Run Kimi K3 Uncensored without a GPU.
Uncensored by Moonshot AI, on Unrestrictable as kimi-k3-uncensored.
Kimi K3 Uncensored is an uncensored build of Kimi K3. It costs $5.745 per million input tokens and $28.68 per million output tokens, prepaid, with a 262,144-token context window. Call it at https://api.unrestrictable.ai/v1/chat/completions with model "kimi-k3-uncensored" and an Unrestrictable key, from any OpenAI SDK or client that takes a base URL.
Price per million tokens
- Input
- $5.745
- Cached input
- $1.437
- Output
- $28.68
- Success rate
- 90.7% of 259 requests, last 24 hours
- Daily check
- Steady since Nov 3
- As of
- 2026-11-16
First request
curl https://api.unrestrictable.ai/v1/chat/completions \ -H "Authorization: Bearer sk-unr-live-…" \ -H "Content-Type: application/json" \ -d '{"model": "kimi-k3-uncensored", "messages": [{"role": "user", "content": "Hello"}]}'Kimi K3 Uncensored settings for SillyTavern and Janitor AI
- SillyTavern API
- Chat Completion
- Source
- Custom (OpenAI-compatible)
- Custom endpoint
- https://api.unrestrictable.ai/v1
- Model
- kimi-k3-uncensored
- Context Size
- 262,144 tokens
- Max response length
- 65,536 tokens
- Janitor AI proxy URL
- https://api.unrestrictable.ai/v1/chat/completions
- Key prefix
- sk-unr-
Kimi K3 Uncensored specs
- Kind
- Uncensored
- Developer
- Moonshot AI
- Base model
- Kimi K3
- Context window
- 262,144 tokens
- Max output
- 65,536 tokens
- Input
- text and image
- Wire formats
- openai
Get a key
- Create a key in the console. Credit is prepaid from $10, with no subscription.
- Set OPENAI_BASE_URL to https://api.unrestrictable.ai/v1 and send your sk-unr- key as the bearer token.
- Send kimi-k3-uncensored as the model. The same key calls every model on Unrestrictable.
What Kimi K3 Uncensored is
- Base model
- Base parameters
- 2.8T total, 104B active
- Base context, per the card
- one million tokens
- License of the base, read 2026-10-26
- Kimi K3 License
- Kind
- the model served without a content filter
- Context window here
- 262,144 tokens
- Max output
- 65,536 tokens
- Input
- text and image
From the SDK
from openai import OpenAI client = OpenAI(base_url="https://api.unrestrictable.ai/v1", api_key="sk-unr-live-…") completion = client.chat.completions.create( model="kimi-k3-uncensored", messages=[{"role": "user", "content": "Hello"}],)print(completion.choices[0].message.content)import OpenAI from 'openai'; const client = new OpenAI({ baseURL: 'https://api.unrestrictable.ai/v1', apiKey: 'sk-unr-live-…' }); const completion = await client.chat.completions.create({ model: 'kimi-k3-uncensored', messages: [{ role: 'user', content: 'Hello' }],});console.log(completion.choices[0].message.content);What changed from stock Kimi K3
Kimi K3 Uncensored is an uncensored build: it answers without the safety refusals of the stock model.
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 Nov 3”.
Use it from the OpenAI SDK, from SillyTavern or Janitor, or from a coding agent. Keys and top-ups live in the console.
Also try
More from Moonshot AI
Compare
What Kimi K3 Uncensored costs, worked
A chat turn of 2,000 input and 500 output tokens at $5.745 input and $28.68 output per million tokens is $0.0258; 1,000 turns are $25.83. A long chat session of 100 replies of 300 tokens costs $3.1584 at 4,000 tokens of context and $10.0524 at 16,000: every message resends the context, so size it to what the chat needs. All from prepaid credit, no subscription.
| Uncensored builds | Context | In / out per 1M | 1,000 chat turns |
|---|---|---|---|
| GLM-5.3 Flash Uncensored | — | $0.1053 / $0.3685 | $0.39 |
| GLM-5.3 Uncensored | — | $0.282 / $0.846 | $0.99 |
| Dolphin Mistral 24B Venice Edition | 33K | $0.50 / $2.25 | $2.13 |
| Deepseek V4.1 Flash Uncensored | 1000K | $0.5412 / $2.1647 | $2.16 |
| Gemma 4 26B-A4B Uncensored | 33K | $0.60 / $2.80 | $2.60 |
| Gemma 4 31B K1 v5 | 262K | $1.071 / $1.071 | $2.68 |
| DeepSeek V4 Pro Uncensored | — | $0.97 / $1.94 | $2.91 |
| DeepSeek V4.1 Flash 1017 Uncensored | 1049K | $0.8003 / $3.201 | $3.20 |
| DeepSeek V4.1 Flash 1017 Uncensored Thinking | 1049K | $0.8003 / $3.201 | $3.20 |
| DeepSeek V4.1 Flash 0910 Uncensored | 524K | $0.825 / $3.30 | $3.30 |
| DeepSeek V4.1 Flash 0910 Uncensored Thinking | 524K | $0.825 / $3.30 | $3.30 |
| DeepSeek V4.1 Flash Uncensored Thinking | 1049K | $0.825 / $3.30 | $3.30 |
| Qwen3.8 Max Uncensored | 991K | $1.00 / $3.00 | $3.50 |
| GLM-5.3 Flash Code Uncensored | — | $6.00 / $6.00 | $15.00 |
| Kimi K3 Uncensored | 262K | $5.745 / $28.68 | $25.83 |
Kimi K3 Uncensored in SillyTavern and Janitor AI: what to set
The three fields are the base URL, the key and the model id, as in the settings above. What differs by build is the reply length, the reasoning switch and the context size, and those decide both whether a reply arrives whole and what each message costs.
