GLM: Embedding 3

z-ai/embedding-3

Embedding-3 is the third-generation text embedding model launched by Zhipu AI. Representing a comprehensive upgrade over its predecessors, it offers enhanced semantic understanding capabilities and greater flexibility in selecting vector dimensions. The model supports custom vector dimensions, thereby providing an optimal balance between performance and cost for diverse application scenarios while maintaining high-quality semantic representations.

Model specifications

Input
text
Output
text
Context
8,000 tokens
Max output
8,000 tokens
Input price
$0.08 / 1M tokens
Output price
$0 / 1M tokens
Released
2026-04-01

Capabilities

  • Streaming
  • Function calling
  • Vision
  • JSON mode
  • Playground

Provider pricing, discounts and data privacy

Compare effective provider prices, published discounts, regions, retention policies, training use, compliance, and privacy links by service tier.

Standard service tier

1 available provider · tier input average $0.08 / 1M tokens

BigModel

Tier: Standard · Region: CN

Pricing
Input
$0.08 / 1M tokens

No provider discount is currently published.

Data privacy and compliance
Region
CN
Zero data retention
No
Data retention
Unknown retention
Used for training
Unknown
Data collection
Moderated
No
GDPR compliant
No
HIPAA compliant
No
SOC 2 certified
No
BYOK supported
No

Frequently asked questions

What is GLM: Embedding 3?
Embedding-3 is the third-generation text embedding model launched by Zhipu AI. Representing a comprehensive upgrade over its predecessors, it offers enhanced semantic understanding capabilities and greater flexibility in selecting vector dimensions. The model supports custom vector dimensions, thereby providing an optimal balance between performance and cost for diverse application scenarios while maintaining high-quality semantic representations.
How much does GLM: Embedding 3 cost?
Input costs start at $0.08 / 1M tokens and output costs start at $0 / 1M tokens. Provider-level prices vary by service tier.
What is the context length of GLM: Embedding 3?
GLM: Embedding 3 supports a 8,000 token context window and up to 8,000 output tokens.
What capabilities does GLM: Embedding 3 support?
GLM: Embedding 3 supports Streaming, Function calling, Vision, JSON mode, Playground.
Which providers offer GLM: Embedding 3?
GLM: Embedding 3 is available from BigModel.
How do providers handle data privacy for GLM: Embedding 3?
1 of 1 providers report that customer data is not used for training, and 0 offer zero-data-retention routing. Retention, compliance, and privacy-policy links are listed per provider.

Browse all AI models