Llama 3.3 70B Speculative Decoding

Send a message to start chatting

Try asking: "Hello, how are you?"

Use in your App

Integrate models into your app using any OpenAI compatible client. Oxen.ai provides access to all models through a unified endpoint and API Key.

curl -X POST  \
  https://hub.oxen.ai/api/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d '{
    "model": "groq:llama-3.3-70b-specdec",
    "messages": [
      {
        "role": "user",
        "content": "What is a strong, powerful name for an ox?"
      }
    ]
  }'