all-MiniLM-L6-v2
Embeddingsentence-transformerspytorchtfrustonnxsafetensorsopenvinobertfeature-extractionsentence-similaritytransformersendataset:s2orcdataset:flax-sentence-embeddings/stackexchange_xmldataset:ms_marcodataset:gooaqdataset:yahoo_answers_topicsdataset:code_search_netdataset:search_qadataset:eli5dataset:snlidataset:multi_nlidataset:wikihowdataset:natural_questionsdataset:trivia_qadataset:embedding-data/sentence-compressiondataset:embedding-data/flickr30k-captionsdataset:embedding-data/altlexdataset:embedding-data/simple-wikidataset:embedding-data/QQPdataset:embedding-data/SPECTERdataset:embedding-data/PAQ_pairsdataset:embedding-data/WikiAnswersarxiv:1904.06472arxiv:2102.07033arxiv:2104.08727arxiv:1704.05179arxiv:1810.09305base_model:nreimers/MiniLM-L6-H384-uncasedbase_model:quantized:nreimers/MiniLM-L6-H384-uncasedlicense:apache-2.0eval-resultstext-embeddings-inferenceendpoints_compatibledeploy:sagemakerdeploy:azureregion:us
Context
512 tokens
Max Output
256 tokens
Released
3/2/2022
Providers
1
Overview
all-MiniLM-L6-v2 is a large language model developed by UKP Lab. It supports 512 tokens context and is available through 1 API provider(s).
Key Highlights
- Embedding
Brand
UKP Lab
Organization
Country: Germany
View all models, pricing and details from UKP Lab.
Specifications
Basic Information
| Model | all-MiniLM-L6-v2 |
| Brand | UKP Lab |
| Version | 6 |
| Model Type | sentence-transformers |
| Status | stable |
| Released | 3/2/2022 |
| Popularity | 252279890 |
Architecture
| Parameter Size | 22.7M |
| Architecture Type | bert |
| Attention Mechanism | Unknown / Not disclosed |
| Tokenizer | Unknown / Not disclosed |
| Vocabulary Size | Unknown / Not disclosed |
Context & I/O
| Context | 512 tokens |
| Max Output | 256 tokens |
| Modalities | Embedding |
| Languages | en |
Capabilities
| Vision | No |
| Audio | No |
| Reasoning | No |
| Function Call | No |
| MCP | No |
| JSON Mode | No |
| Embedding | Yes |
Training Data
| Training Dataset | Unknown / Not disclosed |
| Estimated Data Size | Unknown / Not disclosed |
| Knowledge Cutoff | Unknown / Not disclosed |
Inference & Deployment
| API Access | Yes |
| VRAM Estimate | Unknown / Not disclosed |
| Quantization Support | Unknown / Not disclosed |
| Hardware Requirements | Unknown / Not disclosed |
Safety & Compliance
| Safety Evaluations | Unknown / Not disclosed |
| Content Policy | Unknown / Not disclosed |
| Region Restrictions | Unknown / Not disclosed |
License & Pricing
| License | apache-2.0 |
| Commercial Use | Unknown / Not disclosed |
| Open Source | Yes |
Provider & Pricing
| Provider | Input | Output | Cache | Batch | Website |
|---|---|---|---|---|---|
| sentence-transformers | $0.000/1M | $0.000/1M | - | - | Visit Website |
Price Changes
No recorded price changes.
Benchmarks
No benchmark data available.
Changelog
- Page created / data imported9/23/2026
- Last updated9/23/2026
Frequently Asked Questions
What is all-MiniLM-L6-v2?
all-MiniLM-L6-v2 is a large language model developed by UKP Lab.
Who developed all-MiniLM-L6-v2?
all-MiniLM-L6-v2 was developed by UKP Lab. You can learn more on the brand page or official website.
What is the context length of all-MiniLM-L6-v2?
all-MiniLM-L6-v2 supports up to 512 tokens of context.
How much does all-MiniLM-L6-v2 API cost?
API pricing for all-MiniLM-L6-v2 starts at $0.000/1M per 1M input tokens and $0.000/1M per 1M output tokens. See the pricing table above for provider-specific rates.