text-embedding-v4

alibaba/text-embedding-v4

Qwen3-based text embedding model (June 2025) with 64-2,048 selectable dimensions and 8,192-token inputs, 15-40% better than v3 on Alibaba's evaluations. Still Alibaba's default text-embedding recommendation, though qwen3.7-text-embedding is newer.

Get API Key Read the Docs

curl "$AUDIOLAB_API_URL/v1/embeddings" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "alibaba/text-embedding-v4",
  "input": "Build search with AudioLab.",
  "encoding_format": "float"
}'

Input Price: $0.0595 / 1M tokens
Output Price: —
Context: 8.2K tokens
Output: Embedding

Capabilities

Explore what text-embedding-v4 supports, then use the API section for a request tailored to this model.

DimensionsBatch

Model Information

Provider: Alibaba Cloud Model Studio
Product: Embeddings
Release Date: Jun 5, 2025
Data Policy: Not specified
Region: Global
Input: Text
Output: Embedding

Provider Documentation

Playground

Try text-embedding-v4 by Alibaba Cloud Model Studio. Requests use the selected workspace’s credits and API pricing.

text-embedding-v4

This model uses a dedicated input format. Explore its API example or open the supported playground.

View API reference

Providers

Compare available endpoints, pricing, and context limits for text-embedding-v4.

Provider	Context	Output	Input Price	Output Price	Endpoint
Alibaba Cloud Model Studio	8.2K tokens	Embedding	$0.0595 / 1M tokens	—	`text-embedding-v4`

Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Limit	Value
Dimensions	2048
Max batch	10
Max total tokens	81920

Status

Current catalog availability. Your workspace’s access is checked separately before a request runs.

Checking availability…

A live availability check is not available right now.

Getting Started

Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.

curl "$AUDIOLAB_API_URL/v1/embeddings" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "alibaba/text-embedding-v4",
  "input": "Build search with AudioLab.",
  "encoding_format": "float"
}'

Read the Endpoint Reference

Request Parameters

Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.

Parameter	Details
`model`	`alibaba/text-embedding-v4` — Required model identifier.
`input`	View Accepted Values
`encoding_format`	View Accepted Values
`dimensions`	View Accepted Values
`input_type`	View Accepted Values

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Limit	Value
Dimensions	2048
Max batch	10
Max total tokens	81920

Similar Models

Explore more embeddings and compare their capabilities.

Model	Context	Input Price	Output Price
qwen3.7-text-embeddingAlibaba Cloud Model Studio	128K tokens	$0.0595 / 1M tokens	—
tongyi-embedding-vision-flashAlibaba Cloud Model Studio	1K tokens	$0.0765 / 1M tokens	—
tongyi-embedding-vision-plusAlibaba Cloud Model Studio	1K tokens	$0.0765 / 1M tokens	—
text-embedding-v3Alibaba Cloud Model Studio	8.2K tokens	$0.0595 / 1M tokens	—
nvidia/Nemotron-3-Embed-1B-BF16DeepInfra	32.8K tokens	$0.0128 / 1M tokens	—
nvidia/Nemotron-3-Embed-1B-NVFP4DeepInfra	32.8K tokens	$0.0085 / 1M tokens	—

View All Embeddings