Ctrlk
API KeyModelsPlaygroundGitHubGet Support
For the complete documentation index, see llms.txt. This page is also available as Markdown.

Qwen Text Embedding v4

This documentation is valid for the following list of our models:

  • alibaba/qwen-text-embedding-v4

Try in Playground

Model Overview

A compact language model supporting over 100 languages. It features a 4B parameter architecture, a context length of up to 32K tokens, and outputs embeddings with up to 2560 dimensions. Embeddings exhibit tighter intra-cluster cohesion and sharper inter-cluster separation compared to qwen-text-embedding-v3.

Setup your API Key

If you don’t have an API key for the AI/ML API yet, feel free to use our Quickstart guide.

API Schema

post
Authorizations
AuthorizationstringRequired

Bearer key

Body
modelundefined · enumRequiredPossible values:
inputany ofRequired

Input text to embed, encoded as a string or array of tokens.

string · min: 1Optional
or
string[] · min: 1Optional
dimensionsinteger · min: 64 · max: 2048Optional

The number of dimensions for the embedding. Default is 1024.

Default: 1024
Responses
200Success
application/json
objectstring · enumRequiredPossible values:
modelstringRequired
post/v1/embeddings
POST /v1/embeddings HTTP/1.1
Host: api.aimlapi.com
Authorization: Bearer YOUR_SECRET_TOKEN
Content-Type: application/json
Accept: */*
Content-Length: 75

{
  "model": "alibaba/qwen-text-embedding-v4",
  "input": "text",
  "dimensions": 1024
}
200Success
{
  "object": "object",
  "data": [
    {
      "object": "embedding",
      "index": 1,
      "embedding": [
        1
      ]
    }
  ],
  "model": "text",
  "usage": {
    "total_tokens": 1
  }
}

Code Example

This example shows how to set up an API client, send text to the embedding API, and print the response with the embedding vector. See how large a vector response the model generates from just a single short input phrase.

Response

You can find a more advanced example of using embedding vectors in our article Find Relevant Answers: Semantic Search with Text Embeddings in the Use Cases section.

PreviousQwen Text Embedding v3
NextAnthropic

Last updated

Was this helpful?