Gemma 4 31B SDFT Heretic RP by API.

Abliterated by Google (community tune), on UncensoredLLM as gemma-4-31b-sdft-heretic-rp.

Get a key

Price per million tokens

Input
$1.224
Output
$1.224
Daily check
Steady since Oct 23
How the check works
As of
2026-10-24

First request

curl
1curl https://api.uncensoredllm.ai/v1/chat/completions \
2 -H "Authorization: Bearer sk-ullm-live-…" \
3 -H "Content-Type: application/json" \
4 -d '{"model": "gemma-4-31b-sdft-heretic-rp", "messages": [{"role": "user", "content": "Hello"}]}'

Base URL https://api.uncensoredllm.ai/v1. The key comes from the console; prices settle per token.

Gemma 4 31B SDFT Heretic RP specs

Kind
Abliterated
Developer
Google (community tune)
Base model
Gemma 4 31B
Context window
262,144 tokens
Input
text
Wire formats
openai

Get a key

  1. Create a key in the console. Credit is prepaid from $10, with no subscription.
  2. Point your SDK or tool at https://api.uncensoredllm.ai/v1, for example with OPENAI_BASE_URL, and send the key as the bearer token.
  3. Send gemma-4-31b-sdft-heretic-rp as the model. The same key calls every model on UncensoredLLM.

Also try

GLM-5.3 Abliterated$4.50 outGLM-5.3 Flash Abliterated$0.88 outDeepSeek V4.1 Flash Abliterated$1.6975 outDeepSeek R1 Distill Llama 70B Abliterated$2.80 out

More from Google (community tune)

Gemma 4 31B Agares v1$1.071 outGemma 4 31B Animus V14.1$1.071 outGemma 4 31B AssGuard$1.071 outGemma 4 31B Cognitive Unshackled$1.071 outGemma 4 31B Dark Gemistry$1.224 outGemma 4 31B DarkIdol$1.80 out

What this build is

Gemma 4 31B SDFT Heretic RP is an abliterated build: the refusal direction was removed from the weights, so it answers prompts the stock model declines. There is no system prompt trick to maintain and nothing the model has to be talked into.

Every request is routed to the build’s live route and settled to the token at the prices above. The daily real-model check sends a fixed prompt to every model and records whether the answer still matches; this model’s verdict today is “Steady since Oct 23”.

Use it from the OpenAI SDK, from SillyTavern or Janitor, or from a coding agent. Keys and top-ups live in the console.

Gemma 4 31B SDFT Heretic RP questions

Gemma 4 31B SDFT Heretic RP is an abliterated build of Gemma 4 31B from Google (community tune), with a 262,144-token context window, taking text input. On UncensoredLLM it answers as gemma-4-31b-sdft-heretic-rp.

Gemma 4 31B SDFT Heretic RP is an abliterated build: the refusal direction was removed from the weights, so it answers prompts the stock model declines. There is no system prompt trick to maintain and nothing the model has to be talked into.

$1.224 per million input tokens and $1.224 per million output tokens. Credit is prepaid from $10, with no subscription.

It is pay as you go: prepaid credit from $10, billed per token, with no subscription or monthly fee. A 1,000-token prompt with a 500-token reply costs about $0.0018.

Gemma 4 31B SDFT Heretic RP has a 262,144-token context window. It takes text input.

Yes. Send gemma-4-31b-sdft-heretic-rp as the model through the OpenAI SDK, or any client that takes a custom OpenAI base URL, with base URL https://api.uncensoredllm.ai/v1.

In SillyTavern, set API to Chat Completion, Source to Custom (OpenAI-compatible) and the custom endpoint to https://api.uncensoredllm.ai/v1, paste your key, then pick gemma-4-31b-sdft-heretic-rp from the list it loads. In Janitor AI, choose Proxy, set the URL to https://api.uncensoredllm.ai/v1/chat/completions, paste your key and type gemma-4-31b-sdft-heretic-rp as the model. See the docs.

Yes. The daily real-model check sends every model the same fixed prompt and records whether the answer still matches. Gemma 4 31B SDFT Heretic RP’s latest result, from Oct 24: steady since Oct 23. See the daily check.