Zen Embedding
Dense text embeddings for semantic search, retrieval, and clustering.
- Context Window
- 33K
- In
- $0.010per million tokens
- Out
- $0.010per million tokens
Hanzo · starter
zen-embeddingSpecifications
In$0.010
Out$0.010
8K context · Embeddings
- Context Window
- 33K
- Modalities
- embeddings
- Price
- $0.010 in · $0.010 out, per million tokens
- Model ID
- zen-embedding
Quick start
zen-embedding
$0.010 in · $0.010 out, per million tokens
import OpenAI from 'openai'
const client = new OpenAI({
apiKey: process.env.HANZO_API_KEY,
baseURL: 'https://api.hanzo.ai/v1'
})
const response = await client.chat.completions.create({
model: 'zen-embedding',
messages: [{ role: 'user', content: 'Hello!' }]
})
console.log(response.choices[0].message.content)
from openai import OpenAI
client = OpenAI(
api_key=os.environ["HANZO_API_KEY"],
base_url="https://api.hanzo.ai/v1"
)
response = client.chat.completions.create(
model="zen-embedding",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
curl https://api.hanzo.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $HANZO_API_KEY" \
-d '{
"model": "zen-embedding",
"messages": [{"role": "user", "content": "Hello!"}]
}'
package main
import (
"context"
"fmt"
"os"
"github.com/sashabaranov/go-openai"
)
func main() {
cfg := openai.DefaultConfig(os.Getenv("HANZO_API_KEY"))
cfg.BaseURL = "https://api.hanzo.ai/v1"
client := openai.NewClientWithConfig(cfg)
resp, _ := client.CreateChatCompletion(context.Background(),
openai.ChatCompletionRequest{
Model: "zen-embedding",
Messages: []openai.ChatCompletionMessage{
{Role: openai.ChatMessageRoleUser, Content: "Hello!"},
},
},
)
fmt.Println(resp.Choices[0].Message.Content)
}
More from Hanzo
View all Hanzo models →$0.12Bill a month
1M is free at this volume.
Zen Embedding$0.1233K
1M$01M
- zen-embedding-3
- zen-free
- Zen Guard — Content Safety Safety classifier for moderation and guardrails across a broad category and language set.
- zen-scribe Hanzo's speech-to-text model, which writes down what is said in any language, served at /v1/audio/transcriptions.
- Zen VL — Vision-Language Reads images and reasons over them — visual Q&A, document and chart understanding, grounded captioning.
- zen-voice-mini Hanzo's text-to-speech voice, served at /v1/audio/speech. It speaks Arabic as well as English.
Use Zen Embedding via Hanzo AI
One API key. Every major model. OpenAI-compatible. Start free.
