MODEL PROFILE · 模型档案

jina-embeddings-v5-text-nano

jinaai · jina-embeddings-v5-text-nano

`jina-embeddings-v5-text-nano` is the fifth generation of Jina AI's multilingual embedding models, released on February 18, 2026. For higher performance at a larger size, see jina-embeddings-v5-text-small. `jina-embeddings-v5-text-nano` scores 71.0 average on MTEB English v2 and 65.5 on MMTEB with only 239M parameters, matching or exceeding all other sub-500M embedding models including KaLM-mini-v2.5 (494M) and Gemma-300M (308M). Built on EuroBERT-210M and trained by combining embedding distillation from Qwen3-Embedding-4B with task-specific contrastive losses, it supports multilingual text up to 32K tokens and produces embeddings robust under truncation and binary quantization. | Feature | Value | | --- | --- | | Parameters | 239M | | Supported Tasks | `retrieval`, `text-matching`, `clustering`, `classification` | | Max Sequence Length | 8192 | | Embedding Dimension | 768 | | Matryoshka Dimensions | 32, 64, 128, 256, 512, 768 | | Pooling Strategy | Last-token pooling | | Base Model | EuroBERT/EuroBERT-210m | For training details and evaluation results, see our technical report.

译文排队中,当前展示来源原文。

向量与相似度license:cc-by-nc-4.0
上下文窗口来源未披露
输入 → 输出文本 → 向量
模型权重待核验
档案更新时间2026/11/2 19:15:44
OVERVIEW

模型介绍

`jina-embeddings-v5-text-nano` is the fifth generation of Jina AI's multilingual embedding models, released on February 18, 2026. For higher performance at a larger size, see jina-embeddings-v5-text-small. `jina-embeddings-v5-text-nano` scores 71.0 average on MTEB English v2 and 65.5 on MMTEB with only 239M parameters, matching or exceeding all other sub-500M embedding models including KaLM-mini-v2.5 (494M) and Gemma-300M (308M). Built on EuroBERT-210M and trained by combining embedding distillation from Qwen3-Embedding-4B with task-specific contrastive losses, it supports multilingual text up to 32K tokens and produces embeddings robust under truncation and binary quantization. | Feature | Value | | --- | --- | | Parameters | 239M | | Supported Tasks | `retrieval`, `text-matching`, `clustering`, `classification` | | Max Sequence Length | 8192 | | Embedding Dimension | 768 | | Matryoshka Dimensions | 32, 64, 128, 256, 512, 768 | | Pooling Strategy | Last-token pooling | | Base Model | EuroBERT/EuroBERT-210m | For training details and evaluation results, see our technical report.

主要特点

特点摘要待依据来源补齐,不凭模型名称推断能力。

局限与注意事项

暂无足够来源支持具体缺点结论。请重点验证实际任务表现、时延、数据政策、许可与版本生命周期。

PRICING & COST

来源报价与费用分析

同一模型在不同渠道、地区和配置下可能采用不同价格。下表独立保留各渠道报价,不将渠道价格视为厂商官方统一价格。

来源 / 渠道输入输出计费单位采集时间
暂未取得可核验报价,请查阅来源渠道。

按月估算基础 Token 费用

—

预估不包含缓存优惠、阶梯定价、多模态附加费用、网络检索、税费及推理额外输出。

INDEPENDENT BENCHMARKS

公开评测与运行配置

暂无已采集的可核验公开评分。模型未上榜不代表能力较低。

查看完整已收录榜单 →

常见问题

开放权重是否代表可以免费商用?

不一定。应核对具体版本许可证、商用门槛和使用政策。自部署还会产生算力和维护成本。

这些价格是实时结算价格吗?

不是实时结算价格,而是带采集时间的来源报价快照。请到对应渠道核对当前版本、区域、折扣和计费方式。

资料来源与可追溯记录

许可证:cc-by-nc-4.0。模型介绍与第三方评测均以原来源的具体版本和方法为准。