Google
Operational· checked every few minutes

Gemma 4 Uncensored API

The Gemma 4 Uncensored API: a community uncensored fine-tune of Google's Gemma 4 26B, with a 256K-token context, image input and tools, 4% below list price

Price per 1M tokens4%off
Input
$0.155$0.1625
Output
$0.48$0.50
Get your API keyTry it in the playground
Model IDgemma-4-uncensoredUpdated
chat.py
from openai import OpenAI
client = OpenAI(
    base_url="https://api.zurelay.com/v1",
    api_key="YOUR_ZURELAY_KEY",
)
stream = client.chat.completions.create(
    model="gemma-4-uncensored",
    messages=[
        {"role": "user", "content": "Explain quicksort briefly."},
    ],
    stream=True,
)
for chunk in stream:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="")

Base URL https://api.zurelay.com/v1. Works with any OpenAI SDK. Chat API docs

Context window
256K tokens
Max output
8K tokens
Reasoning
None
Input
Text, Image
Status
Operational

Pricing

Gemma 4 Uncensored API pricing. A fraction of the list price.

Pay as you go from prepaid credit, with no subscription. Top up from $10. Requests that fail are never billed.

RateZurelayGoogle list
Input
per 1M tokens
$0.155$0.1625
Output
per 1M tokens
$0.48$0.50

One rate at every prompt length, up to the full 256K context window. Streaming, tool calls and structured outputs cost nothing extra.

Every Uncensored LLM model and price
Savings calculator

Move the sliders to your monthly usage.

Input tokens per month50M
Output tokens per month10M
Zurelay
$12.55
Google list price
$13.13
You save every month$0.57

$6.90 a year

Cost

Gemma 4 Uncensored API cost, worked out. And compared.

Typical workloads at Zurelay's live prices next to the list price, and what other places charge for the same model.

  • Chatbot

    50,000 requests a month, 1,500 tokens in and 300 out, 30% of the input cached. $0.000376 a request.

    $18.83a month$19.69 at list

  • Documents

    20,000 requests a month, 8,000 tokens in and 500 out, 20% of the input cached. $0.00148 a request.

    $29.60a month$31.00 at list

  • Coding agent

    5,000 requests a month, 40,000 tokens in and 1,500 out, 85% of the input cached. $0.00692 a request.

    $34.60a month$36.25 at list

  • Classification

    1,000,000 requests a month, 400 tokens in and 5 out. $0.000064 a request.

    $64.40a month$67.50 at list

Where to buy Gemma 4 Uncensored

Prices per 1M tokens

SellerInputOutput
Google
List price, direct
$0.1625$0.50
OpenRouter
List price, plus 5.5% on card top-ups
$0.1625$0.50
Zurelay
No fee to add credit
$0.155$0.48

OpenRouter's fee as its pricing page listed it on October 28, 2026. Zurelay's prices are live. Some labs also discount batch or off-peak requests.

Overview

What is Gemma 4 Uncensored?

Gemma 4 Uncensored is a community uncensored fine-tune of Google's Gemma 4 26B, a mixture-of-experts model with about 4B parameters active per token, tuned for chat without content filtering. It isn't made or endorsed by Google. The Zurelay Gemma 4 Uncensored API serves it through one OpenAI-compatible endpoint with a 256K-token context window, image input and tool calling, at 4% below list price. Zurelay's Terms of Service still apply to everything you send it.

Gemma 4 Uncensored starts from Gemma 4 26B, Google's open-weight mixture-of-experts model with 26B parameters in all and about 4B active for each token, and is fine-tuned for chat without refusals or content filtering. The fine-tune, supergemma4-26b-uncensored, is published on Hugging Face by Jiunsong and runs in 4-bit precision. It is a community build, not made or endorsed by Google. It reads text and one image per request and writes text, with a context window of 256,000 tokens and up to 8,192 output tokens. On Zurelay the model ID is gemma-4-uncensored, and supergemma4-26b-uncensored works too. It costs $0.155 per 1M input tokens and $0.48 per 1M output tokens.

It suits chat, writing and assistant work where a filtered model refuses or hedges: fiction with mature themes, roleplay, frank answers on sensitive topics, and agents that shouldn't refuse parts of a task. Fine-tuning away refusals can shift other abilities too, so test it on your own tasks before you rely on it. Fewer refusals don't change what you may use it for. Zurelay's Terms of Service (https://zurelay.com/legal/terms) still apply to everything sent to it, including the acceptable use rules in section 7, and you are responsible for how you use its output.

It answers directly, without a reasoning step, at about 40 tokens per second in our tests. It calls tools on its own, several at once and while streaming, follows json_object and json_schema in response_format, and takes max_tokens, stop sequences and the usual sampling settings, top_k and seed included. You pay $0.155 per 1M input tokens and $0.48 per 1M output tokens against a list price of $0.1625 and $0.50.

Strengths

Where Gemma 4 Uncensored shines. And what teams build with it.

