Vultron Retriever Flash 0.8B vultron-retriever-flash-qwen3.5-0.8b

curl https://api.vultrinference.com/v1/rerank \
  -H "Authorization: Bearer $VULTR_INFERENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "vultron-retriever-flash-qwen3.5-0.8b",
    "query": "What is the capital of France?",
    "documents": [
      "Berlin is the capital of Germany.",
      "Paris is the capital of France."
    ],
    "top_n": 1
  }'

import os
import requests

response = requests.post(
    "https://api.vultrinference.com/v1/rerank",
    headers={"Authorization": f"Bearer {os.environ['VULTR_INFERENCE_API_KEY']}"},
    json={
        "model": "vultron-retriever-flash-qwen3.5-0.8b",
        "query": "What is the capital of France?",
        "documents": [
            "Berlin is the capital of Germany.",
            "Paris is the capital of France.",
        ],
        "top_n": 1,
    },
)
print(response.json())

const response = await fetch("https://api.vultrinference.com/v1/rerank", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.VULTR_INFERENCE_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "vultron-retriever-flash-qwen3.5-0.8b",
    "query": "What is the capital of France?",
    "documents": [
      "Berlin is the capital of Germany.",
      "Paris is the capital of France."
    ],
    "top_n": 1
  }),
});
console.log(await response.json());