Try Bifrost Enterprise free for 14 days.
Request access[ MODEL COMPARISON ]
Compare text-embedding-004 with other models
Select another model to compare pricing, limits, and capabilities with text-embedding-004.
VS
Models
text-embedding-004vertex_ai
—
—
Context Length
2K
—
Input Cost
$0.10/M
—
Mode
Embedding
—
Max Input Tokens
2K
—
Max Tokens
2K
—
Provider
Google Vertex AI
—
Deprecation Date
2026-01-14
—
Scale with the Fastest LLM Gateway
Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.
Comparison Insights
Comprehensive analysis based on the latest model metadata from the comparison table above.
What should I know about text-embedding-004?
Overview
- text-embedding-004 is a embedding model provided by Google Vertex AI.
- This model has a context capacity of 2K tokens.
Pricing
- Input processing costs $0.10 per million tokens.
- Output generation costs $0.00 per million tokens.
Availability
- Please note: This model is scheduled for deprecation on 2026-01-14.