Inference API
UncensuredAI
Serves its own abliterated GLM 5.3, GLM 5.3 Flash and DeepSeek V4.1 Flash through an OpenAI-compatible API. Prepaid credits.
3
Models we route here
117
Median tok/s
6023
Median TTFT, ms
99.2%
Success rate, 7 days
Content policy
What UncensuredAI lets through.
Says prompts and completions are not retained (zero data retention). Does not publish which checkpoints it serves.
| Source | Cyber | Bio | Chem | Weap | Drug | Adult | Viol | Hate | Self | OSINT | Fraud | Polit | CSAM |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeclaredReported | n/t | n/t | n/t | n/t | n/t | n/t | n/t | n/t | n/t | n/t | n/t | n/t | Blocked |
OpenPartialBlockedNot tested
Pricing
GLM 5.3 Abliterated $0.39 in / $1.32 out, GLM 5.3 Flash Abliterated $0.22 / $0.80, DeepSeek V4.1 Flash Abliterated $0.27 / $0.95 per M tokens.
Sources
Catalogue
3 models we route to UncensuredAI.
| Model | Price here | TTFT | Throughput | Success | OpenUncensored Score |
|---|---|---|---|---|---|
| GLM 5.3 Flash Uncensoredglm-5.3-flash-uncensored | $0.22 / $0.80 | 6023 ms | 104 tok/s | 98.2% | 69.7 (#2) |
| DeepSeek V4.1 Flash Uncensoreddeepseek-v4.1-flash-uncensored | $0.27 / $0.95 | 8458 ms | 210 tok/s | 99.4% | 64.3 (#5) |
| GLM 5.3 Uncensoredglm-5.3-uncensored | $0.39 / $1.32 | 5874 ms | 117 tok/s | 99.3% | 63.0 (#9) |
Speed and success rate come from real API traffic over the last 7 days, once a route has 5 successful requests.