Venice
Operational· checked every few minutes

Venice Uncensored Role-Play API

The Venice Uncensored Role-Play API: Venice's uncensored model tuned to stay in character, for roleplay, companions and interactive fiction, 30% below Venice's list price

Price per 1M tokens30%off
Input
$0.35$0.50
Output
$1.40$2.00
Get your API keyTry it in the playground
Model IDvenice-uncensored-role-playUpdated
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="venice-uncensored-role-play",
    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
128K tokens
Max output
4K tokens
Reasoning
None
Input
Text
Status
Operational

Pricing

Venice Uncensored Role-Play 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.

RateZurelayVenice list
Input
per 1M tokens
$0.35$0.50
Output
per 1M tokens
$1.40$2.00

One rate at every prompt length, up to the full 128K 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
$31.50
Venice list price
$45.00
You save every month$13.50

$162.00 a year

Cost

Venice Uncensored Role-Play API cost, worked out.

Typical workloads at Zurelay's live prices, next to the list price.

  • Chatbot

    50,000 requests a month, 1,500 tokens in and 300 out, 30% of the input cached. $0.000945 a request.

    $47.25a month$67.50 at list

  • Documents

    20,000 requests a month, 8,000 tokens in and 500 out, 20% of the input cached. $0.0035 a request.

    $70.00a month$100.00 at list

  • Coding agent

    5,000 requests a month, 40,000 tokens in and 1,500 out, 85% of the input cached. $0.0161 a request.

    $80.50a month$115.00 at list

  • Classification

    1,000,000 requests a month, 400 tokens in and 5 out. $0.000147 a request.

    $147.00a month$210.00 at list

Overview

What is Venice Uncensored Role-Play?

Venice Uncensored Role-Play is Venice's uncensored model tuned for roleplay: it follows a persona from your system prompt, stays in character and writes immersive scenes and dialogue. Venice builds it on a 24B-parameter roleplay fine-tune. The Zurelay Venice Uncensored Role-Play API serves it through one OpenAI-compatible endpoint with a 128K-token context window, at 30% below Venice's list price. Zurelay's Terms of Service still apply to everything you send it.

Venice Uncensored Role-Play is Venice's model for roleplay, which Venice describes as built for immersive storytelling, character interactions and open-ended creative writing with maximum freedom. Venice lists 24B-3.2-RP-K2-final, a 24B-parameter roleplay fine-tune published by dphnAI, as its source. It reads and writes text, with a context window of 128,000 tokens and up to 4,096 output tokens per response. On Zurelay the model ID is venice-uncensored-role-play, and venice-role-play-uncensored and venice-uncensored-roleplay work too. It costs $0.35 per 1M input tokens and $1.40 per 1M output tokens.

Put the character, the setting and the rules of the scene in the system prompt, and it plays that character turn after turn, in the voice and tone you set, without stepping out of the story to object. Uncensored means it writes mature and dark scenes that filtered models decline. 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. It 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; logprobs isn't supported. It calls tools when tool_choice is required or names a tool, and on auto answers in text. It takes text only. In our tests it found one fact buried in a 95K-token prompt in 11 to 14 seconds. You pay $0.35 per 1M input tokens and $1.40 per 1M output tokens against Venice's list price of $0.50 and $2.00.

Strengths

Where Venice Uncensored Role-Play shines. And what teams build with it.

01

Stays in character

It follows the persona in your system prompt and keeps it, so a character keeps its voice across a long conversation.

02

Immersive scenes

Venice tuned it for storytelling and character interaction, so it writes scenes and dialogue rather than summaries.

03

No refusals mid-story

Dark, mature and morally complex scenes get written for the story, without the model breaking off to object.

04

128K tokens of context

Long chats and the whole story so far fit in one request, so the character remembers what happened.

Use cases

  • Roleplay and companion apps

    Characters with their own personality, voice and memory of the conversation, set in your system prompt.

  • Interactive fiction and text games

    A narrator that runs the world, plays the other characters and reacts to what the player does.

  • Story writing with mature themes

    Crime, horror, romance and war, written in scene without the model stepping out of the story.

  • Dialogue for games and scripts

    Lines and scenes for many characters, each in their own voice.

Get started

Call Venice Uncensored Role-Play 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 venice-uncensored-role-play

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

    venice-uncensored-role-play

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 general uncensored model, when you also need image input or up to 8,192 output tokens.

Venice Uncensored 1.2 API
4%off

Gemma 4 Uncensored

$0.155 / $0.48 per 1M tokens

Pick Gemma 4 Uncensored for an uncensored model with a 256K-token context window and tools it calls on its own.

Gemma 4 Uncensored API
2%off

Abliterated Large V2

$2.93 / $4.88 per 1M tokens

Pick Abliterated Large V2 for a much larger model with its refusals removed and reasoning, at a higher price per token.

Abliterated Large V2 API

FAQ

Venice Uncensored Role-Play API questions.

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

How much does the Venice Uncensored Role-Play API cost?

On Zurelay, venice-uncensored-role-play costs $0.35 per 1M input tokens and $1.40 per 1M output tokens. Venice's list price is $0.50 input and $2.00 output per 1M, so you save 30%. One rate applies at every prompt length, and failed requests are never billed.

How do I set up a character?

Describe the character in the system prompt: who they are, how they speak, the setting and anything they should or shouldn't do. Then send the conversation as user and assistant messages as usual. It keeps the persona across turns. Asked who made it while in character, it may answer as the character or name Mistral AI, whose model its fine-tune starts from.

Do Zurelay's Terms of Service still apply?

Yes. An uncensored model changes what the model will write, not the rules. Zurelay's Terms of Service (https://zurelay.com/legal/terms) apply to everything sent to Venice Uncensored Role-Play, 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 Venice Uncensored Role-Play 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 "venice-uncensored-role-play". Zurelay also accepts venice-role-play-uncensored and venice-uncensored-roleplay.

What is the Venice Uncensored Role-Play context window?

It holds 128,000 tokens of context and writes up to 4,096 output tokens per response, so long scenes come in several turns. In our tests it found one fact buried in a 95K-token prompt in 11 to 14 seconds.

Can Venice Uncensored Role-Play read images?

No. It takes text only on Zurelay. A request that includes images or files is turned away with a clear error before anything is billed. Venice Uncensored 1.2 reads images if you need them.

Does Venice Uncensored Role-Play support tool calling and JSON output?

It calls tools when tool_choice is "required" or names a tool, and reads tool results; with tool_choice auto it answers in text. For JSON, send response_format with json_object or json_schema. logprobs isn't supported. It answers without a reasoning step.

Is it the same model Venice serves?

Yes. Requests for venice-uncensored-role-play run on Venice's Venice Uncensored Role-Play, 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. Responses are sampled, so wording varies between runs. Zurelay is independent and is not affiliated with or endorsed by Venice.

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