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.

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 PROVIDER	Qwen
TYPE	Embeddings
PARAMETERS	4B
CONTEXT LENGTH	32K
PRICING	Input $0.01 / Million Tokens
DEPLOYMENT	Serverless Batch
DOCUMENTATION

Save up to 90% on Qwen 3 Embedding 4B inference

Deploy in under five minutes and immediately start saving money on your inference bill.