ScaledThought
← All models

Alibaba

Qwen3-Embedding-8B

Live · US + CAtextApache 2.0

Topped the MTEB multilingual leaderboard at release, and still the standard open embedding family.

Price per 1M tokens

Input

$0.10

Priced per model · Same in US and CA · Free tier included · Pricing

Specs

Model id
qwen3-embedding-8b
Weights released
Jun 5, 2025
Parameters
8B
Architecture
Dense
Context
32K tokens (32,768)
Input
text
License
Apache 2.0
Regions
us, ca

Benchmarks

  • MTEB Multilingual70.58%

Sources: huggingface.co · qwenlm.github.io

Use it

Three lines of code, or zero.

OpenAI-compatible. Use the model id below, or auto to let the router decide when this model is worth it.

Quickstart→
import os
from openai import OpenAI

client = OpenAI(base_url=os.environ["ST_BASE_URL"], api_key=os.environ["ST_API_KEY"])
vec = client.embeddings.create(model="qwen3-embedding-8b", input="open weights, served hot")

Opens your agent with the prompt typed. You press Enter.