Llava 13B

llava-13b

Llava 13B is an AI model that transforms image content into meaningful text descriptions.

L40S 45GB

Fast Inference

REST API

Try in Console API Docs Examples

Model Information

Response Time~7 sec

StatusActive

Version

0.0.1

Updatedabout 2 months ago

Live Demo

Average runtime: ~7 seconds

Input

Configure model parameters

Prompt

A prompt is a starting text or question given to the AI to guide its response or generate content.

Are you allowed to swim here?

Max Tokens

Max tokens control the maximum length of the generated text by setting a limit on the number of words or characters.

1024

Image

An image input or output involves using pictures or graphics in the AI model's processes.

File upload is currently disabled

JPEGPNGJPGWEBP

Output

View generated results

Result

Preview, share or download your results with a single click.

["Yes, ","you ","are ","allowed ","to ","swim ","in ","the ","lake ","near ","the ","pier. ","The ","image ","shows ","a ","pier ","extending ","out ","into ","the ","water, ","and ","the ","water ","appears ","to ","be ","calm, ","making ","it ","a ","suitable ","spot ","for ","swimming. ","However, ","it ","is ","always ","important ","to ","be ","cautious ","and ","aware ","of ","any ","potential ","hazards ","or ","regulations ","in ","the ","area ","before ","swimming."]

Cost is calculated based on execution time.The model is charged at $0.0011 per second. With a $1 budget, you can run this model approximately 129 times, assuming an average execution time of 7 seconds per run.

API Reference

View Full Documentation

Prerequisites

Create an API Key from the Eachlabs Console
Install the required dependencies for your chosen language (e.g., requests for Python)

API Integration Steps

1. Create a Prediction

Send a POST request to create a new prediction. This will return a prediction ID that you'll use to check the result. The request should include your model inputs and API key.

import requests
import time

API_KEY = "YOUR_API_KEY"  # Replace with your API key
HEADERS = {
    "X-API-Key": API_KEY,
    "Content-Type": "application/json"
}

def create_prediction():
    response = requests.post(
        "https://api.eachlabs.ai/v1/prediction/",
        headers=HEADERS,
        json={
            "model": "llava-13b",
            "version": "0.0.1",
            "input": {
  "image": "your_file.image/jpeg",
  "top_p": 1,
  "prompt": "your prompt here",
  "max_tokens": 1024,
  "temperature": 0.2
}
        }
    )
    prediction = response.json()
    
    if prediction["status"] != "success":
        raise Exception(f"Prediction failed: {prediction}")
    
    return prediction["predictionID"]

2. Get Prediction Result

Poll the prediction endpoint with the prediction ID until the result is ready. The API uses long-polling, so you'll need to repeatedly check until you receive a success status.

def get_prediction(prediction_id):
    while True:
        result = requests.get(
            f"https://api.eachlabs.ai/v1/prediction/{prediction_id}",
            headers=HEADERS
        ).json()
        
        if result["status"] == "success":
            return result
        elif result["status"] == "error":
            raise Exception(f"Prediction failed: {result}")
        
        time.sleep(1)  # Wait before polling again

3. Complete Example

Here's a complete example that puts it all together, including error handling and result processing. This shows how to create a prediction and wait for the result in a production environment.

try:
    # Create prediction
    prediction_id = create_prediction()
    print(f"Prediction created: {prediction_id}")
    
    # Get result
    result = get_prediction(prediction_id)
    print(f"Output URL: {result['output']}")
    print(f"Processing time: {result['metrics']['predict_time']}s")
except Exception as e:
    print(f"Error: {e}")

Additional Information

The API uses a two-step process: create prediction and poll for results
Response time: ~7 seconds
Rate limit: 60 requests/minute
Concurrent requests: 10 maximum
Use long-polling to check prediction status until completion