qwen3-embedding-8b

Name: qwen3-embedding-8b
Author: Vercel AI Gateway

embed8B

Context

41K

Input price

$0.05/1M tokens

Output price

$0/1M tokens

Capabilities

vision

tool call

structured output

reasoning

json mode

streaming

fine tuning

batch

Details

Model IDalibaba/qwen3-embedding-8b

ProviderVercel AI Gateway

CreatorQwen

Familyqwen3

License—

Parameters8B

Status—

Input modalities—

Output modalities—

Architecture—

Knowledge cutoff—

Training data cutoff—

Release date—

Deprecation date—

Typeembed

Reasoning tokens—

Max input—

Open weight—

Sourceofficial

Last updated2026-08-05

Pricing

Input

$0.05

Output

Cache write

—

Cache read

—

Batch in

—

Batch out

—

Family Comparison: qwen3

Model	Caps	Perf	Speed	Context	Max out	Pricing
qwen3-embedding-0.6b	RVTS	—	—	33K	—	$0.01$0
qwen3-embedding-4b	RVTS	—	—	33K	—	$0.02$0
qwen3-embedding-8b	RVTS	—	—	41K	—	$0.05$0
qwen3-coder-30b-a3b	RVTS	—	—	262K	—	$0.15$0.6
qwen3-next-80b-a3b-instruct	RVTS	—	—	262K	—	$0.15$1.2
qwen3-next-80b-a3b-thinking	RVTS	—	—	262K	—	$0.15$1.2
qwen3-vl-235b-a22b-instruct	RVTS	—	—	262K	—	$0.2$0.88
qwen3-vl-instruct	RVTS	—	—	262K	—	$0.2$0.88
qwen3-coder	RVTS	—	—	262K	—	$0.22$1.8
qwen3-235b-a22b-thinking	RVTS	—	—	262K	—	$0.23$2.3
qwen3-vl-thinking	RVTS	—	—	131K	—	$0.4$3.95
qwen3-coder-next	RVTS	—	—	256K	66K	$0.5$1.2
qwen3-coder-plus	RVTS	—	—	1M	66K	$1$5
qwen3-max-preview	RVTS	—	—	262K	—	$1.2$6
qwen3-max-thinking	RVTS	—	—	256K	—	$1.2$6
qwen3-max	RVTS	—	—	262K	33K	$1.2$6

API

GET/v1/models/vercel/alibaba/qwen3-embedding-8b

qwen3-embedding-8b

alibaba/qwen3-embedding-8b

Changes · 3 entries

alibaba/qwen3-embedding-8bupdate19c9fe3Aug 5, 2026, 03:04 PM

context_window32800→41000

alibaba/qwen3-embedding-8bupdate2b100acMar 23, 2026, 05:30 AM

parameters8

alibaba/qwen3-embedding-8bcreateb50649fMar 21, 2026, 11:58 PM