NewHow we catch a seller listing the wrong model, and refund you if one does.

Uncensored LLM APIs (November 2026)

Updated November 20, 2026, 11:00 UTC. MartLLM prices are read live when the page is built (every hour); other providers' prices were checked October 30, 2026 or read from their public price lists at build. MartLLM wrote this page and is one of the providers in it.

On November 20, 2026, MartLLM had 12 uncensored text models taking requests (3 more listed but offline right now); they cost up to 42% less than their list price, with the card fee added. No ID or KYC check: sign up with your email (a 6-digit code) or with Google, then add prepaid credit by card or PayPal, from $5. DeepSeek V4.1 Flash Uncensored cost $0.2244 / $0.8976 on MartLLM against $0.33 / $1.32 on Venice. Venice, Unlid, NanoGPT and uncensoredllm.ai also take OpenAI-style requests; OpenRouter lists one uncensored model.

ProviderUncensored text modelsMain model price, in / out per 1MHow you pay
MartLLM12 taking requests nowDeepSeek V4.1 Flash Uncensored $0.2244 / $0.8976Prepaid by card or PayPal, from $5; no ID or KYC
VeniceVenice Uncensored, plus uncensored Gemma and DeepSeek buildsVenice Uncensored 1.2 $0.20 / $0.90Card or crypto credit, or staked DIEM
OpenRouter1 (Venice: Uncensored, a Dolphin Mistral 24B edition)$0.20 / $0.90Card, crypto; 5.5% fee on credit
UnlidGLM 5.3, Gemma 4 and DeepSeek V4.1 Flash uncensored, among othersDeepSeek V4.1 Flash Uncensored $0.40 / $1.61Card or USDT/USDC, $5 to $5,000 per top-up
NanoGPTVenice, DeepSeek, GLM 5.3, Qwen, MiMo and abliterated modelsDeepSeek V4.1 Flash Uncensored $0.33 / $1.32Pay as you go, or $12/month
uncensoredllm.ai130 chat models, incl. GLM 5.3 uncensored and abliteratedGLM 5.3 Flash Uncensored $0.1086 / $0.3802Prepaid from $10, card or crypto
uncensored.com1 in its API list (DeepSeek V4.1 Flash Uncensored)$0.30 / $1.20Subscriptions from $29.99/month, or credits
Abliteration.aiIts own abliterated modelsLarge Flash $1.00 / $2.00Plans from $20/month, or pay as you go

MartLLM first because it lists the most uncensored models here that you can call with the same key as mainstream models; the rest follow by how many uncensored models they list. An empty cell means we could not confirm it on the provider's own pages.

Uncensored text models on MartLLM now ($ per 1M input / output tokens)

ModelMartLLM priceStatus
DeepSeek V4.1 Flash 1017 Uncensored$0.2145 / $0.858Taking requests
DeepSeek V4.1 Flash Uncensored$0.2244 / $0.8976Taking requests
Abliterated Large V2$1.74 / $2.90Taking requests
Venice Role Play Uncensored$0.2747 / $1.0989Taking requests
Venice Uncensored 1.2$0.1111 / $0.4999Taking requests
Abliterated Large Flash$0.6985 / $1.3969Taking requests
GLM 4.7 Flash Heretic$0.049 / $0.2797Taking requests
Gemma 4 26B A4B Uncensored (E2EE)$0.1055 / $0.4887Taking requests
Qwen 3.6 Plus Uncensored$0.5125 / $3.075Taking requests
Venice Uncensored 1.1$0.19 / $0.855Taking requests
Qwen 3.6 35B A3B Uncensored (E2EE)$0.20 / $0.60Taking requests
GLM 5.3 Flash Abliterated / Uncensored$0.736 / $1.472Taking requests
GLM 5.3 UncensoredOffline right now
GLM 5.3 AbliteratedOffline right now
GLM 5.3 Flash AbliteratedOffline right now

MartLLM: the best seller’s price, read November 20, 2026; a reply can cost more when the cheapest seller is busy. Other services: their own pages and model lists, checked 2026-10-30 (Venice and OpenRouter read when this page was built).

Each provider, good and bad

MartLLM

Pick it if: Uncensored models next to GPT, Claude and DeepSeek on one key, billed per token, with no ID check.

Watch for: Some uncensored models have a single provider and go offline when it is down or busy: the table below shows which can take requests now. Adult image and video models are hidden on the model list until you tick “Show adult models”.

Source: MartLLM models (live, November 20, 2026)

Venice

Pick it if: The maker of Venice Uncensored, with a privacy-first policy.

Watch for: Its DeepSeek uncensored price is above the cheapest resellers.

Source: Venice model list, Venice pricing (checked 2026-10-30)

OpenRouter

Pick it if: You already use OpenRouter and need one uncensored model.

Watch for: One uncensored model, not free.

Source: OpenRouter model list (checked 2026-10-30)

Unlid

Pick it if: A wide uncensored list including GLM 5.3 Uncensored.

Watch for: Higher DeepSeek uncensored price than Venice or MartLLM.

Source: Unlid (checked 2026-10-30)

NanoGPT

Pick it if: A subscription that also works in SillyTavern and Janitor AI.

Watch for: Paid models keep billing your balance on the subscription.

Source: NanoGPT model list, NanoGPT pricing (checked 2026-10-30)

uncensoredllm.ai

Pick it if: The lowest GLM 5.3 Flash Uncensored price we found.

Watch for: Prepaid from $10.

Source: uncensoredllm.ai pricing (checked 2026-10-30)

uncensored.com

Pick it if: You also want its chat app.

Watch for: One model in its API list.

Source: uncensored.com model list (checked 2026-10-30)

Abliteration.ai

Pick it if: The makers of the abliterated models, with a free one-credit preview.

Watch for: Higher per-token prices than resellers of the same models.

Source: Abliteration.ai pricing (checked 2026-10-30)

How to switch to MartLLM

Uncensored models take the same OpenAI-style request as any other model: change the base URL, the key and the model id.

python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.martllm.com/v1",  # was: https://api.venice.ai/api/v1
    api_key="ull_your_key_here",
)

resp = client.chat.completions.create(
    model="deepseek/deepseek-v4.1-flash-uncensored",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

No MartLLM fee on requests. Adding credit by card costs 5.5% + $0.50.

Questions

Does MartLLM ask for ID or KYC?

No ID or KYC check: sign up with your email (a 6-digit code) or with Google, then add prepaid credit by card or PayPal, from $5.

Which request formats work with uncensored models on MartLLM?

One key and the same request formats as every other model: OpenAI chat completions (/v1/chat/completions), the OpenAI Responses API (/v1/responses) and Anthropic messages (/v1/messages), base URL https://api.martllm.com/v1. Streaming works on all three.

What is still not allowed with uncensored models?

Uncensored means the model does not refuse legal adult or sensitive topics. Each service keeps terms of use: MartLLM’s ban breaking the law and sexual content involving minors, and so do uncensoredllm.ai’s.

Do uncensored API providers keep prompts?

Venice says prompts and replies are not retained after the request completes; Abliteration.ai says they are not stored by default; Unlid says request bodies are not kept beyond what serving them needs. Read each provider’s policy before sending private data.

Can I use uncensored models in SillyTavern or JanitorAI?

Yes, through any OpenAI-compatible provider: set the API URL to the provider’s base URL (for MartLLM, https://api.martllm.com/v1) and the model id.

Are there other fees on MartLLM?

No MartLLM fee on requests. Adding credit by card costs 5.5% + $0.50.