🪷 Zen LM

Embeddings

Generate 1024-dimensional vector embeddings with zen-embedding

Embeddings

Generate dense vector embeddings for text using zen-embedding, the embedding model in the Zen family.

Endpoint

POST https://api.hanzo.ai/v1/embeddings

Request Body

ParameterTypeRequiredDescription
modelstringYesMust be zen-embedding
inputstring/arrayYesText to embed (string or array of strings)

Example

curl https://api.hanzo.ai/v1/embeddings \
  -H "Authorization: Bearer $HANZO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zen-embedding",
    "input": "Zen LM is a family of frontier AI models"
  }'

Python

from hanzoai import Hanzo

client = Hanzo(api_key="hk-your-key")

response = client.embeddings.create(
    model="zen-embedding",
    input=["Hello world", "Zen LM models"],
)

for embedding in response.data:
    print(f"Vector dim: {len(embedding.embedding)}")

TypeScript

import Hanzo from '@hanzo/ai'

const client = new Hanzo({ apiKey: 'hk-your-key' })

const response = await client.embeddings.create({
  model: 'zen-embedding',
  input: ['Hello world', 'Zen LM models'],
})

for (const item of response.data) {
  console.log(`Vector dim: ${item.embedding.length}`)
}

Response

{
  "object": "list",
  "data": [
    {
      "object": "embedding",
      "index": 0,
      "embedding": [0.0023, -0.0091, 0.0152, "..."]
    }
  ],
  "model": "zen-embedding",
  "usage": {
    "prompt_tokens": 8,
    "total_tokens": 8
  }
}

Specifications

PropertyValue
Modelzen-embedding
Dimensions1,024
Max Input8,191 tokens
Tierpro max
Pricing$0.39 / 1M tokens

Use Cases

  • Semantic search: Find similar documents by meaning
  • RAG: Retrieval-augmented generation pipelines
  • Clustering: Group similar texts together
  • Classification: Use embeddings as features for classifiers
  • Deduplication: Identify near-duplicate content at scale

Wire compatibility

The request and response bodies are the standard embeddings JSON shape, so an HTTP client already written against that shape works here once its base URL points at https://api.hanzo.ai/v1 and it sends a Hanzo key. Model ids do not carry across vendors — zen-embedding is a Hanzo model and resolves only here.

On this page