NEAR AI
Sign inStart building

Uncensored LLM API.

NEAR AI Cloud is an uncensored LLM API. It serves abliterated open-weight models, with their refusal behavior removed, through an OpenAI-compatible endpoint. The models run inside secure enclaves (TEEs), so neither NEAR AI nor the cloud provider can read your prompts. Every account can use them, with no application.

Refusal direction · removed from the weights
Why private matters

Uncensored prompts are the sensitive ones.

You reach for an uncensored model when the work is sensitive: an exploit for your own system, a vulnerability nobody has patched yet, a malware sample, a hostile bug report. On a typical hosted API, those prompts are readable on the provider's servers, and "we don't log" is a promise you cannot check.

NEAR AI Cloud runs its abliterated models inside trusted execution environments on Intel and NVIDIA confidential computing. NEAR AI and the cloud provider cannot see your prompts or the answers, and you can verify it with a hardware attestation. More in what private AI inference is.

  • No application, no identity checks
  • No premium for privacy on NEAR-hosted models
Models and prices

Uncensored models on the API.

Context windows and prices come from the live catalog. You pay per token, with no minimums.

ModelContextPrice / 1M tokens (in / out)Privacy
DeepSeek 4.1 Flash Abliterateddeepseek-ai/DeepSeek-V4.1-Flash-1017-abliterated1.05M context · $0.3 / $1.2 per 1M1.05M$0.3 / $1.2 outPrivate TEE
Qwen3.8 27B AbliteratedQwen/Qwen3.8-27B-abliterated262K context · $0.04 / $1.35 per 1M262K$0.04 / $1.35 outPrivate TEE
Quickstart

Your first request. Same code as OpenAI.

  1. Create a NEAR AI Cloud account.No application. No identity checks.
  2. Create an API key.Export it as NEARAI_API_KEY.
  3. Change the base URL.https://cloud-api.near.ai/v1, then call any model ID from the table.
curl https://cloud-api.near.ai/v1/chat/completions \
  -H "Authorization: Bearer $NEARAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-V4.1-Flash-1017-abliterated",
    "messages": [
      {"role": "user", "content": "Explain how this SQL injection payload works."}
    ]
  }'

Works with any tool that accepts an OpenAI-compatible base URL. Full reference in the API docs.

Choosing a provider

How to choose an uncensored LLM API

CheckWhy it mattersNEAR AI Cloud
Does it actually answer?Some providers add a filter in front of the model, so it still refuses. Test the prompts your work needs.Abliterated models, with the refusal direction removed from the weights.
Who can read your prompts?Uncensored work means sensitive prompts: exploits, findings, hostile code. On a typical API, "we don't log" is a promise you cannot check.The models run in a TEE. NEAR AI and the cloud provider cannot read your prompts, and you can verify it.
Does your code still work?An OpenAI-compatible API means your SDK, agents and tools keep working with a new base URL.OpenAI-compatible chat completions at cloud-api.near.ai/v1.
Can you start today?Some uncensored offerings need an application or a sales call.Open to every account. No application, no identity checks, pay per token.
Are the rules clear?Uncensored does not mean anything goes. A clear usage policy protects you and the service.Governed by NEAR AI's public Acceptable Use Policy.
Security use cases

Built for defense.

  • Vulnerability review

    Find injection flaws, auth bypasses and unsafe deserialization in your own code without the model refusing to discuss the attack.

  • Authorized testing

    Write proof-of-concept exploits for systems you are authorized to test, and explain them to the team that fixes them.

  • Threat analysis

    Deobfuscate malware, explain payloads and read hostile bug bounty reports inside an enclave, then draft detection rules.

  • Red-teaming your AI

    Generate adversarial prompts to test the guardrails of your own AI products before attackers do.

More on how security teams work with these models: security research on NEAR AI Cloud.

Usage rules

Uncensored is not lawless.

The models answer what mainstream models refuse. You stay responsible for what you do with the answers. Use is governed by the Acceptable Use Policy.

Security teams can join NEAR AI RED for discounts and early access to new models.

FAQ

Questions developers ask about the uncensored API.

What is an uncensored LLM API?

It is an API that serves language models with their refusal behavior removed, so they answer requests a mainstream model would decline. NEAR AI Cloud serves abliterated models, where the refusal direction has been removed from the weights.

Which uncensored models can I use through the API?

NEAR AI Cloud serves abliterated DeepSeek V4.1 Flash and Qwen 3.8 27B. The table on this page lists every one with its live context window and price.

Is it OpenAI-compatible?

Yes. Point the OpenAI SDK, or any tool that accepts an OpenAI-compatible base URL, at https://cloud-api.near.ai/v1 and use your NEAR AI API key.

Can NEAR AI read my prompts?

No. The abliterated models run inside trusted execution environments on NEAR AI's infrastructure, so NEAR AI and the cloud provider cannot see your prompts or the answers. You can verify it with a hardware attestation.

Do I need to apply for access?

No. Every NEAR AI Cloud account can use the uncensored models, with no application and no identity checks. Security teams can join NEAR AI RED for discounts and early access.

How much does the uncensored API cost?

You pay per token, with no minimums. The live price per million input and output tokens for each model is in the table on this page and on each model page.

Is there a free uncensored LLM API?

NEAR AI Cloud is pay as you go, so you pay only for the tokens you use. You can also download abliterated models from Hugging Face and run them on your own hardware for free, if you have a GPU that fits them.

What am I allowed to use it for?

Legitimate work such as security research, authorized testing, malware analysis and red-teaming your own AI. Use is governed by NEAR AI's Acceptable Use Policy, and you stay responsible for what you do with the output.

Can I use it with coding agents and frameworks?

Yes. Tools that let you set a custom OpenAI-compatible base URL, such as most coding agents, LangChain and LlamaIndex, work with NEAR AI Cloud.

Uncensored answers. Private prompts.

Abliterated models through an OpenAI-compatible API, running in secure enclaves on NEAR AI Cloud.