Z.AI: GLM 5.3 Uncensored
z-ai/glm-5.3-uncensored
GLM 5.3 Abliterated is Arnict's modified-refusal-behavior derivative of GLM 5.3, served through the zai/glm-5.3-uncensored endpoint for general-purpose text inference. Arnict's model page describes a mixture-of-experts architecture with DeepSeek Sparse Attention, 78 transformer layers and approximately 753B total parameters. The live catalog declares text-only input and output, a 1,048,576-token context and a 131,072-token output limit. It does not identify a derivative checkpoint, serving quantization or supported generation parameters; the base release's FP8 format is therefore not asserted for this hosted endpoint.
Model specifications
- Input
- text
- Output
- text
- Context
- 1,048,576 tokens
- Max output
- 131,072 tokens
- Input price
- $6.25 / 1M tokens
- Output price
- $11.25 / 1M tokens
- Released
- 2026-10-02
Capabilities
- Streaming
- Function calling
- Vision
- JSON mode
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 $6.25 / 1M tokens · tier output average $11.25 / 1M tokens
Arnict
Tier: Standard · Region: US
Pricing
- Input
- $6.25 / 1M tokens
- Output
- $11.25 / 1M tokens
- Cache read
- $6.25 / 1M tokens
No provider discount is currently published.
Data privacy and compliance
- Region
- US
- Zero data retention
- No
- Used for training
- No
- Data collection
- Moderated
- No
- GDPR compliant
- No
- HIPAA compliant
- No
- SOC 2 certified
- No
- BYOK supported
- No
Priority service tier
1 available provider · tier input average $6 / 1M tokens · tier output average $10 / 1M tokens
HAI
Tier: Priority · Region: JP · Quantization: fp8
Pricing
- Input
- $6 / 1M tokens
- Output
- $10 / 1M tokens
- Cache read
- $0.6 / 1M tokens
No provider discount is currently published.
Data privacy and compliance
- Region
- JP
- Zero data retention
- Yes
- Used for training
- No
- Data collection
- Moderated
- No
- GDPR compliant
- No
- HIPAA compliant
- No
- SOC 2 certified
- No
- BYOK supported
- No
Frequently asked questions
- What is Z.AI: GLM 5.3 Uncensored?
- GLM 5.3 Abliterated is Arnict's modified-refusal-behavior derivative of GLM 5.3, served through the zai/glm-5.3-uncensored endpoint for general-purpose text inference. Arnict's model page describes a mixture-of-experts architecture with DeepSeek Sparse Attention, 78 transformer layers and approximately 753B total parameters. The live catalog declares text-only input and output, a 1,048,576-token context and a 131,072-token output limit. It does not identify a derivative checkpoint, serving quantization or supported generation parameters; the base release's FP8 format is therefore not asserted for this hosted endpoint.
- How much does Z.AI: GLM 5.3 Uncensored cost?
- Input costs start at $6.25 / 1M tokens and output costs start at $11.25 / 1M tokens. Provider-level prices vary by service tier.
- What is the context length of Z.AI: GLM 5.3 Uncensored?
- Z.AI: GLM 5.3 Uncensored supports a 1,048,576 token context window and up to 131,072 output tokens.
- What capabilities does Z.AI: GLM 5.3 Uncensored support?
- Z.AI: GLM 5.3 Uncensored supports Streaming, Function calling, Vision, JSON mode.
- Which providers offer Z.AI: GLM 5.3 Uncensored?
- Z.AI: GLM 5.3 Uncensored is available from Arnict, HAI.
- How do providers handle data privacy for Z.AI: GLM 5.3 Uncensored?
- 2 of 2 providers report that customer data is not used for training, and 1 offer zero-data-retention routing. Retention, compliance, and privacy-policy links are listed per provider.