Pass IndexThe State of AISign in

Qwen3-Embedding-0.6B

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks.

text → text · made by Alibaba

$0.01per Mtok in
DeepInfra · 4 sellers

Sold by 5 ways

SellerLaneRate
Databricks cloudstandard$0.02per Mtok in$0.02per Mtok cached$0.02per Mtok cache writeraw.githubusercontent.com · read 2026-09-16
DigitalOcean cloudstandard$0.04per Mtok inmodels.dev · read 2026-09-16
DeepInfra aggregatorstandard$0.01per Mtok inapi.deepinfra.com · read 2026-08-25
Vercel AI Gateway aggregatorstandard$0.01per Mtok inai-gateway.vercel.sh · read 2026-08-25
Cloudflare 0 ways$0.012
Cloudflare aggregatornot on the seller's list todaystandard$0.012per Mtok indevelopers.cloudflare.com · read 2026-08-25

Measured 2 standings

PlaceBoardMetricScore
19thof 86MTEB · Multilingual (MTEB(Multilingual, v2))meanTask (mean score, 0-1)0.6434
25thof 183MTEB · English (MTEB(eng, v2))meanTask (mean score, 0-1)0.7047

About

Qwen3-Embedding-0.6B — a text model from Alibaba, sold by 4 companies from $0.01 per Mtok in, placed 25th of 183 on MTEB · English (MTEB(eng, v2)).

It takes text and returns text, with a context window of 32,768 tokens. It was published in June 2025. The catalogue files it under rerank. Four companies sell it. The cheapest is $0.01 per Mtok in at DeepInfra. It has been measured on 2 boards, and stands best at 25th of 183 on MTEB · English (MTEB(eng, v2)).

Every current figure

Maker
Alibaba
Register
model
Takes
text
Returns
text
Context
32,768 tokens
Published
June 2025
Parameters
600 million · read from its own name
Licence
not read
Sellers
4
Maker's own price
not read
Price
$0.01 per Mtok in — DeepInfra
Boards
2
Best place
25th of 183 — MTEB · English (MTEB(eng, v2))

Known as 3 names

Qwen/Qwen3-Embedding-0.6B@cf/qwen/qwen3-embedding-0.6balibaba/qwen3-embedding-0.6b