Inference

Qwen 3 Embedding 4B

Name: Qwen 3 Embedding 4B
Brand: Inference

Canonical ID: inference/qwen/qwen3-embedding-4b

More Inference models More qwen3-embedding-4b family models

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Reasoning: No Tool use: No Open weights

Overview

text

Provider: Inference
Family: qwen3-embedding-4b
Release date: 2025-01-01
Last updated: 2025-01-01
Input modalities: text
Output modalities: text

Pricing and Limits

Token pricing

Input: $0.01/1M
Output: $0/1M
Cached input: N/A

Context and output

Context window: 32,000
Max output tokens: 2,048
Qualified ID: inference/qwen/qwen3-embedding-4b

Model Summary

Qwen 3 Embedding 4B is a model listing in the Inference provider catalog. It is categorized under the qwen3-embedding-4b family.

The model supports text modalities across input/output paths. Reported context capacity is 32,000. Pricing is listed at $0.01/1M input and $0/1M output.

Same Family: qwen3-embedding-4b

Comparable models in the same family across providers.

Browse family

Model	Provider	Context	Input	Output
Qwen 3 Embedding 4B huggingface/Qwen/Qwen3-Embedding-4B	Hugging Face	32,000	$0.01/1M	$0/1M
Qwen3 Embedding 4B vercel/alibaba/qwen3-embedding-4b	Vercel AI Gateway	32,768	$0.02/1M	$0/1M
Qwen3-Embedding 4B privatemode_ai/qwen3-embedding-4b	Privatemode AI	32,000	$0/1M	$0/1M
Qwen: Qwen3 Embedding 4B openrouter/qwen/qwen3-embedding-4b	OpenRouter	32,768	$0.02/1M	$0/1M

Qwen 3 Embedding 4B

Overview

Pricing and Limits

Token pricing

Context and output

Model Summary

More From Inference

Google Gemma 3

Llama 3.1 8B Instruct

Llama 3.2 11B Vision Instruct

Llama 3.2 1B Instruct

Llama 3.2 3B Instruct

Mistral Nemo 12B Instruct

Osmosis Structure 0.6B

Qwen 2.5 7B Vision Instruct

Same Family: qwen3-embedding-4b