Groq

Add the x-props-provider: groq header.

Call Groq via the OpenAI SDK

Props AI supports Groq queries via the OpenAI SDK.

We'll take care of creating a mapping between the OpenAI SDK and the Groq API, from formatting the request to handling the response.

import os
from openai import OpenAI
 
client = OpenAI(
    api_key=process.env.GROQ_API_KEY,
    base_url="https://proxy.getprops.ai",
    default_headers={
        "x-props-key": process.env.PROPS_API_KEY,
        "x-props-provider": "groq"
    }
)
 
chat_completion = client.chat.completions.create(
    messages=[
        {
            "role": "user",
            "content": "Say this is a test",
        }
    ],
    model="llama3-8b-8192",
    user="<USER_ID or STRIPE_SUBSCRIPTION_ID or INTERNAL_PROCESS_ID>"
)

Groq SDK

from groq import Groq
import json
 
client = Groq(
    base_url="https://proxy.getprops.ai",
    api_key="<GROQ_API_KEY>",
    default_headers={
        "x-props-key": "<PROPS_API_KEY>",
        "x-props-provider": "groq",
    }
)
 
chat_completion = client.chat.completions.create(
    messas=[
        {
            "role": "user",
            "content": "Explain the importance of fast language models",
        }
    ],
    model="llama3-8b-8192",
    user="<USER_ID or STRIPE_SUBSCRIPTION_ID or INTERNAL_PROCESS_ID>"
)

REST

curl -X POST https://proxy.getprops.ai/openai/v1/chat/completions \
-H "Authorization: Bearer $GROQ_API_KEY" \
-H "Content-Type: application/json" \
-H "x-props-key: $PROPS_API_KEY" \
-H "x-props-provider: groq" \
-d '{
    "messages": [
        {
            "role": "user",
            "content": "Explain the importance of fast language models."
        }
    ],
    "model": "llama3-8b-8192",
    "user": "<USER_ID or STRIPE_SUBSCRIPTION_ID or INTERNAL_PROCESS_ID>"
}'

OpenAI Anthropic