Identity
- Status
- active
- Developer ID
Qwen/Qwen3-Embedding-8B- Released
- Jun 3, 2025
- Version
- Qwen3 Embedding 8B
- License
- apache-2.0
QwenQwen3 Embedding 8B
Qwen3 Embedding 8B is Qwen's open-weight multilingual text-embedding model with a 32K-token context window and configurable output dimensions up to 4,096.
- Token context
- 33K tokens
- Inputs
- Text
- Outputs
- Embedding
- Released
- Jun 3, 2025
Providers & Pricing
Estimate workload cost →| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
 DeepinfraAvailable | $0.010 | — | — | — | Sep 22, 2026 | Provider-reported |
At a Glance
Model Facts
Capacity
- Token context
- 33K tokens
- Maximum output
- Unknown
- Total parameters
- 8B
- Active parameters
- Unknown
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text
- Outputs
- Embedding
- API available
- Yes
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- No
- Vision
- No
- Tool calling
- No
- Capabilities
- embeddings, multilingual, retrieval
This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
Aliasesqwen3-embedding-8b, Qwen3 Embedding 8B, Qwen/Qwen3-Embedding-8B
Explicit Unknowns
- Maximum output
- Knowledge cutoff
Primary Evidence
Sources and Observation Date
Qwen/Qwen3-Embedding-8B developer model repositoryQwen · observed Sep 3, 2026Qwen/Qwen3-Embedding-8B config.json at 1d8ad4ca9b3dQwen · observed Sep 3, 2026Qwen/Qwen3-Embedding-8B README.md at 1d8ad4ca9b3dQwen · observed Sep 3, 2026Qwen/Qwen3-Embedding-8B immutable Hub API metadataQwen · observed Sep 3, 2026Qwen/Qwen3-Embedding-8B tokenizer_config.json at 1d8ad4ca9b3dQwen · observed Sep 3, 2026Deepinfra catalogDeepinfra · observed Sep 22, 2026Fireworks Ai catalogFireworks Ai · observed Sep 22, 2026
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
| vs |  GPT-6 AstraOpenAI | cross-developer peers | |
| vs | Claude Fable 5.1Anthropic | cross-developer peers | |
| vs |  Gemini 3.1 ProGoogle DeepMind | cross-developer peers | |
| vs |  DeepSeek V4.1 FlashDeepSeek | cross-developer peers | |
| vs | Grok 4.6xAI | cross-developer peers | |
| vs | Qwen3.8 MaxQwen | family variants | |
| vs |  Kimi K3Moonshot AI | cross-developer peersembedding | |
| vs |  MiniMax M3MiniMax | cross-developer peers | |
| vs |  GLM 5.3Z.ai | cross-developer peers | |
| vs |  Hy4 previewTencent | cross-developer peers | |
| vs | Seed 2.1 ProByteDance Seed | cross-developer peers | |
| vs |  Mistral Large 3Mistral AI | cross-developer peers | |
| vs | cross-developer peers | ||
| vs |  Nova 2 LiteAmazon | cross-developer peers | |
| vs | cross-developer peers | ||
| vs |  ERNIE 5.1Baidu | cross-developer peers | |
| vs | cross-developer peers | ||
| vs | cross-developer peers | ||
| vs |  Phi-4 ReasoningMicrosoft | cross-developer peers | |
| vs | cross-developer peers | ||
| vs |  Sonar ProPerplexity | cross-developer peers | |
| vs | Claude Mythos 5.1Anthropic | cross-developer peers |
Questions
Qwen3 Embedding 8B FAQs
What is Qwen3 Embedding 8B?+
Qwen3 Embedding 8B is Qwen's open-weight multilingual text-embedding model with a 32K-token context window and configurable output dimensions up to 4,096. It is developed by Qwen and its current sourced lifecycle status is active.
What inputs and outputs does Qwen3 Embedding 8B support?+
Qwen3 Embedding 8B's current record lists Text as input and Embedding as output.
How much context does Qwen3 Embedding 8B support?+
The current record lists a 33K-token context window and does not report a maximum output length.
Is Qwen3 Embedding 8B available through an API?+
Qwen3 Embedding 8B is marked as API-available. The directly sourced provider records currently include Deepinfra and Fireworks Ai.
How large is Qwen3 Embedding 8B?+
The current record lists 8B total parameters and an unknown active parameter count. Its architecture is Qwen3ForCausalLM.
What capabilities and tasks does Qwen3 Embedding 8B support?+
Qwen3 Embedding 8B's recorded capabilities are embeddings, multilingual, and retrieval. Its supported tasks are code-retrieval, embedding, retrieval, and text.
How much does Qwen3 Embedding 8B cost through an API?+
The lowest directly sourced prices currently attached to Qwen3 Embedding 8B are $0.010 per million input tokens through Deepinfra and an unknown output-token price. Prices are provider-specific and should be checked against each cited observation date.
Can Qwen3 Embedding 8B be self-hosted?+
Qwen3 Embedding 8B is an open-weight model. Self-hosting is supported, and the recorded license is apache-2.0.
Does Qwen3 Embedding 8B have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are qwen3-embedding-8b, Qwen3 Embedding 8B, and Qwen/Qwen3-Embedding-8B.
Which models can Qwen3 Embedding 8B be compared with?+
The current compatible peer set includes GPT-6 Astra, Claude Fable 5.1, Gemini 3.1 Pro, DeepSeek V4.1 Flash, and Grok 4.6. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →