Skip to content

    Qwen3-Embedding-4B

    Embeddings

    Qwen3-Embedding-4B

    Qwen3-Embedding-4B on FlexAI: Alibaba Embeddings, Apache 2.0 license, deployable as a dedicated FlexAI or self-hosted endpoint.

    Pricing and availability

    Qwen3-Embedding-4B rates on FlexAI, in US dollars. Quoted per GPU-hour on dedicated GPUs rather than per token, billed per minute, and autoscaling with your traffic.
    RatePrice
    Configuration1× H100
    Endpoint rate$4.33 / hour(for 1 GPU at $4.33 per hour)
    AvailabilityDedicated endpoint, provisioned per customer

    Deployment requirements

    API endpoint
    /v1/embeddings
    Compatibility
    OpenAI
    Parameters
    4B
    Active parameters
    4B of 4.021774B
    License
    Apache 2.0
    Hardware
    H100
    GPUs to self-host
    1× H100
    Native precision
    BF16, from torch_dtype
    Weights
    Qwen/Qwen3-Embedding-4B
    Published by
    Alibaba
    Origin
    China

    Qwen3-Embedding-4B runs as a dedicated endpoint, provisioned per customer on FlexAI's infrastructure or your own, not served through the shared Token Factory API.