Banner background

    Announcing our $11.8M Series Seed.

    Read more

    Qwen 3 Embedding 4B

    Qwen3-Embedding-4B is a powerful text embedding model that generates high-quality vector representations for semantic search, retrieval-augmented generation, and similarity matching tasks, supporting multiple languages with state-of-the-art performance.

    Qwen 3 Embedding 4B model graphic

    API Usage

    API IDENTIFIER

    qwen/qwen3-embedding-4b
    import OpenAI from "openai";

const openai = new OpenAI({
  baseURL: "https://api.inference.net/v1",
  apiKey: process.env.INFERENCE_API_KEY,
});

const embedding = await openai.embeddings.create({
  model: "qwen/qwen3-embedding-4b",
  input: "The food was delicious and the waiter...",
  encoding_format: "float",
});

console.log(embedding.data[0].embedding);
    MODEL PROVIDERQwen
    TYPEEmbeddings
    PARAMETERS4B
    CONTEXT LENGTH32K
    PRICINGInput $0.01 / Million Tokens
    DEPLOYMENT
    Serverless
    Batch
    DOCUMENTATION

    Own your model. Scale with confidence.

    Schedule a call with our research team to learn more about custom training. We'll propose a plan that beats your current SLA and unit cost.