Inference (Reseller)
Qwen 3 Embedding 4B Pricing
API pricing for Qwen 3 Embedding 4B via Inference. Input tokens cost $0.01/1M, output tokens cost $0/1M with 32K context window.
Last updated:
Input Cost
$0.01
per 1M tokens
Output Cost
$0
per 1M tokens
Context Window
32K
tokens
Cost Calculator
Estimated Cost:
$0.00
Model Details
Reseller
Inference
Model ID
qwen/qwen3-embedding-4b
Context Window
32K tokens
Max Output
2048 tokens
Sources