Hugging Face model card
Fields: tags, gated, license, summary, base model, library name, pipeline tag
The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.
- Context
- 33K
- Max output
- Unknown
- Input
- $0.02
- Output
- $0.00
Recommended use cases
Strengths in this dataset
- 32,768-token context window
- text input
- 11 supported API parameters listed
Limits and caveats
- Provider behavior and pricing can change; verify the linked sources before production use.
Capability
Model-native facts
Model- Reasoning
- Unknown
- Open weights
- Unknown
Provider endpoint facts
Provider endpoint- Tool calling
- Not supported
- Structured output
- Supported
- Streaming
- Unknown
- Prompt cache
- Unknown
- Batch
- Unknown
- Fine-tuning
- Unknown
Qwen3 Embedding 4B Provider pricing
Provider endpoint: qwen/qwen3-embedding-4b
- Input
- $0.02 per 1M tokens
- Output
- $0.00 per 1M tokens
- Cached input
- Unknown per 1M tokens
- Image output
- Unknown per 1M tokens
Sources and verification
Official model documentation
Fields: model identity
OpenRouter Models API
Fields: identity, description, modalities, context window, maximum output, pricing, supported parameters
Frequently asked questions
Answers are generated from the same sourced model and provider facts shown above.
The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B). This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.
Model specifications and prices may vary by provider and change over time. AIToolly displays sources and verification dates so users can confirm critical details before production use.