Ernie Embedding v1 API

CN Baidu ERNIE | released 2023-05

Ernie Embedding v1 is Baidu Chinese-first embedding model, producing 384-dimensional vectors optimized for Simplified Chinese text. It is the cost-effective default for Chinese semantic search and recommendation use cases where short queries dominate.

Embedding

Pricing (official list, per 1M tokens)

Input

$0.04/M

Output

$0.00/M

Specifications

Context window4.096K tokens Input modalitiesText StreamingYes APIOpenAI-compatible

How to use Ernie Embedding v1

Drop-in OpenAI replacement. Change only the base_url and model.

# Python -pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://meshtok.com/v1",
    api_key="sk-your-MeshTok-key",
)

resp = client.chat.completions.create(
    model="baidu/embedding-v1",
    messages=[{"role":"user","content":"Hello!"}],
)
print(resp.choices[0].message.content)

# cURL
curl https://meshtok.com/v1/chat/completions \
  -H "Authorization: Bearer sk-your-MeshTok-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"baidu/embedding-v1","messages":[{"role":"user","content":"Hello!"}]}'