Security research.
Malware analysis, reverse engineering and detection engineering.
Security research guideUncensored models.
We built this for ourselves. Our engineers use these models every day on client projects and internal development, for work like security audits and red-teaming where stock models stop mid-task. We have spare capacity, so a few teams can use it too.
The models.
Every text model is our abliterated version of the open model: the same weights, with only the direction that leads to refusals removed. In the API they carry the suffix -uncensored.
| Model | Best for | Input | Context | Max output | Tokens per sec | First token |
|---|---|---|---|---|---|---|
| Model page | Best forCoding agents, hard reasoning | InputText, image | Context1M | Max output64K | Tokens per sec108 | First token2.1 s |
| Model page | Best forLong reports, large code changes | InputText | Context1M | Max output128K | Tokens per sec92 | First token2.6 s |
| Model page | Best forBatch jobs, labeling | InputText, image | Context1M | Max output32K | Tokens per sec71 | First token2.0 s |
| Model page | Best forAgentic coding, research | InputText, image, video | Context1M | Max output922K | Tokens per sec29 | First token2.7 s |
| Model page | Best forChat, quick drafts | InputText, image | Context128K | Max output32K | Tokens per sec42 | First token1.0 s |
Reference-to-video. 1 to 9 reference images, clips of 4 to 15 seconds, up to 1344 × 768, and up to 3 LoRAs per run.
All five text models support tool calls and reasoning. Full specs are in the model catalog.
Each dot is one request. Rings mark the median. Select a model above or in the chart.
Measured 6 Nov 2026: 5 streamed requests per model on shared capacity, up to 400 tokens, same prompt, reasoning tokens included. Your numbers will vary, so test with your own prompts.
OpenAI and Anthropic formats both work, and so do Claude Code and Codex. Quickstart
curl https://xfield.cloud.brutal.ai/api/v1/chat/completions \
-H "Authorization: Bearer $XFIELD_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v4.1-flash-1017-uncensored",
"stream": true,
"messages": [{"role": "user", "content": "Hello."}]
}'Malware analysis, reverse engineering and detection engineering.
Security research guideAuthorized penetration tests and AI red-team evaluations.
Red teaming guideAgents that keep working through the security-adjacent parts of a job.
Claude Code setupOn the text API, prompts and replies pass through and are not stored or used for training. Each request leaves a usage record with model, token counts, timing and cost.
How we handle dataTell Lukas who you are and what you are building. You get an invitation by email.
Sign in and open Settings, then API keys. Each key is shown once.
Point your SDK or agent at XField, our API, and pick a model. It is OpenAI- and Anthropic-compatible, hosted in the EU, and does not store your prompts.
Use our spare capacity with an API key and pay for what you use. We maintain the models and help when something breaks.
Capacity reserved for your team, running your choice of models and your own guardrails, with the same operations and support.
Image and video models tuned to your style or products, and small custom models where a large one is too slow or too expensive.
Tell Lukas what you are building and where your current model refuses. You get access and pricing back by email.
Access is reviewed company by company. Uncensored models do not change what is legal: you remain responsible for how you use them and for their output, under our acceptable use policy.
Stock models learn an internal direction that pushes sensitive requests over a threshold, and the model refuses. Abliteration removes that direction. XField's abliterated models have the same weights as the open models, with only that direction removed. In the API they carry the suffix -uncensored.
Five text models: DeepSeek V4.1 Flash (deepseek-v4.1-flash-1017-uncensored), GLM 5.3 (glm-5.3-uncensored), GLM 5.3 Flash (glm-5.3-flash-uncensored), Kimi K3.1 Pro (kimi-k3.1-pro-uncensored) and Qwen 3.8 27B (qwen-3.8-27b-uncensored). There is also MiniMax H3 for video from reference images. All text models support tool calls and reasoning.
Email Lukas at lukas@brutal.ai and tell him who you are and what you are building. You then get an invitation by email. You create the key under Settings, API keys, and it is shown only once. Brutal AI reviews access company by company.
Brutal AI in Vienna. Brutal AI runs the compute for its own systems and offers spare capacity to developers. Its own engineers use these models every day on client projects and internal development.