Hugging Face Inference

curl https://api-inference.huggingface.co/models/meta-llama/Llama-3.3-70B-Instruct/v1/chat/completions \
  -H "Authorization: Bearer $HF_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/Llama-3.3-70B-Instruct",
    "messages": [{"role": "user", "content": "Hello in 5 words"}]
  }'

from huggingface_hub import InferenceClient

client = InferenceClient(api_key="YOUR_HF_TOKEN")
resp = client.chat.completions.create(
    model="meta-llama/Llama-3.3-70B-Instruct",
    messages=[{"role": "user", "content": "Hello in 5 words"}],
)
print(resp.choices[0].message.content)

import { HfInference } from "@huggingface/inference";

const hf = new HfInference(process.env.HF_TOKEN);
const resp = await hf.chatCompletion({
  model: "meta-llama/Llama-3.3-70B-Instruct",
  messages: [{ role: "user", content: "Hello in 5 words" }],
});
console.log(resp.choices[0].message.content);