← All models
Qwen: Qwen3 Embedding 8B
qwen/qwen3-embedding-8bembeddings
The flagship text embedding model of the Qwen3 series: retrieval, clustering, RAG and ranking. Text-only (no multimodal input); strong multilingual coverage including Russian. $0.01/1M input tokens — noticeably cheaper than OpenAI.
Price
Released
Oct 28, 2025
Parameters
inputa string or array of stringsHow to use via API
from openai import OpenAI
client = OpenAI(base_url="https://api.mixen.ai/v1", api_key="mxn-...")
r = client.embeddings.create(
model="qwen/qwen3-embedding-8b",
input="Привет! Это Mixen AI.", # строка или список строк
)
vec = r.data[0].embedding
print(len(vec), vec[:3])