Skip to main content

​
What is each::sense?

each::sense is an AI agent that provides a unified, OpenAI-compatible interface for generating images, videos, audio, and managing AI workflows. Instead of manually selecting models and parameters, describe what you want in natural language and the agent handles the rest. 
"Generate a cyberpunk cityscape at night" → Agent selects best model → Image generated

​
Key Features

  • OpenAI-compatible: Just plug in the OpenAI SDK with your each::labs API key
  • Intelligent model selection: Automatically picks the best model from 500+ available
  • Multi-modal: Text, images, videos, audio, and 3D models
  • Streaming: Real-time SSE streaming with 18 event types
  • Sessions: Persistent conversation memory for multi-turn interactions
  • Workflows: Create and execute multi-step AI pipelines via natural language
  • Behavior modes: Control how the agent handles requests

​
Base URL

https://eachsense-agent.core.eachlabs.run

​
Authentication

# Method 1: X-API-Key header (recommended)
curl -H "X-API-Key: YOUR_API_KEY" ...

# Method 2: Bearer token (OpenAI SDK compatible)
curl -H "Authorization: Bearer YOUR_API_KEY" ...

​
Endpoints

MethodPathDescription
POST/v1/chat/completionsChat completions (primary endpoint)
POST/workflowWorkflow builder
GET/v1/modelsList available models
GET/memoryGet session memory
DELETE/memoryClear session memory
GET/sessionsList all sessions

​
Quick Example

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_EACHLABS_API_KEY",
    base_url="https://eachsense-agent.core.eachlabs.run/v1"
)

response = client.chat.completions.create(
    model="eachsense/beta",
    messages=[{"role": "user", "content": "Generate a portrait photo"}],
    stream=True
)

for chunk in response:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

​
Supported Model Categories

CategoryExample Models
Image Generationflux-2-max, nano-banana-pro, seedream-v4-5
Video Generationveo-3, kling-3-0, wan-v2-6-image-to-video
Image Editingflux-2-edit, eachlabs-bg-remover-v1, topaz-upscale-image
Audio/Musicelevenlabs-text-to-speech, mureka-generate-music

​
Pricing

each::sense itself is completely free. You only get charged for the models it uses under the hood. When the agent picks a model to generate your image, video, or audio, you pay the same model cost as if you called each::api directly. The smart routing, natural language understanding, and orchestration? All on us.
Last modified on March 6, 2026