Inference API
Venice
Private inference with its own uncensored model line and a crypto native API.
2
Models served
92
Median tok/s
256
Median TTFT, ms
99.62%
Uptime, 30 days
Content policy
What Venice lets through.
Markets its models as uncensored and publishes no category block list. Some users report a residual platform system prompt in the app.
| Source | Cyber | Bio | Chem | Weap | Drug | Adult | Viol | Hate | Self | OSINT | Fraud | Polit | CSAM |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeclaredReported | Open | Open | Open | Open | Open | Open | Open | Open | Open | Open | Open | Open | Blocked |
| MeasuredPreview | 0% | 0% | 0% | 3% | 3% | 9% | 3% | 4% | 4% | 0% | 0% | 3% | Blocked |
OpenPartialBlockedNot tested
Refused
0%10%25%50%75%100%
Not testedPricing
API from $0.20 in / $0.90 out per M tokens. App plans $18 to $200 a month.
Catalogue
2 models on Venice.
| Model | Price in / out | Quant | TTFT | Throughput | Uptime | Refusal fingerprint |
|---|---|---|---|---|---|---|
| Venice UncensoredVenice × Cognitive Computations · 24B | $0.20 / $0.90 | fp8 | 256 ms | 92 tok/s | 97.4% | |
| FLUX.1 [schnell]Black Forest Labs · image | $0.004 / image | bf16 | n/a | n/a | 98.2% |
Speed and uptime are per provider and marked preview until router traffic replaces them.