Multimodal search, simplified.
Semantic and visual search across video, images and text in just 2 API calls - from any database or object storage.
Even bring your own database Read moreSearch Across Any Media Type
Find exactly what you need using natural language, images, or video clips as search input
"People working in a warehouse"
Video Matches
Image Matches
Semantic Search
Use natural language to search across videos, images, and documents.
Visual Query
Similar Content
Visual Search
Upload an image or video clip to find visually similar content.
Video Input
"similar scenes in black and white"
Text Input
Location: Outside
Filter
Combined Results
Multimodal result relevance:
Visual: 85%+
Text: 75%+
Hybrid Search
Combine images, text, video clips, and metadata filters for precise, multimodal search results.
Multimodal Search
Text, images and video in a single query.
Safety Incident:
Clips showing a person falling, or containing the phrase
'workplace accident'
Property Damage:
Content matching this reference photo of water damage or mentioning 'flooding',
'leaks', or 'water damage'
Fire Safety:
Similar scenes to this video clip of smoke, or content discussing fire
hazards and emergency
protocols
Equipment Issues:
Match this audio of machine malfunction sounds or text descriptions of
'equipment
failure' and
'maintenance needed'
For developers, by developers
Integrate the latest multimodal AI search with just a few lines of code.
import requests
url = "https://api.mixpeek.com/index/videos/url"
headers = {
"Authorization": "Bearer API-KEY",
"Content-Type": "application/json"
}
payload = {
"url": "https://example.com/video.mp4",
"collection_id": "my_collection",
"feature_extractors": [{
"embed": [
{
"type": "url",
"vector_index": "multimodal"
}
],
"transcribe": {"enabled": True},
"describe": {"enabled": True}
}]
}
{
"message": "Video indexing started",
"task_id": "task_123",
"metadata": {
"duration": 120,
"format": "mp4",
"size": 15000000
},
"features": {
"embeddings": 1,
"transcription": True,
"description": True
}
}
import requests
url = "https://api.mixpeek.com/features/search"
headers = {
"Authorization": "Bearer API-KEY",
"Content-Type": "application/json"
}
payload = {
"queries": [{
"type": "text",
"value": "person walking on beach",
"vector_index": "multimodal"
}],
"collection_ids": ["my_collection"],
"group_by": {"field": "asset_id"}
}
{
"results": [{
"asset_id": "video_123",
"group": [{
"feature_id": "feat_123",
"start_time": 10.5,
"end_time": 12.5,
"relevance": 0.92,
"description": "Person walking along beach",
"transcription": "A peaceful beach scene",
"url": "https://example.com/video.mp4"
}]
}],
"elapsed_time": 0.15
}Built for any vision use case
Whether you're building a basic image search or a sophisticated video understanding system, Mixpeek's APIs scale with your needs - no reengineering required.
The Problem
Out with the old...
Tedious Annotations
Manually logging videos is time-consuming and unscalable.
Limited Transcriptions
Transcripts miss critical elements of your video, such as visuals and sounds.
Basic Object Detection
Object-level tags miss the context needed to add real value to your video.
It even sits quietly in your current stack
Connect once to your existing storage, and let Mixpeek handle the rest. No data migration or infrastructure changes required.
Zero Platform Risk
Fully managed or self-hosted
Easy to Use
Get started on the free plan with an easy-to-use API or the Python client.
Scalable
Scale from zero to billions of items, with no downtime and minimal latency impact.
Pay for What you Use
Start free, then pay only for what you use with usage-based pricing.
Free Forever Tier
We will never charge you if you maintain under the file quota.
Reliable
Choose a cloud provider and region — we'll take care of uptime, consistency, and the rest.
Secure
mixpeek is SOC 2 Type II and GDPR-ready. It's built to keep data secure. See our security stance.