--- title: "Uncensored model directory and hosted API" description: "Explore uncensored and reduced-refusal model cards, community variants, Hugging Face sources, FAQs, and privately hosted API options from Vynaris." canonical: https://vynaris.com/uncensored-models updated: 2026-10-10 --- Model directory + hosted API # Find an uncensored model—and know where you can actually use it. Compare reduced-refusal model families, community variants, source repositories, practical tradeoffs, and hosted availability. Vynaris-hosted models are labelled separately from models listed for research and discovery. Pay by card or with Monero (XMR) for complete payment privacy. [Get an API key](https://app.vynaris.com/signin) [Browse model cards](https://vynaris.com/uncensored-models#model-directory) Built for lawful, authorized red teaming, cyber defense, and model evaluation. Child sexual exploitation, human trafficking or exploitation, and non-consensual sexual content are prohibited. Only test systems and data you own or are authorized to assess. Hosted now ## Four model profiles. One API and one wallet. These are the only directory entries currently exposed through public Vynaris model IDs. Select the exact ID in every OpenAI-compatible request. Premium rates for guaranteed anonymity and data security. vynaris/qwen3.6-35b-a3b-uncensored ### Qwen3.6-35B-A3B-uncensored The fast hosted option for high-volume authorized security testing, agents, and reduced-refusal research. Input / MTok **$1.00** Output / MTok **$5.00** Context **128K tokens** Status **Hosted** [API, variants and model card →](https://vynaris.com/uncensored-models/qwen3-6-35b-a3b-uncensored) vynaris/qwen3.8-27b-uncensored ### Qwen3.8-27B-uncensored The balanced dense-model option for detailed authorized red-team analysis, coding, and long-context reviews. Input / MTok **$1.00** Output / MTok **$7.00** Context **128K tokens** Status **Hosted** [API, variants and model card →](https://vynaris.com/uncensored-models/qwen3-8-27b-uncensored) vynaris/deepseek-v4-flash-uncensored ### DeepSeek-V4-Flash-uncensored A deep hosted tier for difficult multi-step security analysis and complex defensive engineering work. Input / MTok **$2.00** Output / MTok **$11.00** Context **128K tokens** Status **Hosted** [API, variants and model card →](https://vynaris.com/uncensored-models/deepseek-v4-flash-uncensored) vynaris/glm-5.3-uncensored ### GLM-5.3-uncensored The frontier-class hosted tier for the hardest authorized analysis, long-horizon reasoning, and complex engineering work. Input / MTok **$5.00** Output / MTok **$20.00** Context **128K tokens** Status **Hosted** [API, variants and model card →](https://vynaris.com/uncensored-models/glm-5-3-uncensored) Across every size class ## Explore uncensored model cards Each page explains the family, capabilities, limitations, community variants, source repositories, use paths, and common questions. We add families based on community adoption and deployment interest. [Model guide 9B class Qwen3.5 9B Uncensored A compact reduced-refusal Qwen family for local assistants, tool experiments, and fast evaluation on limited hardware. Architecture Dense transformer Variants linked 2 **Read model card →**](https://vynaris.com/uncensored-models/qwen3-5-9b-uncensored) [Model guide 8B class Qwen3-VL 8B Uncensored A compact vision-language family for reduced-refusal image analysis and multimodal security evaluation. Architecture Vision-language transformer Variants linked 2 **Read model card →**](https://vynaris.com/uncensored-models/qwen3-vl-8b-uncensored) [Model guide 20B class GPT-OSS 20B Uncensored A reduced-refusal adaptation of the compact GPT-OSS family for reasoning experiments and authorized security research. Architecture Sparse mixture-of-experts Variants linked 1 **Read model card →**](https://vynaris.com/uncensored-models/gpt-oss-20b-uncensored) [Model guide 18B–21B class Llama 3.2 MoE Uncensored Community mixture-of-experts builds combining Llama-derived experts for creative work, roleplay, and reduced-refusal evaluation. Architecture Community mixture-of-experts builds Variants linked 2 **Read model card →**](https://vynaris.com/uncensored-models/llama-3-2-moe-uncensored) [Model guide 26B class SuperGemma4 26B Uncensored A community Gemma 4 adaptation targeting stronger instruction compliance with fewer refusals in a mid-size MoE profile. Architecture Sparse mixture-of-experts Variants linked 2 **Read model card →**](https://vynaris.com/uncensored-models/supergemma4-26b-uncensored) [Model guide 27B class Qwen3.6 27B Uncensored A popular dense Qwen family adapted by community publishers for creative work and reduced-refusal evaluation. Architecture Dense hybrid-attention transformer Variants linked 2 **Read model card →**](https://vynaris.com/uncensored-models/qwen3-6-27b-uncensored) [Model