Groq

Overview

Groq serves open models on its custom LPU (Language Processing Unit) hardware, delivering extremely low latency and high throughput through an OpenAI-compatible API.

Official Website: https://groq.com API Documentation: https://console.groq.com/docs

Key features

• Ultra-fast inference — LPU-accelerated for minimal latency
• High throughput — well-suited to real-time and interactive applications
• Chat — OpenAI-compatible text generation with function calling
• Vision — image understanding
• Speech — speech-to-text and text-to-speech
• JSON mode — structured, schema-constrained outputs
• Batch — asynchronous bulk processing

Using Groq with Yunxin

Address Groq models by prefixing the model id with the groq slug — groq/<model>. You always call the same Yunxin base URL, https://api.yuhuanstudio.com/v1, with your sk- API key; Yunxin routes the request to Groq.

Usage example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["YUNXIN_API_KEY"],
    base_url="https://api.yuhuanstudio.com/v1",
)

response = client.chat.completions.create(
    model="groq/model-id",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"},
    ],
)

print(response.choices[0].message.content)

Available models

List the models currently available for this provider:

curl "https://api.yuhuanstudio.com/v1/models?provider=groq" \
  -H "Authorization: Bearer $YUNXIN_API_KEY"

Official resources

• Groq Website
• Console
• Documentation