Qwen3 Embedding Models by Alibaba
2 models2025Up to 33k ctxFrom $0.07/1M input
Details
ResearcherAlibaba
LicenseApache 2.0OSI-approved
Commercial useCommercial use: permitted
Models2
Released2025
Max context33k
About
Qwen3 Embedding is Alibaba's multilingual text embedding model series from the Qwen3 generation, supporting 119 languages. Available in 0.6B, 4B, and 8B sizes. Open-sourced under Apache 2.0 and achieves SOTA on MTEB multilingual benchmarks.
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
2 in view
Qwen3 Embedding 0.6BCurrent
Use when the workload needs embedding, 33k context, and 600M parameters.
2025-06embedding33k context600M parameters
Qwen3 Embedding 8BCurrent
Use when the workload needs embedding, 33k context, and 8B parameters.
2025-06embedding33k context8B parameters
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Qwen3 Embedding 0.6B | Use when the workload needs embedding, 33k context, and 600M parameters. | 2025-06 | embedding33k context600M parameters | Current |
| Qwen3 Embedding 8B | Use when the workload needs embedding, 33k context, and 8B parameters. | 2025-06 | embedding33k context8B parameters | Current |
Release Timeline
1 release group2025-06
2 current
Qwen3 Embedding 0.6B
Currentembedding33k context600M parameters
Qwen3 Embedding 8B
Currentembedding33k context8B parameters
Specifications(2 models)
| Model | Released | Context | Parameters |
|---|---|---|---|
| Qwen3 Embedding 0.6B | 2025-06 | 33k | 0.6B |
| Qwen3 Embedding 8B | 2025-06 | 33k | 8B |
Available From(2 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Qwen3 Embedding 0.6B | Novita AI | $0.07 | — | Serverless |
| Qwen3 Embedding 8B | Novita AI | $0.07 | — | Serverless |
Frequently Asked Questions
- What is Qwen3 Embedding used for?
- Qwen3 Embedding is used for embedding. The family description and listed model capabilities point to those workloads as the best fit.
- How does Qwen3 Embedding compare to Tongyi DeepResearch?
- Qwen3 Embedding by Alibaba is strongest where you need embedding, while Tongyi DeepResearch by Alibaba is the closest related family to check for adjacent model selection. Qwen3 Embedding has 2 listed variants and reaches up to 33k context, while Tongyi DeepResearch reaches up to 131k context, so compare the specs and pricing tables before choosing a production model.
- Which Qwen3 Embedding model should I use?
- For the lowest listed input price, start with Qwen3 Embedding 0.6B through Novita AI at $0.07/1M input tokens. For the most capable/latest local choice, evaluate Qwen3 Embedding 0.6B with 33k context.