01

Answers instead of refusing

It was fine-tuned to answer rather than decline, so fiction, roleplay and sensitive questions get a reply instead of a refusal or a lecture.

02

256K tokens of context

Long documents, chats and codebases fit in one request.

03

Reads an image

Send one image per request, as an https link or base64 data URL, and it describes it or answers questions about it.

04

Tools on its own

It decides when to call a tool, calls several at once, also while streaming, and reads the results, so it works in agents.

Use cases

  • Uncensored assistants

    Chat and writing help that doesn't refuse or hedge on mature or sensitive requests.

  • Fiction and roleplay

    Stories and characters with dark or mature themes, written without the model stepping out to object.

  • Uncensored agents

    Agents that call tools on their own without refusing parts of the task.

  • Images without a filter

    Descriptions and questions about an image that filtered vision models decline.

Get started

Call Gemma 4 Uncensored in three steps.

No waitlist and no new SDK. If your code already talks to OpenAI, it already talks to Zurelay.

  1. 1

    Create a key

    Sign up, add credit and create an API key. Set a monthly budget or a rate limit per key if you like.

    Get your API key
  2. 2

    Point your SDK at Zurelay

    Change the base URL. Everything else in your code stays the same.

    https://api.zurelay.com/v1
  3. 3

    Use gemma-4-uncensored

    Send chat completions as usual. Streaming, tool calls and usage reporting work as you expect.

    gemma-4-uncensored

Works with the tools you already use

Compare

Similar models. All on the same key.

30%off

Venice Uncensored 1.2

$0.14 / $0.63 per 1M tokens

Pick Venice Uncensored 1.2, Venice's uncensored chat model, for faster answers and up to 10 images per request.

Venice Uncensored 1.2 API
13%off

GLM-4.7 Flash Heretic

$0.061 / $0.35 per 1M tokens

Pick GLM-4.7 Flash Heretic for an uncensored model that reasons, with levels you can set, at a lower price per token.

GLM-4.7 Flash Heretic API
71%off

Gemini 3.8 Flash

$0.22 / $1.10 per 1M tokens

Pick Gemini 3.8 Flash for Google's own model with its safety tuning intact.

Gemini 3.8 Flash API

FAQ

Gemma 4 Uncensored API questions.

Anything else? Ask our team and we’ll answer by email.

How much does the Gemma 4 Uncensored API cost?

On Zurelay, gemma-4-uncensored costs $0.155 per 1M input tokens and $0.48 per 1M output tokens. The list price is $0.1625 input and $0.50 output per 1M, so you save 4%. One rate applies at every prompt length, and failed requests are never billed.

Is Gemma 4 Uncensored made by Google?

No. Google made Gemma 4 26B and released its weights; Gemma 4 Uncensored is a community fine-tune of those weights, supergemma4-26b-uncensored, not made or endorsed by Google. Asked what it is, it names itself Gemma 4 Uncensored and credits Google, whose model it's built on. For Google's own models with their safety tuning intact, use Gemini.

Do Zurelay's Terms of Service still apply?

Yes. An uncensored fine-tune changes what the model will write, not the rules. Zurelay's Terms of Service (https://zurelay.com/legal/terms) apply to everything sent to Gemma 4 Uncensored, including the acceptable use rules in section 7, and you are responsible for how you use its output, as with any model on Zurelay.

How do I call the Gemma 4 Uncensored API with the OpenAI SDK?

Install the official openai package, set base_url to https://api.zurelay.com/v1 and use your Zurelay API key. Then send a Chat Completions request with model set to "gemma-4-uncensored". Zurelay also accepts supergemma4-26b-uncensored.

What is the Gemma 4 Uncensored context window?

It holds 256,000 tokens of context and writes up to 8,192 output tokens per response.

Can Gemma 4 Uncensored read images?

Yes, one per request, sent as an https link or a base64 data URL in OpenAI's format. A request with more than one image, or with audio, video or documents, is turned away with a clear error before anything is billed.

Does Gemma 4 Uncensored support tool calling and JSON output?

Yes. Pass tools as you would to any OpenAI model; it calls them on its own with tool_choice auto, several at once and while streaming, reads tool results, and follows "required" and a tool forced by name. For JSON, send response_format with json_object or json_schema. It answers without a reasoning step, and logprobs isn't returned.

Does Zurelay swap in another model?

No. Requests for gemma-4-uncensored run on Gemma 4 Uncensored, and Zurelay doesn't swap in a smaller or substitute model. Automatic smart routing has no alternative for it, so a request never quietly falls back to a filtered model; only a fallback you set yourself, in a key's custom rules or a request's models list, can answer instead, and the x-zurelay-model header names the model that answered. Zurelay is independent and is not affiliated with or endorsed by Google.

More models on Zurelay

All models

Stop paying list price.
Start saving today.

Create a key in seconds, point the SDK you already use at Zurelay, and every request costs up to 90% less from the first token.

Get your API keyTalk to an engineer