Skip to content
AnyRouter

Qwen3 Embedding 4B

Embeddings
qwen/qwen3-embedding-4b

Embed · 2560 dimensions · Oct 2025 · 3 upstreams

Qwen3 Embedding 4B is the open-weight 4B size in the Qwen3 embedding and reranking family. It embeds text over a 32,768-token window at 2,560 dimensions, and supports 100+ languages and Matryoshka truncation from 32 to 2,560 dimensions.

Needs your own keyTo use Qwen3 Embedding 4B, add a key from OpenRouter, Nous Research or SiliconFlow. AnyRouter adds no fee.
max input
33K
dimensions
2560
input / 1M (list)
$0.02
routes
3

Upstreams

3
  1. 1OpenRouterYour keynot addedBilled to your key
  2. 2Nous ResearchYour keynot addedBilled to your key
  3. 3SiliconFlowYour keynot addedBilled to your key

Quick start

POST /api/v1/embeddings
curl
curl https://anyrouter.dev/api/v1/embeddings \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3-embedding-4b",
    "input": "The quick brown fox jumps over the lazy dog"
  }'

Details

Owner
Qwen
Kind
Embeddings
Released
Oct 2025
Context
33K
Data policy
Provider retention
Endpoint
/api/v1/embeddings