Models

Qwen3 Reranker 8B

qwen3-reranker-8bOpen-weight multilingual reranker.

Input / 1M tokens

Free

$0 / token

Output / 1M tokens

Free

$0 / token

Uptime · 24h

—

No traffic yet

Details

Type
Rerank
Input
text
Output
rerank

Supported parameters

querydocumentstop_nreturn_documents

Last 24 hours

Requests per hour; red = provider errors.

Avg latency
—
Avg first token
—
Throughput
—

Use it

curl https://api.ultragpt.pro/v1/chat/completions \
  -H "Authorization: Bearer $ULTRAGPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3-reranker-8b",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'