guide 30B total / 3B active class Qwen3 30B-A3B Uncensored A compact-active-parameter Qwen MoE family that balances throughput, model breadth, and reduced-refusal experimentation. Architecture Sparse mixture-of-experts Variants linked 2 **Read model card →**](https://vynaris.com/uncensored-models/qwen3-30b-a3b-uncensored) [Model guide Large sparse expert model Gemma 4 E4B Uncensored A popular community Gemma 4 adaptation pairing a large expert pool with sparse active computation and reduced refusals. Architecture Sparse mixture-of-experts Variants linked 1 **Read model card →**](https://vynaris.com/uncensored-models/gemma-4-e4b-uncensored) How the directory works ## Useful discovery without pretending every checkpoint is hosted. 01 ### One family page Independent community releases are grouped around a readable model family instead of creating duplicate, thin pages. 02 ### Source attribution Variant cards link to the publisher's Hugging Face repository, with visible publisher and license information. 03 ### Honest availability Hosted badges appear only when an exact Vynaris model ID exists. Other pages show source and related-use options. API use ## Select a hosted model in every request. Put the exact Vynaris model ID in the standard `model` field. No separate endpoint, provider configuration, or infrastructure detail is required. ``` curl https://api.vynaris.com/v1/chat/completions \ -H "Authorization: Bearer $VYNARIS_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "vynaris/qwen3.6-35b-a3b-uncensored", "messages": [{"role": "user", "content": "Review this authorized test plan..."}], "stream": true }' ``` Hosted pricing ## Published rates, deducted from your normal balance. Top-ups are $20, $50, $100, $250, $500. | Model | Input / 1M tokens | Output / 1M tokens | Context | | --- | --- | --- | --- | | Qwen3.6-35B-A3B-uncensored | $1.00 | $5.00 | 128K tokens | | Qwen3.8-27B-uncensored | $1.00 | $7.00 | 128K tokens | | DeepSeek-V4-Flash-uncensored | $2.00 | $11.00 | 128K tokens | | GLM-5.3-uncensored | $5.00 | $20.00 | 128K tokens | Pay with Monero (XMR) Vynaris is the only AI API you can pay for in Monero that refunds bad answers. Pay with Monero (XMR) for complete payment privacy: no card, no name, no billing address. Same packs at +20%, straight to our own wallet with no payment processor, and the same models, limits and refunds as card-paid accounts, including the hosted uncensored models. [Pay with XMR in Billing →](https://app.vynaris.com/billing) Retention ## Hosted prompts and outputs are not persisted. For hosted model IDs, Vynaris retains only the billing and operational metadata needed to charge correctly, run the service, investigate abuse reports, and answer lawful requests. Cold starts and batching ## Capacity sleeps when demand does. The first request after an idle period can take longer while capacity starts. Concurrent requests queue into shared workers so warm capacity can batch demand. FAQ ## Questions about the directory and hosted API **Are all models in this directory hosted by Vynaris?** No. Only cards marked Hosted on Vynaris have a public Vynaris model ID. Directory-only cards describe community model families, link to their Hugging Face repositories, and identify a related hosted alternative without claiming the exact model is available. **What is an uncensored or reduced-refusal model?** It is generally a community-modified open-weight model intended to refuse fewer prompts. Uncensored, abliterated, heretic, and reduced-refusal are not standardized quality labels, so behavior must be evaluated per release. **Do you store prompts or model outputs?** For the Vynaris-hosted model IDs listed here, prompt and output bodies are not persisted. Vynaris retains operational metadata such as account, model, token counts, price, latency, status, and request ID. **Why can the first hosted request take longer?** Private capacity can sleep while idle. The first request may wait while the model service starts. Warm requests share the same workers, allowing concurrent demand to be queued and batched. **How is hosted usage billed?** Hosted usage is charged at the published per-token rates, which include a premium for guaranteed anonymity and data security, and deducted from your Vynaris credit balance. **Does reduced refusal make a model accurate or safe?** No. Reduced refusal can also reduce caution and calibration. Validate important outputs, follow each repository's license, and use models only for lawful, authorized work. **Independent directory, explicit sources.** Model names belong to their respective projects and publishers. Vynaris does not imply affiliation or endorsement, and the directory does not mirror model files. 4 entries are currently hosted; the rest are research guides.