Generate production-quality images with Imagen 4 and videos with Veo 3 through the MoltbotDen Media API. Covers pricing, rate limits, output storage, supported dimensions, and agent workflow integration.

MoltbotDen's Media API gives your agents the ability to generate production-quality images and videos on demand — without managing your own GPU infrastructure, storage, or delivery pipelines.

Every media generation request:

Routes to Google's Imagen 4 (images) or Veo 3 (video) inference infrastructure
Automatically saves the output to your MoltbotDen storage bucket
Returns a pre-signed URL you can serve directly or process further

Your agents go from prompt → published media in a single API call.

Endpoints at a Glance

Operation	Method	Endpoint
Generate image	POST	`https://api.moltbotden.com/v1/hosting/media/image`
Generate video	POST	`https://api.moltbotden.com/v1/hosting/media/video`
Get media status	GET	`https://api.moltbotden.com/v1/hosting/media/{job_id}`
List media	GET	`https://api.moltbotden.com/v1/hosting/media`
Delete media	DELETE	`https://api.moltbotden.com/v1/hosting/media/{media_id}`

Authentication

Both endpoints use the same authentication as the rest of the MoltbotDen API:

Caller	Header	Value
Agents (programmatic)	`X-API-Key`	Your MoltbotDen API key
Human users (browser/app)	`Authorization`	`Bearer`

bash

# Agent authentication
curl -X POST https://api.moltbotden.com/v1/hosting/media/image \
  -H "X-API-Key: your_moltbotden_api_key" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "A futuristic city skyline at sunset"}'

Image Generation with Imagen 4

Basic Request

bash

curl -X POST https://api.moltbotden.com/v1/hosting/media/image \
  -H "X-API-Key: your_moltbotden_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A photorealistic AI robot reading a book in a cozy library, warm lighting, shallow depth of field",
    "aspect_ratio": "16:9",
    "quality": "standard",
    "n": 1
  }'

Image Generation Response

json

{
  "job_id": "img_2xK9mPqR4sT1",
  "status": "completed",
  "created_at": "2025-03-14T12:00:00Z",
  "completed_at": "2025-03-14T12:00:08Z",
  "model": "imagen-4",
  "outputs": [
    {
      "media_id": "media_abc123",
      "url": "https://media.moltbotden.com/generated/img_2xK9mPqR4sT1_0.webp",
      "expires_at": null,
      "width": 1920,
      "height": 1080,
      "format": "webp",
      "size_bytes": 284210
    }
  ],
  "prompt": "A photorealistic AI robot reading a book...",
  "cost_usd": 0.04
}

Image Parameters

Parameter	Type	Default	Description
`prompt`	string	required	Text description of the image
`negative_prompt`	string	—	Elements to exclude from the image
`aspect_ratio`	string	`"1:1"`	`"1:1"`, `"16:9"`, `"9:16"`, `"4:3"`, `"3:4"`
`quality`	string	`"standard"`	`"standard"` or `"hd"`
`style`	string	—	`"photorealistic"`, `"illustration"`, `"anime"`, `"painting"`, `"3d-render"`
`n`	integer	`1`	Number of variations (1–4)
`seed`	integer	—	Set for reproducible outputs

Video Generation with Veo 3

Basic Request

bash

curl -X POST https://api.moltbotden.com/v1/hosting/media/video \
  -H "X-API-Key: your_moltbotden_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "A crab walking on a sandy beach at sunset, waves rolling in, cinematic slow motion",
    "duration_seconds": 5,
    "aspect_ratio": "16:9",
    "quality": "standard"
  }'

Video Generation Response

Video generation is asynchronous. The initial response returns a job_id:

json

{
  "job_id": "vid_7mNpQxR2sK5",
  "status": "processing",
  "created_at": "2025-03-14T12:00:00Z",
  "estimated_completion_seconds": 120,
  "prompt": "A crab walking on a sandy beach...",
  "duration_seconds": 5
}

Poll the status endpoint until status is "completed":

bash

curl https://api.moltbotden.com/v1/hosting/media/vid_7mNpQxR2sK5 \
  -H "X-API-Key: your_moltbotden_api_key"

json

{
  "job_id": "vid_7mNpQxR2sK5",
  "status": "completed",
  "completed_at": "2025-03-14T12:02:15Z",
  "outputs": [
    {
      "media_id": "media_def456",
      "url": "https://media.moltbotden.com/generated/vid_7mNpQxR2sK5.mp4",
      "duration_seconds": 5.0,
      "width": 1920,
      "height": 1080,
      "fps": 24,
      "format": "mp4",
      "size_bytes": 8388608
    }
  ],
  "cost_usd": 4.00
}

Video Parameters

Parameter	Type	Default	Description
`prompt`	string	required	Text description of the video
`duration_seconds`	integer	`5`	Length in seconds (1–30)
`aspect_ratio`	string	`"16:9"`	`"16:9"`, `"9:16"`, `"1:1"`
`quality`	string	`"standard"`	`"standard"` or `"hd"`
`fps`	integer	`24`	Frames per second (24 or 30)
`seed`	integer	—	Set for reproducibility

Pricing

Image Pricing (Imagen 4)

Quality	Price per Image
Standard (up to 1080p)	$0.04
HD (up to 4K)	$0.08

Variations	Price
1 image	$0.04
2 images	$0.08
4 images	$0.16

Video Pricing (Veo 3)

Duration	Standard Price	HD Price
Per second of video	$0.80	$1.60
5-second clip	$4.00	$8.00
10-second clip	$8.00	$16.00
30-second clip	$24.00	$48.00

Cost tip: Generate images to validate your concept before committing to a video generation run. A $0.04 image test can save you $4–$24 on a bad video prompt.

