AI Rate CardText Embedding V4 · aihubmix
This is the Tongyi Laboratory's multilingual unified text vector model trained based on Qwen3, which significantly improves performance in text retrieval, clustering, and classification compared to version V3; it achieves a 15% to 40% improvement on evaluation tasks such as MTEB multilingual, Chinese-English, and code retrieval; supports user-defined vector dimensions ranging from 64 to 2048.
Input, $/1M $0.08
Output, $/1M $0.08
Price alerts
API
OpenAI-compatible API: the official OpenAI SDKs work with this base URL. Replace YOUR_API_KEY with your key from the provider.
| API base URL | |
|---|---|
| Endpoint | |
| Model id | |
curl
curl https://aihubmix.com/api/v1/embeddings \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "text-embedding-v4", "input": ["first text", "second text"]}'Python
import requests
r = requests.post(
"https://aihubmix.com/api/v1/embeddings",
headers={"Authorization": "Bearer YOUR_API_KEY"},
json={
"model": "text-embedding-v4",
"input": [
"first text",
"second text"
]
},
)
print(r.json())JavaScript
const r = await fetch("https://aihubmix.com/api/v1/embeddings", {
method: "POST",
headers: {Authorization: "Bearer YOUR_API_KEY", "Content-Type": "application/json"},
body: JSON.stringify({
"model": "text-embedding-v4",
"input": [
"first text",
"second text"
]
}),
});
console.log(await r.json());Request (JSON)
{
"model": "text-embedding-v4",
"input": [
"first text",
"second text"
]
}Response (JSON)
{
"object": "list",
"model": "text-embedding-v4",
"data": [
{
"object": "embedding",
"index": 0,
"embedding": [
0.0123,
-0.0456,
"..."
]
}
],
"usage": {
"prompt_tokens": 6,
"total_tokens": 6
}
}The address is taken from the provider's model list; check it against the provider's documentation.
Source: AI Rate Card, https://airatecard.com/en/c/offer%3Aaihubmix%7Ctext-embedding-v4, prices checked 2026-11-04; seller's page: https://aihubmix.com
Technical details
ID: offer:aihubmix|text-embedding-v4