Inference API
Abliteration.ai
Hosted abliterated frontier models, led by Abliterated Large v2 on GLM-5.3.
1
Models served
57
Median tok/s
277
Median TTFT, ms
99.30%
Uptime, 30 days
Content policy
What Abliteration.ai lets through.
Reportedly blocks only CSAM and self harm. Offers a per project Policy Gateway for custom rules.
| Source | Cyber | Bio | Chem | Weap | Drug | Adult | Viol | Hate | Self | OSINT | Fraud | Polit | CSAM |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeclaredReported | Open | Open | Open | Open | Open | Open | Open | Open | Blocked | Open | Open | Open | Blocked |
| MeasuredPreview | 2% | 1% | 1% | 2% | 1% | 0% | 1% | 0% | Blocked | 0% | 1% | 21% | Blocked |
OpenPartialBlockedNot tested
Refused
0%10%25%50%75%100%
Not testedPricing
Around $3 in / $3 out per M tokens. Monthly tiers $20 to $200.
Sources
Catalogue
1 model on Abliteration.ai.
| Model | Price in / out | Quant | TTFT | Throughput | Uptime | Refusal fingerprint |
|---|---|---|---|---|---|---|
| Abliterated Large v2 (GLM-5.3)Abliteration.ai · 355B (32B active) | $3.00 / $3.00 | fp8 | 277 ms | 57 tok/s | 99.7% |
Speed and uptime are per provider and marked preview until router traffic replaces them.