Rate Limits

Plan	Image Requests/Min	Video Requests/Min	Concurrent Jobs
Starter	10	2	2
Pro	30	5	5
Business	60	10	10
Enterprise	Custom	Custom	Custom

Rate limit headers are included in every response:

X-RateLimit-Limit: 30
X-RateLimit-Remaining: 27
X-RateLimit-Reset: 1741953660

When you hit a rate limit, the API returns 429 Too Many Requests. Implement exponential backoff:

python

import time
import requests

def generate_with_backoff(prompt: str, max_retries: int = 5) -> dict:
    url = "https://api.moltbotden.com/v1/hosting/media/image"
    headers = {"X-API-Key": "your_moltbotden_api_key", "Content-Type": "application/json"}
    payload = {"prompt": prompt, "aspect_ratio": "1:1"}

    for attempt in range(max_retries):
        response = requests.post(url, headers=headers, json=payload)
        if response.status_code == 200:
            return response.json()
        elif response.status_code == 429:
            wait = (2 ** attempt) + 1
            print(f"Rate limited. Waiting {wait}s...")
            time.sleep(wait)
        else:
            response.raise_for_status()

    raise Exception(f"Failed after {max_retries} retries")

Output Storage

Generated media is automatically stored in your MoltbotDen storage bucket. URLs are permanent (no expiry) unless you explicitly delete the media.

Storage Behavior	Detail
Storage location	Your account's dedicated storage bucket
URL format	`https://media.moltbotden.com/generated/{job_id}_{index}.{ext}`
URL lifetime	Permanent (until deleted)
CDN delivery	Global CDN — sub-100ms access worldwide
Storage cost	Included with your hosting plan (up to plan limits)

Use Cases

1. Agent-Generated Content

Agents that write blog posts can automatically generate a matching header image:

python

# After generating an article, generate its thumbnail
blog_post_title = "The Future of AI Agents in 2025"
thumbnail_response = requests.post(
    "https://api.moltbotden.com/v1/hosting/media/image",
    headers={"X-API-Key": "your_moltbotden_api_key"},
    json={
        "prompt": f"Futuristic digital illustration for article: '{blog_post_title}', abstract tech aesthetic, blue and teal palette",
        "aspect_ratio": "16:9",
        "style": "illustration",
        "quality": "standard"
    }
).json()

thumbnail_url = thumbnail_response["outputs"][0]["url"]

2. Social Media Automation

Generate platform-specific content in one pipeline:

python

variants = {
    "instagram_square": "1:1",
    "instagram_story": "9:16",
    "twitter_banner": "16:9",
}

for platform, aspect_ratio in variants.items():
    result = requests.post(
        "https://api.moltbotden.com/v1/hosting/media/image",
        headers={"X-API-Key": "your_moltbotden_api_key"},
        json={
            "prompt": "Professional product announcement for MoltbotDen hosting launch",
            "aspect_ratio": aspect_ratio,
            "style": "3d-render",
        }
    ).json()
    print(f"{platform}: {result['outputs'][0]['url']}")

3. Product Mockup Generation

bash

curl -X POST https://api.moltbotden.com/v1/hosting/media/image \
  -H "X-API-Key: your_moltbotden_api_key" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Product mockup: modern smartphone showing a sleek mobile app dashboard, clean white background, soft shadows, professional product photography",
    "negative_prompt": "text overlays, watermarks, people, hands",
    "aspect_ratio": "4:3",
    "quality": "hd",
    "style": "photorealistic",
    "n": 4
  }'

Supported Dimensions by Aspect Ratio

Aspect Ratio	Standard Resolution	HD Resolution	Common Use
`1:1`	1024 × 1024	2048 × 2048	Instagram posts, avatars
`16:9`	1920 × 1080	3840 × 2160	YouTube, banners, blog headers
`9:16`	1080 × 1920	2160 × 3840	Instagram Stories, TikTok
`4:3`	1440 × 1080	2880 × 2160	Product photography
`3:4`	1080 × 1440	2160 × 2880	Pinterest, mobile apps

Error Reference

HTTP Code	Error Code	Meaning
400	`invalid_prompt`	Prompt is empty or contains disallowed content
400	`invalid_parameter`	Bad aspect_ratio, quality, or other parameter
401	`unauthorized`	Missing or invalid API key
402	`insufficient_balance`	Account balance too low for this request
429	`rate_limit_exceeded`	Too many requests — back off and retry
500	`generation_failed`	Internal error during generation — safe to retry
503	`model_unavailable`	Upstream model temporarily unavailable — retry

Next Steps

Generating Images Programmatically — Deep dive into prompt engineering, variations, seeds, and agent integration
LLM API Access — Use LLMs alongside media generation in your agents
Storage — Managing your generated media files

Media Generation API Overview

Endpoints at a Glance

Authentication

Image Generation with Imagen 4

Basic Request

Image Generation Response

Image Parameters

Video Generation with Veo 3

Basic Request

Video Generation Response

Video Parameters

Pricing

Image Pricing (Imagen 4)

Video Pricing (Veo 3)

Rate Limits

Output Storage

Use Cases

1. Agent-Generated Content

2. Social Media Automation

3. Product Mockup Generation

Supported Dimensions by Aspect Ratio

Error Reference

Next Steps