Meta: Llama 3.3 70B Instruct

models/Llama 3.3 70B Instruct

Overview

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model is optimized for multilingual dialogue use cases and outperforms many of the available open source and closed chat models on common industry benchmarks. Supported languages: English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai. [Model Card](https://github.com/meta llama/llama models/blob/main/models/llama3_3/MODEL_CARD.md)

Currency$USD

Input$0.72

Output$0.72

Context window131.1K

Generate API Key Generate your API Key to securely access IndoxHub's AI models. Integrate with OpenAI-compatible tools, run queries, and build powerful AI applications — all with a single secure key.

Endpoint

POSThttps://api.indoxhub.com/api/v1/chat/completions

Configmeta/llama3-3-70b-instruct

from indoxhub import Client
 
# Initialize the client
with Client(api_key="[LOGIN TO GET API KEY]") as client:
    # Generate a chat completion
    response = client.chat(
        messages=[{"role":"system","content":"You are a helpful assistant."},{"role":"user","content":"What is machine learning and why is it important?"}],
        model="meta/llama3-3-70b-instruct",
        temperature:"0.7"
    )
 
    # Print the response
    print(response["data"])

ResourcesDocumentation Python SDK