Kinfra Text Embedding 4B API

Tencent Kinfra Text Embedding 4B produces high-quality 2560-dimension text vectors for retrieval-augmented generation, semantic search and clustering — at provider list price, zero platform fee.

$0.0923

Input / 1M tokens

2560

Dimensions

Output (embeddings)

Platform fee

Why use Kinfra Text Embedding 4B on NovAI?

2560-dim vectors - large model for high-fidelity semantic embeddings
RAG & search ready - strong retrieval quality out of the box
Batch input - pass a string or a list of strings
Ultra-low cost - under $0.10 per 1M tokens
Zero platform fee - raw provider list price, no markup
OpenAI-compatible - drop-in via /v1/embeddings

Best use cases

Retrieval-augmented generation (RAG)
Semantic search and re-ranking
Document clustering and dedup
Recommendation features
Similarity and classification pipelines

Quick start

cURL

curl https://aiapi-pro.com/v1/embeddings \
  -H "Authorization: Bearer $NOVAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kinfra-text-embedding-4b",
    "input": "hello world"
  }'

Python (OpenAI SDK)

from openai import OpenAI
client = OpenAI(
    base_url="https://aiapi-pro.com/v1",
    api_key="YOUR_NOVAI_API_KEY",
)
resp = client.embeddings.create(
    model="kinfra-text-embedding-4b",
    input="hello world",
)
print(len(resp.data[0].embedding), "dimensions")

Try Kinfra Text Embedding 4B today

Zero platform fee. Credits never expire. OpenAI-compatible API.