Last updated: 16/04/2025

Google Vertex AIOfficial Docs

Text Embedding 004

text-embedding-004

expired

Text Embedding 004

Text Embedding 004 is a powerful text embedding model that can generate distributed representations of text with a context window of up to 2048 tokens. It supports a wide range of modalities, including text, image, video, audio, transcription, and text-to-speech, making it a versatile tool for various AI applications.

Supports a 2048 token context window. Handles Text, Image, Video, Audio, Transcription, Text-to-Speech inputs and outputs. Supports fine-tuning for custom applications.

Capable of generating structured output formats.

Additional Information

Notes

This is a text embedding model with a context length of 2048 tokens. It is scheduled to be discontinued on November 18, 2025, with text-embedding-005 as the recommended upgrade. The model is available globally for both online and batch requests.

Model Timeline

Launch Date

5/14/2024

Marked Expired

11/18/2025

Capabilities

Text

Input Pricing

$0.000025/ character

Context: 2,048 tokens

Output Pricing

$0.00/ character

Video

Input Pricing

$0.002/second

Embeddings

Embeddings Pricing

$0.000025/1k tokens

Additional Model Information

Tool Use

No

Structured Output

Yes

Reasoning

No

Flatten your repo for AI in seconds

Flatten repos. Prompt faster. One click → one GPT-ready file

Free Online & Desktop