GLM 5.3 Uncensored is an uncensored variant of Z.ai's GLM-5.3, with refusal behavior removed through abliteration and further fine-tuning. It takes text input and output with a 1M-token context window, always reasons at low, high or max depth, and is aimed at red teaming, security research and agent testing.
Modalities
In / out price
$3.00 / $5.00per 1M
Cached price
$0.30per 1M
Context
1M
Max output
131K
Providers
3 routesCompare providers by price, privacy, and speed.
abliteration.ai | Private | $3.00 | $5.00 | $0.30 | 1M | 131K | — | — |
| Anonymous | $3.00 | $5.00 | $0.30 | 1M | 33K | — | — | |
Surplus Intelligence | Anonymous | $2.10 | $3.50 | $0.21 | 1M | 33K | — | — |
Privacy
2 / 4Private routing
Private tier
- Anonymous
- Private
- TEE
- E2EE
Prompt and response content is not retained after the request. Request content is visible to the inference runtime while it is being processed. Learn more
Features
5Streaming
Tool calling
Reasoning
JSON/schema
Prompt caching
Uptime
FAQ
Common questions about GLM 5.3 Uncensored.