MiniCPM · 1B Uncensored
A small text model used to verify the actual streaming and token-usage path on bounded CPU infrastructure.
Review compact abliterated models alongside larger uncensored releases. Each entry brings together its source, proposed rate and current serving status, so you can distinguish an interesting model from one you can call today.
| Model | Details | Input / 1M | Output / 1M | Availability |
|---|---|---|---|---|
| MiniCPM · 1B Uncensored hf/dealignai/MiniCPM-V-4.7-1B-CRACK-GGUF minicpm-1b-uncensored A small text model used to verify the actual streaming and token-usage path on bounded CPU infrastructure. | GGUF · Q4_K_M1BUncensored | $0.10USD / preview | $0.30USD / preview | Integration tested |
| Qwen3 · 8B Abliterated v2 hf/huihui-ai/Huihui-Qwen3-8B-abliterated-v2 qwen3-8b-abliterated Qwen3-8B Abliterated v2, with a 16K-context serving configuration on one L4 GPU. | SafeTensors · BF168BAbliterated | $0.18USD / preview | $0.18USD / preview | Integration tested |
| Qwen3 · 32B Abliterated hf/huihui-ai/Qwen3-32B-abliterated qwen3-32b-abliterated A larger abliterated model for longer generations and more involving text tasks. | SafeTensors · BF1632BAbliterated | $0.75USD / preview | $0.75USD / preview | Planned |
| GLM 5.3 Flash · Uncensored hf/dealignai/GLM-5.3-Flash-UNCENSORED-FP8 glm-5.3-flash-uncensored A large but more efficient general-purpose variant, with reasoning and a vision tower reported by the source card. | SafeTensors · FP8320B reportedUncensored | $1.00USD / preview | $3.00USD / preview | Planned |
| GLM 5.3 · Uncensored hf/dealignai/GLM-5.3-UNCENSORED-FP8 glm-5.3-uncensored The full-size general-purpose GLM release for demanding text and reasoning workloads. | SafeTensors · FP8753B reportedUncensored | $2.00USD / preview | $8.00USD / preview | Planned |
| DeepSeek V4.1 Flash 1017 · Uncensored hf/dealignai/DeepSeek-V4.1-Flash-1017-UNCENSORED-FP8 deepseek-v4.1-flash-1017-uncensored A long-context multimodal research model with reasoning tiers and native tool support reported upstream. | SafeTensors · FP8 + FP4763B reportedUncensored | $1.20USD / preview | $4.00USD / preview | Planned |
| Kimi K3.1 Pro · Uncensored hf/lyber-ai/Kimi-K3.1-Pro-UNCENSORED-MXFP4 kimi-k3.1-pro-uncensored An extended-reasoning release with reported native tools and 128K+ source context. Upstream access approval is required. | SafeTensors · MXFP4128K+ source contextUncensored | $5.00USD / preview | $24.00USD / preview | Planned |
Only “Integration tested” entries are exposed through the configured inference route. Planned entries may show source-reported capabilities; they are not Blaschke serving guarantees or enabled API model IDs.
Rates shown are proposed USD per million tokens.
Calculate a request estimateA small text model used to verify the actual streaming and token-usage path on bounded CPU infrastructure.
Qwen3-8B Abliterated v2, with a 16K-context serving configuration on one L4 GPU.
A larger abliterated model for longer generations and more involving text tasks.
A large but more efficient general-purpose variant, with reasoning and a vision tower reported by the source card.
The full-size general-purpose GLM release for demanding text and reasoning workloads.
A long-context multimodal research model with reasoning tiers and native tool support reported upstream.
An extended-reasoning release with reported native tools and 128K+ source context. Upstream access approval is required.
Kimi K3.1 Pro access: the Lyber AI × DealignAI model requires upstream access approval and custom-generation configuration. A catalogue entry does not bypass either requirement.
Abliteration changes the weights to reduce a targeted refusal-oriented representation. The precise method and its effects are determined by the author of each source model.
Uncensored is a broader label that can encompass fine-tuning, activation engineering and other techniques. The linked source remains the best guide to what was changed and how it was evaluated.
This status means we have verified a real worker, an API request, a text stream and its token usage. It does not imply benchmark coverage, consistent refusal behaviour or production readiness.