Sentence Transformers

All-MiniLM-L6-v2

Generally availableOpen weights256 context

Summary

All-MiniLM-L6-v2 is an open-weight language model from Sentence Transformers, released on 30 Aug 2021. It accepts text and generates text, with a 256-token context window and up to 384 output tokens per response.

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Last verified 18 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperSentence Transformers
Release date30 Aug 2021 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [models.dev]
Context window256 (256 tokens) [models.dev]
Max output384 tokens [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeNo [models.dev]
Tool callingNo [models.dev]

All-MiniLM-L6-v2 API pricing by provider

USD per million tokens. Sorted by input price.

We do not currently track a paid API listing for this model.

Frequently asked questions

What is the context window of All-MiniLM-L6-v2?

All-MiniLM-L6-v2 has a context window of 256 tokens (256) and can generate up to 384 tokens in a single response, according to models.dev.

Is All-MiniLM-L6-v2 open source?

All-MiniLM-L6-v2 is an open-weight model. Check the license terms before commercial use.

When was All-MiniLM-L6-v2 released?

Sentence Transformers released All-MiniLM-L6-v2 on 30 Aug 2021, according to models.dev.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
E5 Large v2IntfloatMay 2023512––Open
Whisper Large v3OpenAI6 Nov 2023448––Open
Whisper Large V3 TurboOpenAI1 Oct 2024448––Open
MythoMax L2 13BGryphe10 Aug 20234K$0.08$0.09Open
Llama Prompt Guard 2 22MpreviewMeta29 Apr 2025512$0.03$0.03Open
Prompt Guard 2 86MpreviewMeta29 Apr 2025512$0.04$0.04Open

Change history

  • Added to the directory

Sources