Nebius Token Factory

Qwen3-Embedding-8B

Name: Qwen3-Embedding-8B
Brand: Nebius Token Factory

Canonical ID: nebius/Qwen/Qwen3-Embedding-8B

More Nebius Token Factory models More qwen3-embedding-8b family models

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

Reasoning: No Tool use: No Open weights

Overview

text

Provider: Nebius Token Factory
Family: qwen3-embedding-8b
Release date: 2026-01-10
Last updated: 2026-02-04
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: 32,768
Max output tokens: —
Qualified ID: nebius/Qwen/Qwen3-Embedding-8B

Model Summary

Qwen3-Embedding-8B is a model listing in the Nebius Token Factory provider catalog. It is categorized under the qwen3-embedding-8b family.

The model supports text modalities across input/output paths. Reported context capacity is 32,768. Pricing is listed at $0.01/1M input and $0/1M output.

Same Family: qwen3-embedding-8b

Comparable models in the same family across providers.

Browse family

Model	Provider	Context	Input	Output
Qwen 3 Embedding 8B huggingface/Qwen/Qwen3-Embedding-8B	Hugging Face	32,000	$0.01/1M	$0/1M
Qwen3 Embedding 8B vercel/alibaba/qwen3-embedding-8b	Vercel AI Gateway	32,768	$0.05/1M	$0/1M
Qwen3 Embedding 8B evroc/Qwen/Qwen3-Embedding-8B	evroc	40,960	$0.12/1M	$0.12/1M
Qwen: Qwen3 Embedding 8B openrouter/qwen/qwen3-embedding-8b	OpenRouter	32,000	$0.01/1M	$0/1M

Qwen3-Embedding-8B

Overview

Pricing and Limits

Token pricing

Context and output

Model Summary

More From Nebius Token Factory

BGE-ICL

bge-multilingual-gemma2

DeepSeek-R1-0528

DeepSeek R1 0528 Fast

DeepSeek-V3-0324

DeepSeek-V3-0324 (Fast)

DeepSeek-V3.2

DeepSeek V4.1 Flash

Same Family: qwen3-embedding-8b