Qwen3 Embedding 4B vs Qwen3 Embedding 0.6B
Lower and Larger mark one number at a time; they don’t rank the models. How well a model does depends on your task; see Benchmarks for measured results.
| Detail | Qwen3 Embedding 4Balibaba/qwen3-embedding-4b | Qwen3 Embedding 0.6Balibaba/qwen3-embedding-0.6b |
|---|---|---|
| Maker | alibaba | alibaba |
| Kind | Embeddings | Embeddings |
| Input per 1M tokens | $0.021 | $0.0105 Lower |
| Cached input per 1M tokens | Not applicable | Not applicable |
| Output per 1M tokens | Not applicable | Not applicable |
| Context window | 32,768 tokens | 32,768 tokens |
| Max output | Not applicable | Not applicable |
| Capabilities | None listed | None listed |
| Takes | Text | Text |
| Returns | Text | Text |
| Zero data retention | Yes, on every provider | Yes, on every provider |
| No training on requests | Yes, on every provider | Yes, on every provider |
| Released | 2025-06-05 | 2025-11-14 |
Example costs
Example requests, priced at today’s rates with no cached input.
| Example request | Qwen3 Embedding 4B | Qwen3 Embedding 0.6B |
|---|---|---|
| 1,000 tokens | $0.000021 | $0.000011 |
| 100,000 tokens | Too long for this model | Too long for this model |