Stella EN 400M V5
NovaSearch/stella_en_400M_v5
published Jul 2024 · updated Jul 2025
Stella EN 400M V5 is an English text embedding model that uses Matryoshka Representation Learning to support multiple output dimensions from 512 to 8192.
specs
| Task | Text embedding (sentence-to-passage and sentence-to-sentence) |
| Architecture | Transformer (based on Alibaba-NLP/gte-large-en-v1.5) |
| Parameters | 400M |
| License | MIT |
about this model
The model is optimized for sentence‑to‑passage (s2p) and sentence‑to‑sentence (s2s) tasks via dedicated prompt templates. For retrieval use cases, the s2p prompt is recommended; for semantic textual similarity, the s2s prompt. Documents do not require any prompt.
Hosted as a managed API on gigarouter, the model can be called via a single HTTP endpoint without local installation or dependency management. The underlying architecture delivers strong performance in RAG pipelines and FAQ retrieval, with a sequence length of 512 tokens. For further details, refer to the Jasper and Stella technical report and the RAG‑Retrieval code repository.
best for
- ·Dense retrieval for RAG pipelines
- ·Semantic textual similarity
- ·FAQ matching and question answering
FAQ
It supports 512, 768, 1024, 2048, 4096, 6144, and 8192 dimensions via Matryoshka Representation Learning; 1024 is the default and recommended.
For sentence-to-passage (retrieval) use the s2p_query prompt; for sentence-to-sentence (similarity) use the s2s_query prompt. Documents need no prompt.
512 tokens is recommended; the model was trained on sequences of length 512.
Use the gigarouter OpenAI-compatible endpoint with your API key, specifying the model name and your input text.
MIT license.
We're benchmarking and onboarding Stella EN 400M V5 as a hosted, OpenAI-compatible API. Sign in for free credit and be ready when it lands, or tell us you want it and we'll prioritize it.