All AI models · LLM benchmarks · Methodology

Alibaba

Qwen 3 Embedding 4B

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Model facts

Context window
32K tokens
Maximum output
2K tokens
Cheapest paid input
$0.01 per 1M tokens
Cheapest paid output
free per 1M tokens
Open weights
yes
Providers
4

Capabilities and modalities

temperature control, open weights, text.

Observed price history

  • 2026-08-24: $0.01 input / free output per 1M tokens

API providers

  • Hugging Face — model id Qwen/Qwen3-Embedding-4B; $0.01 input / free output per 1M tokens; provider documentation
  • Inference — model id qwen/qwen3-embedding-4b; $0.01 input / free output per 1M tokens; provider documentation
  • Privatemode AI — model id qwen3-embedding-4b; $0.15 input / free output per 1M tokens; provider documentation
  • Vercel AI Gateway — model id alibaba/qwen3-embedding-4b; not published input / not published output per 1M tokens; provider documentation