skip to content
gigarouter gigarouter

Stella EN 1.5B V5

NovaSearch/stella_en_1.5B_v5

published Jul 2024 · updated Jul 2025

Stella EN 1.5B V5 is an embedding model that transforms text into numerical vectors for dense retrieval, supporting multiple output dimensions via Matryoshka Representation Learning.

price
$0.008
/ 1M tokens
API providers
0
downloads / mo
30.1K
license
mit

specs

TaskEmbedding (dense retrieval, semantic similarity)
ArchitectureBased on Alibaba-NLP/gte-Qwen2-1.5B-instruct
Parameters1.5B
LicenseMIT

best for

FAQ

What output dimensions does this model support?

It supports 512, 768, 1024, 2048, 4096, 6144, and 8192 dimensions. 1024 is the default and recommended for most use cases.

What prompts should I use for retrieval vs. similarity tasks?

Use the "s2p_query" prompt for sentence-to-passage retrieval tasks and the "s2s_query" prompt for sentence-to-sentence semantic similarity tasks.

What is the recommended sequence length for this model?

The model is trained on sequences of 512 tokens; longer sequences may degrade performance.

How can I call this model via the gigarouter API?

Use the gigarouter OpenAI-compatible endpoint with your API key, specifying the model name "NovaSearch/stella_en_1.5B_v5".

What license is this model released under?

It is released under the MIT license.

call it
# OpenAI client - just change base_url
from openai import OpenAI
client = OpenAI(base_url="https://gigarouter.ai/v1", api_key=KEY)
v = client.embeddings.create(model="NovaSearch/stella_en_1.5B_v5", input=["hello world"])
print(v.data[0].embedding[:4])

try it live

runs the real hosted model on a shared demo allowance · get your own key + $25 free →

related embeddings models

compare all →