Short answer: for abliterated models with an OpenAI- and Anthropic-compatible API, the main options are XField by Brutal AI, abliteration.ai and Venice. Featherless hosts many community abliterated models on an OpenAI-compatible API. OpenRouter and NanoGPT are routers: they pass your request to a model hosted by someone else. Together AI hosts mainstream open models but lists no uncensored ones. If you need EU hosting, XField is hosted in the EU and abliteration.ai offers EU residency as an option; the others do not state a region or are US-based.
We run XField, so read this with that in mind. We have kept the table to facts each provider publishes, linked every one, and written "not stated" where a provider does not say.
Three ways providers remove refusals
- Abliterated weights. The direction in the model that leads to refusals is removed from the weights. Knowledge and skills stay; false refusals go. See How abliteration works.
- Uncensored fine-tunes. A community model such as Dolphin or Hermes is trained further to refuse less. Quality depends on the fine-tune and usually trails the newest base models.
- Routing. A router forwards your request to another provider's model. It adds one key and one bill, but it cannot change what the weights do. See Routing doesn't remove refusals.
The comparison
| Provider | Approach | OpenAI API | Anthropic Messages / Claude Code | Prompt logging | Hosting region | Access |
|---|---|---|---|---|---|---|
| XField (Brutal AI) | Own abliterated versions of DeepSeek V4.1 Flash, GLM 5.3, Kimi K3.1 Pro, Qwen 3.8 27B | Yes: Chat Completions and Responses | Yes, native; Claude Code documented | Not stored, not used for training | EU | On request, reviewed per company |
| abliteration.ai | Own abliterated models; optional content policies per project | Yes: Chat Completions and Responses | Messages endpoint yes; Claude Code documented | Processed in memory, not written to disk; no training | US by default, EU optional | Self-serve, pay as you go or plans |
| Venice | Own uncensored and abliterated variants; also resells other providers' models, some in an anonymized mode | Yes | No native endpoint; Claude Code via a proxy | Not stored for Venice-hosted models; training not stated | Not stated | Self-serve: API key, or USDC pay per request |
| Featherless | Hosts community abliterated and uncensored models from Hugging Face | Yes | Not stated | Not logged; training not stated | Not stated | Monthly plans |
| OpenRouter | Router; its uncensored model is Venice Uncensored, served by Venice | Yes | Messages yes; Claude Code only guaranteed with Anthropic's own models | Only if you opt in; each upstream provider has its own policy | EU routing on Business and Enterprise plans | Self-serve credits |
| NanoGPT | Router; lists abliterated models modified to refuse less | Yes | Yes, names Claude Code | Not logged in normal inference; some routes allow training | Not stated; EU-only processing per request | Self-serve balance or subscription |
| Together AI | Mainstream open models; no uncensored models listed; terms restrict content | Yes | Messages endpoint yes | Not stored under zero data retention | US endpoint available | Self-serve pay per token |
Example list prices per 1M tokens (input / output), seen 17 Nov 2026: abliteration.ai Abliterated Large v2 $3.00 / $5.00; Venice Uncensored 1.2 $0.20 / $0.90; OpenRouter Venice: Uncensored $0.20 / $0.90. Prices change often, so check the provider's page. XField pricing comes with access.
Who serves Kimi K3.1 Pro uncensored?
Kimi K3.1 Pro is Moonshot AI's flagship open model. Most providers serve only the stock version, which still refuses. Checked on 17 November 2026:
| Provider | Kimi K3.1 Pro |
|---|---|
| XField (Brutal AI) | Abliterated, our own: kimi-k3.1-pro-uncensored, 1M context, up to 922K output, video input, hosted in the EU |
| NanoGPT | An abliterated version listed from a third-party host (Lyber), next to the stock model |
| Venice | Stock model only |
| OpenRouter | Stock model only, from several providers |
| Featherless | Stock model only |
| Together AI | Stock model only |
| abliteration.ai | No Kimi model listed |
Sources: NanoGPT models, Venice models, OpenRouter, Featherless models, Together serverless models, abliteration.ai pricing.
How to choose
- You run a coding agent such as Claude Code. Pick an API with a native Anthropic Messages endpoint and large models with working tool calls: XField, abliteration.ai, NanoGPT or Together (Together has no uncensored models). XField and abliteration.ai document Claude Code setups. Setup for XField: Use Claude Code with an uncensored model.
- You need EU hosting or data residency. XField is hosted in the EU. abliteration.ai offers EU residency as an option, OpenRouter on its Business and Enterprise plans.
- You want the newest large open models, abliterated. XField serves abliterated DeepSeek V4.1 Flash, GLM 5.3 and Kimi K3.1 Pro. Venice and abliteration.ai also serve abliterated versions of recent models.
- You want to try many small community models cheaply. Featherless has the widest catalog of community abliterated models.
- You want one key for everything. A router like OpenRouter or NanoGPT. Check which upstream host serves the uncensored model and its logging policy.
What to check before you send sensitive data
- Who hosts the weights. With a router, your prompt goes to another company. Its policy applies.
- Whether prompts are stored or used for training. Read the provider's data page, not the marketing page.
- Where the servers are. Most providers do not state a region.
- Whether the model actually answers. Run five prompts from your real work, the ones your current model refuses, before committing.
One-to-one comparisons
- abliteration.ai alternative: XField compared
- Venice API alternative: XField compared
- Featherless alternative: XField compared
Setup guides for your tools: Claude Code, Codex CLI, OpenCode, Cline, Roo Code, Continue, Aider.
About XField
XField is the model API of Brutal AI in Vienna. We built it for our own engineers, who use these models on client projects for security audits and red-teaming, and we open spare capacity to a few teams. It is hosted in the EU, speaks OpenAI Chat Completions, Responses and Anthropic Messages, and does not store prompts or completions (data handling). Access is reviewed company by company under our acceptable use policy. Request a key.
Sources (checked 17 Nov 2026)
- abliteration.ai: compatibility, Claude Code, data handling, pricing
- Venice: about, privacy, Claude Code, pricing
- Featherless: overview, privacy and logging, pricing
- OpenRouter: data collection, logging, Claude Code, Venice: Uncensored
- NanoGPT: API, privacy
- Together AI: serverless models, Messages API, terms