DeepSeek V4 Pro is Live → Try it now.

Model Library/Fireworks AI/Qwen3 Reranker 8B
Fireworks Logo Mark

Qwen3 Reranker 8B

Ready
Try in Playground
Deploy on Demand
accounts/fireworks/models/qwen3-reranker-8b

    significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining

    Qwen3 Reranker 8B API Features

    Serverless

    Docs

    Qwen3 Reranker 8B is available via Fireworks' serverless API, where you pay per token. There are several ways to call the Fireworks API, including Fireworks' Python client, the REST API, or OpenAI's Python client.

    On-demand Deployment

    Docs

    On-demand deployments allow you to use Qwen3 Reranker 8B on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

    Available Serverless

    Run queries immediately, pay only for usage

    $0.20
    Per 1M Tokens

    Metadata

    State
    Ready
    Created on
    10/7/2025
    Kind
    Embedding model
    Provider
    Fireworks AI

    Specification

    Calibrated
    No
    Mixture-of-Experts
    No
    Parameters
    8.18B

    Supported Functionality

    Fine-tuning
    Not supported
    Serverless
    Supported
    Context Length
    40.9k tokens
    Function Calling
    Not supported
    Embeddings
    Not supported
    Rerankers
    Not supported
    Support image input
    Not supported