "GET")
    with urlopen(request) as response:
        return json.load(response)

# 1. Submit the prediction.
body = request_json("https://api.wavespeed.ai/api/v3/wavespeed-ai/cosmos-predict-2.5/text-to-video", json.dumps(payload).encode())
task = body.get("data", body)
if not task.get("id"):
    raise RuntimeError("Submission response did not contain a prediction id")
result_url = task.get("urls", {}).get("get") or f"https://api.wavespeed.ai/api/v3/predictions/{task['id']}/result"

# 2. Poll until the prediction finishes.
while True:
    result_body = request_json(result_url)
    result = result_body.get("data", result_body)
    status = result.get("status")
    if status == "completed":
        print(result.get("outputs", []))
        break
    if status in {"failed", "cancelled", "timeout"}:
        raise RuntimeError(result)
    if status not in {"created", "processing"}:
        raise RuntimeError(f"Unexpected status: {status}")
    time.sleep(2)

Cosmos Predict 2.5 Text To Video API — Frequently asked questions

What is the Cosmos Predict 2.5 Text To Video API?

Cosmos Predict 2.5 Text To Video is a WaveSpeedAI model for video generation, exposed as a REST API on WaveSpeedAI. Cosmos Predict 2.5 Text-to-Video generates video from text prompts using NVIDIA's 2B Cosmos Post-Trained Model. Ready-to-use REST inference API, best performance, no cold starts, affordable pricing. You can call it programmatically or try it from the playground above.

How do I call the Cosmos Predict 2.5 Text To Video API?

POST your input parameters to the model's REST endpoint (shown in the API tab of this playground) with your WaveSpeedAI API key in the Authorization header. Submission returns a prediction ID. Poll the result endpoint starting around every 2 seconds, increase the interval for long-running tasks, and stop on any terminal status. The playground generates production-oriented Python, JavaScript, and cURL examples with timeouts, transient-error handling, and safe GET retries. Full request/response shape is documented at https://wavespeed.ai/docs/docs-api/wavespeed-ai/cosmos-predict-2.5-text-to-video.

How much does Cosmos Predict 2.5 Text To Video cost per run?

Cosmos Predict 2.5 Text To Video starts at $0.30 per run. That figure is the base price — the final charge scales with the parameters you set in the form (output size, length, count, references, or whatever knobs this model exposes), so a higher-quality or larger output costs more than a minimal one. The exact cost for your current input is shown live next to the Generate button before you submit, and the actual per-call charge is recorded on the prediction afterwards.

What inputs does Cosmos Predict 2.5 Text To Video accept?

Key inputs: `prompt`. The full JSON schema (types, defaults, allowed values) is rendered above the Generate button and mirrored in the API reference at https://wavespeed.ai/docs/docs-api/wavespeed-ai/cosmos-predict-2.5-text-to-video.

How long does Cosmos Predict 2.5 Text To Video take to generate?

Median end-to-end generation time on WaveSpeedAI is around 125 seconds per request, based on recent successful runs. Queue time varies with global demand; live status is visible in the prediction record.

Can I use Cosmos Predict 2.5 Text To Video outputs commercially?

Commercial usage rights depend on the model's license, set by its provider (WaveSpeedAI). The license summary appears on the model card above; see WaveSpeedAI's Terms of Service for platform-level conditions.