Venice
Operational· checked every few minutes

Venice Uncensored 1.2 API

The Venice Uncensored 1.2 API: Venice's uncensored chat model for creative writing, roleplay and frank conversation, with image input, 30% below Venice's list price

Price per 1M tokens30%off
Input
$0.14$0.20
Output
$0.63$0.90
Get your API keyTry it in the playground
Model IDvenice-uncensored-1.2Updated
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-1.2",
    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
8K tokens
Reasoning
None
Input
Text, Image
Status
Operational

Pricing

Venice Uncensored 1.2 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
$0.14$0.20
Output
per 1M tokens
$0.63$0.90

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
$13.30
Venice list price
$19.00
You save every month$5.70

$68.40 a year

Cost

Venice Uncensored 1.2 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. $0.000399 a request.

    $19.95a month$28.50 at list

  • Documents

    20,000 requests a month, 8,000 tokens in and 500 out, 20% of the input cached. $0.00144 a request.

    $28.70a month$41.00 at list

  • Coding agent

    5,000 requests a month, 40,000 tokens in and 1,500 out, 85% of the input cached. $0.00655 a request.

    $32.73a month$46.75 at list

  • Classification

    1,000,000 requests a month, 400 tokens in and 5 out. $0.000059 a request.

    $59.15a month$84.50 at list

Overview

What is Venice Uncensored 1.2?

Venice Uncensored 1.2 is Venice's uncensored chat model, built for open-ended conversation, roleplay and creative writing without content filtering. Venice builds it on Dolphin Mistral 24B Venice Edition, a fine-tune of Mistral's 24B model. The Zurelay Venice Uncensored 1.2 API serves it through one OpenAI-compatible endpoint with a 128K-token context window and image input, at 30% below Venice's list price. Zurelay's Terms of Service still apply to everything you send it.

Venice Uncensored 1.2 is the newest version of Venice's uncensored model, which Venice describes as built for creative freedom, open-ended exploration, roleplay and unfiltered dialogue, with better abilities than 1.1. Venice lists Dolphin Mistral 24B Venice Edition, a fine-tune of Mistral's 24B model, as its source. It reads text and images and writes text, with a context window of 128,000 tokens and up to 8,192 output tokens. On Zurelay the model ID is venice-uncensored-1.2, and venice-uncensored-1-2 works too. It costs $0.14 per 1M input tokens and $0.63 per 1M output tokens.

Uncensored here means the model was tuned to answer rather than refuse or moralize: it writes the scene, plays the character or answers the question instead of declining. It suits fiction and roleplay with mature or dark themes, brainstorming without guardrails, and frank answers on sensitive topics. 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, and in our tests streamed about 100 tokens per second. It reads up to 10 images per request, 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. It calls tools when tool_choice is required or names a tool; with tool_choice auto it tends to say it will use a tool and then answer in text, so force the call when your app needs one. In our tests it found one fact buried in a 95K-token prompt in 11 to 14 seconds. You pay $0.14 per 1M input tokens and $0.63 per 1M output tokens against Venice's list price of $0.20 and $0.90.

Strengths

Where Venice Uncensored 1.2 shines. And what teams build with it.

01

Writes instead of refusing

Venice tuned it to stay in the conversation, so fiction, roleplay and sensitive questions get an answer rather than a refusal or a lecture.

02

Fast, direct answers

There's no reasoning step before the answer, and in our tests it streamed about 100 tokens per second.

03

Reads images

Send up to 10 images in one request, as https links or base64 data URLs, and it describes, compares or writes about them.

04

A low price per token

It costs $0.14 per 1M input tokens and $0.63 per 1M output tokens, 30% below Venice's list price.

Use cases

  • Fiction and interactive stories

    Mature, dark or morally complex stories, written for the story without the model stepping out of it to object.

  • Characters and companions

    Personas set in your system prompt that stay in character over long conversations.

  • Unfiltered brainstorming

    Ideas, drafts and rewrites without the hedging a filtered model adds.

  • Frank answers on sensitive topics

    Direct discussion of relationships, history, politics, religion and other subjects where mainstream models hedge or decline.

Get started

Call Venice Uncensored 1.2 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-1.2

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

    venice-uncensored-1.2

Works with the tools you already use

Compare

Similar models. All on the same key.

30%off

Venice Uncensored Role-Play

$0.35 / $1.40 per 1M tokens

Pick Venice Uncensored Role-Play, Venice's model tuned to stay in character, for roleplay and interactive fiction.

Venice Uncensored Role-Play 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, reasoning and a 1M-token context window, at a higher price per token.

Abliterated Large V2 API
70%off

Ministral 3 14B

$0.06 / $0.06 per 1M tokens

Pick Ministral 3 14B for Mistral's own model with its safety tuning intact.

Ministral 3 14B API

FAQ

Venice Uncensored 1.2 API questions.

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

How much does the Venice Uncensored 1.2 API cost?

On Zurelay, venice-uncensored-1.2 costs $0.14 per 1M input tokens and $0.63 per 1M output tokens. Venice's list price is $0.20 input and $0.90 output per 1M, so you save 30%. One rate applies at every prompt length, and failed requests are never billed.

What does uncensored mean for Venice Uncensored 1.2?

Venice tuned it to answer rather than refuse: it writes mature fiction, plays characters and discusses sensitive topics that filtered models decline or water down, with no content filter in front of it. Venice lists Dolphin Mistral 24B Venice Edition, a fine-tune of Mistral's 24B model, as its source.

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 1.2, 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 1.2 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-1.2". Zurelay also accepts venice-uncensored-1-2.

What is the Venice Uncensored 1.2 context window?

It holds 128,000 tokens of context and writes up to 8,192 output tokens per response. In our tests it found one fact buried in a 95K-token prompt in 11 to 14 seconds.

Can Venice Uncensored 1.2 read images?

Yes. It reads up to 10 images per request, sent as https links or base64 data URLs in OpenAI's format, and in our tests it read three at once. Audio, video and documents are turned away with a clear error before anything is billed.

Does Venice Uncensored 1.2 reason before it answers?

No. It answers directly, without a thinking step, so every output token is part of the answer.

Does Venice Uncensored 1.2 support tool calling and JSON output?

Yes, with one catch. It calls tools when tool_choice is "required" or names a tool, and reads tool results. With tool_choice auto it usually answers in text, often saying it will use the tool without calling it, so force the call when your app needs one. For JSON, send response_format with json_object or json_schema. logprobs isn't returned.

Is it the same model Venice serves?

Yes. Requests for venice-uncensored-1.2 run on Venice's Venice Uncensored 1.2, and Zurelay doesn't swap in a smaller or substitute model. Asked what it is, it names itself Venice Uncensored 1.2, made by Venice, and it keeps any persona your system prompt gives it, though under some personas it says it was built by Mistral AI, whose model it's tuned from. 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 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