Qwen 3 Embedding 4B
Embedding model for semantic search, retrieval, clustering, and ranking pipelines
Context
32,768
Max output
32,768
Input / 1M
$0.01
Output / 1M
Not listed
Providers
4
01Profile
Profile
Released
2025-01-01
Last updated
2025-06-06
Knowledge cutoff
2024-12
Weights
Open
02Capabilities
Capabilities
Input
text
Output
text
Reasoning
No
Tool calling
No
Structured output
No
Attachments
No
Cache read
—
Cache write
—
03Pricing
Pricing across 3 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
7+ recent events since 2025-01-01
2026-08-11Price upprivatemode-aiinput / 1MNot listed→ $0.15
2026-06-06Price upvercelinput / 1M$0.02→ new
2026-06-06Price upverceloutput / 1MNot listed→ new
2026-01-10Addedverceloffering→ new
2026-01-05Addedprivatemode-aioffering→ new
2025-10-20Addedhuggingfaceoffering→ new
2025-07-09Addedinferenceoffering→ new