MODEL PROFILE

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.

Embeddings & similaritylicense:cc-by-nc-4.0
Context windowNot disclosed
Input → OutputText → Embedding
Model weightsNot verified
Profile updated2026/10/29 21:57:40
OVERVIEW

Model overview

`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.

Key features

特点摘要待依据来源补齐,不凭模型名称推断能力。

Limitations & considerations

Sources are insufficient to establish specific limitations. Verify task performance, latency, data policies, licensing and version lifecycle.

PRICING & COST

Source prices & cost analysis

Prices vary by channel, region and configuration. Channel quotes are listed independently and are not treated as a single official provider price.

Source / channelInputOutputBilling unitCollected at
No verified prices yet. Check the source channel.

Estimate monthly base token costs

—

Estimates exclude cache discounts, tiered pricing, multimodal surcharges, web search, taxes and additional reasoning output.

INDEPENDENT BENCHMARKS

Public benchmarks & run configuration

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。

View full indexed rankings →

Frequently asked questions

Do open weights permit free commercial use?

Not necessarily. Check the version license, commercial conditions and usage policies. Self-hosting incurs compute and maintenance costs.

Are these real-time billing prices?

These are timestamped source snapshots, not live billing prices. Check the channel for current versions, regions, discounts and billing methods.

Sources & traceability

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。