blaschkeTry the console

Compare modified models
with their context intact.

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.

Integration testedPlanned
Models and preview pricing. Proposed USD rates per million tokens, not live customer charges.
ModelDetailsInput / 1MOutput / 1MAvailability
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 / previewIntegration 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 / previewIntegration 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 / previewPlanned
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 / previewPlanned
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 / previewPlanned
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 / previewPlanned
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 / previewPlanned

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 estimate

Understand each model before you choose it.

The source card describes what a model offers; the integration status describes what has actually been verified through Blaschke. These are deliberately kept separate.
01

MiniCPM · 1B Uncensored

A small text model used to verify the actual streaming and token-usage path on bounded CPU infrastructure.

TextStreaming
View Hugging Face model & license information
Integration tested
Public alias
minicpm-1b-uncensored
Source format
GGUF · Q4_K_M
Reported source scale
1B
Input / 1M
$0.10 USD
Output / 1M
$0.30 USD

Text generation and token usage have been tested through the configured worker; tool calls have not.

02

Qwen3 · 8B Abliterated v2

Qwen3-8B Abliterated v2, with a 16K-context serving configuration on one L4 GPU.

TextReasoning
View Hugging Face model & license information
Integration tested
Public alias
qwen3-8b-abliterated
Source format
SafeTensors · BF16
Reported source scale
8B
Input / 1M
$0.18 USD
Output / 1M
$0.18 USD

Text generation and token usage have been tested through the configured worker; tool calls have not.

03

Qwen3 · 32B Abliterated

A larger abliterated model for longer generations and more involving text tasks.

TextReasoning
View Hugging Face model & license information
Planned
Public alias
qwen3-32b-abliterated
Source format
SafeTensors · BF16
Reported source scale
32B
Input / 1M
$0.75 USD
Output / 1M
$0.75 USD

This catalogue candidate is not exposed by the inference route. Its source features and weights still require deployment validation.

04

GLM 5.3 Flash · Uncensored

A large but more efficient general-purpose variant, with reasoning and a vision tower reported by the source card.

TextSource visionReasoning
View Hugging Face model & license information
Planned
Public alias
glm-5.3-flash-uncensored
Source format
SafeTensors · FP8
Reported source scale
320B reported
Input / 1M
$1.00 USD
Output / 1M
$3.00 USD

This catalogue candidate is not exposed by the inference route. Its source features and weights still require deployment validation.

05

GLM 5.3 · Uncensored

The full-size general-purpose GLM release for demanding text and reasoning workloads.

TextReasoning
View Hugging Face model & license information
Planned
Public alias
glm-5.3-uncensored
Source format
SafeTensors · FP8
Reported source scale
753B reported
Input / 1M
$2.00 USD
Output / 1M
$8.00 USD

This catalogue candidate is not exposed by the inference route. Its source features and weights still require deployment validation.

06

DeepSeek V4.1 Flash 1017 · Uncensored

A long-context multimodal research model with reasoning tiers and native tool support reported upstream.

Source visionReasoningSource tools
View Hugging Face model & license information
Planned
Public alias
deepseek-v4.1-flash-1017-uncensored
Source format
SafeTensors · FP8 + FP4
Reported source scale
763B reported
Input / 1M
$1.20 USD
Output / 1M
$4.00 USD

This catalogue candidate is not exposed by the inference route. Its source features and weights still require deployment validation.

07

Kimi K3.1 Pro · Uncensored

An extended-reasoning release with reported native tools and 128K+ source context. Upstream access approval is required.

ReasoningSource imageSource tools
View Hugging Face model & license information
Planned
Public alias
kimi-k3.1-pro-uncensored
Source format
SafeTensors · MXFP4
Reported source scale
128K+ source context
Input / 1M
$5.00 USD
Output / 1M
$24.00 USD

This catalogue candidate is not exposed by the inference route. Its source features and weights still require deployment validation.

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.

The modification is not a guarantee of behaviour.

Abliterated models

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 models

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.

Integration-tested serving

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.

Check API support