LLM Reference

Using Qwen3 Reranker 8B on Novita AI

Implementation guide · Qwen3 Reranker · Alibaba

Serverless

Quick Start

  1. 1
    Create an account at Novita AI and generate an API key.
  2. 2
    Use the Novita AI SDK or REST API to call qwen3-reranker-8b.
  3. 3
    You'll be billed $0.05/1M input. See full pricing.

Code Examples

Code examples for this provider have not been sourced yet.

About Novita AI

Novita AI offers a GPU-based inference API for image, video, and language model generation with a broad catalog of open-source models.

Pricing on Novita AI

TypePrice (per 1M)
Input tokens$0.05

Capabilities

No model capability flags are currently sourced.

About Qwen3 Reranker 8B

Qwen3 Reranker 8B is Alibaba's multilingual reranking model from the Qwen3 generation, designed for retrieval-augmented generation pipelines. Open-sourced under Apache 2.0. Achieves 81.22 on MTEB-Code and 72.94 on MMTEB-R. Released alongside Qwen3 Embedding series June 2025.

Model Specs

Released2025-06-06
Parameters8B
Context33K
ArchitectureDecoder Only

Provider

Novita AI