Qwen3 Reranker 8b API
Qwen's rerank model. Call it on 666 AI with the same API key as every other model. Pay as you go; prices follow the upstream in real time and this page updates hourly.
| Vendor | Qwen |
| Type | rerank |
| Price | $0.27 per 1M tokens |
| Model ID (use this in your request) | qwen/qwen3-reranker-8b |
How to call Qwen3 Reranker 8b
The API is OpenAI-compatible. Replace YOUR-ENDPOINT with the endpoint shown on your API Key page after you sign up, and YOUR-KEY with your key.
curl https://YOUR-ENDPOINT/v1/rerank \
-H "Authorization: Bearer YOUR-KEY" \
-H "Content-Type: application/json" \
-d '{"model": "qwen/qwen3-reranker-8b", "query": "capital of France", "documents": ["Paris is the capital of France.", "Bananas are yellow."]}'Similar models — price comparison
| Model | Price |
|---|---|
| Rerank 2.5 Lite | $0.027 per 1M tokens |
| Rerank 3 Lite | $0.027 per 1M tokens |
| Rerank 2.5 | $0.0675 per 1M tokens |
| Rerank 3 | $0.0675 per 1M tokens |
| Llama Nemotron Rerank VL 1b V2 | $0.0633 per 1M input tokens · $0.0633 per 1M output tokens |
| Nemotron 3.5 Rerank 8b | $0.0633 per 1M input tokens · $0.0633 per 1M output tokens |
More models from Qwen
| Model | Price |
|---|---|
| Qwen Image 2.0 Pro | $0.1013 per image |
| Qwen3.6 Plus | $0.4388 per 1M input tokens · $2.63 per 1M output tokens |
| Qwen3.7 Max | $2.7 per 1M input tokens · $8.1 per 1M output tokens |
| Qwen3.7 Plus | $0.432 per 1M input tokens · $1.73 per 1M output tokens |
| Qwen3.8 2.4T A95B | $2.7 per 1M input tokens · $8.1 per 1M output tokens |
| Qwen3.8 Flash | $0.2025 per 1M input tokens · $0.6345 per 1M output tokens |
| GLM 5.2 Fast Preview | $4.72 per 1M input tokens · $14.85 per 1M output tokens |
| Happyhorse 1.1 | $0.1334 – $0.1725 per second |
FAQ
How much does the Qwen3 Reranker 8b API cost?
On 666 AI, Qwen3 Reranker 8b costs $0.27 per 1M tokens. You pay only for what you use — no monthly fee. Prices follow the upstream in real time; this page updates every hour.
Can I use the official OpenAI SDK?
Yes. The API is OpenAI-compatible: in the OpenAI Python or Node.js SDK just change base_url and api_key, and set model to qwen/qwen3-reranker-8b.
How do I pay?
Bank card (including Google Pay / Apple Pay), USDT / ETH, or bank wire. Top up once and usage is deducted as you go.