- Moonshot’s 2.8T-parameter flagship with 104B active parameters, the largest parameter count of any card on record here (the moonshotai/Kimi-K3 card, read 2026-10-26). The catalog lists a 262,144-token window; keep Context Size at 8,000 to 16,000 unless the chat needs more, because every message resends the context at one of the highest input rates on the key.
- A Max Response Length of 300 to 600 tokens fits a chat reply.
- No jailbreak preamble is needed and none should be sent: a preamble is resent and billed on every message, and this build answers without one.
A request that fails before the model answers is not billed. A refusal written as ordinary text is billed like any answer, which is the reason to send this build rather than a stock model with a preamble: the build does not write one.
What Kimi K3 Uncensored costs by client
| Session | What is sent | At the live price |
|---|---|---|
| SillyTavern or Janitor AI, one evening | 100 replies of 300 tokens on 4,000 tokens of context | $3.1584 |
| The same evening on a long chat | 100 replies of 300 tokens on 16,000 tokens of context | $10.0524 |
| A month of short turns | 1,000 turns of 2,000 input and 500 output tokens | $25.83 |
| One long document, summarised once | 100,000 input and 1,000 output tokens in one request | $0.6032 |
Kimi K3 Uncensored questions
Kimi K3 Uncensored is an uncensored build of Kimi K3 from Moonshot AI, with a 262,144-token context window, taking text and image input. On Unrestrictable it answers as kimi-k3-uncensored.
No. Credit is prepaid from $10 and billed per token: input $5.745 and output $28.68 per million tokens, cached input $1.437.
About $0.0201 for 1,000 tokens in and 500 tokens out, at $5.745 in and $28.68 out per million tokens.
Up to 262,144 tokens, the context window the catalog lists for Kimi K3 Uncensored; Max Response Length can go up to 65,536 tokens.
Yes. Send kimi-k3-uncensored as the model through the OpenAI SDK, or any client that takes a custom OpenAI base URL, with base URL https://api.unrestrictable.ai/v1.
In SillyTavern, set API to Chat Completion, Source to Custom (OpenAI-compatible) and the custom endpoint to https://api.unrestrictable.ai/v1, paste your key, then pick kimi-k3-uncensored from the list it loads. In Janitor AI, choose Proxy, set the URL to https://api.unrestrictable.ai/v1/chat/completions, paste your key and type kimi-k3-uncensored 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. Kimi K3 Uncensored’s latest result, from Nov 16: steady since Nov 3. See the daily check.
Measured on live traffic over the last 24 hours: 90.7% of 259 requests to Kimi K3 Uncensored succeeded.
Moonshot AI's Kimi K3: 2.8T total, 104B active, one million tokens of context, open weights under Kimi K3 License (moonshotai/Kimi-K3, read 2026-10-26). This build is that model served without a content filter.
The stock Kimi K3 is released under Kimi K3 License (moonshotai/Kimi-K3 on Hugging Face, read 2026-10-26). Kimi K3 Uncensored is a build of those weights; sending kimi-k3-uncensored here needs no copy of them.
Yes: kimi-k3-uncensored at https://api.unrestrictable.ai/v1 on the OpenAI format, $5.745 / $28.68 per million tokens in / out, from prepaid credit with no subscription. Point SillyTavern, Janitor AI or the OpenAI SDK at that base URL with your key and this model id.
Both are uncensored Kimi builds on the same key. Kimi K3 Uncensored is $5.745 / $28.68 per million tokens in / out with a 262,144-token context window; Kimi K3.1 Pro Uncensored is $1.164 / $5.82 per million tokens in / out with a 1,048,576-token context window. The catalog lists image input for kimi-k3-uncensored only. A tool switches between them by model id. See Kimi K3.1 Pro Uncensored.
The stock Kimi K3 refuses some prompts, as Moonshot AI ships it. Kimi K3 Uncensored is the build changed to answer instead, served as kimi-k3-uncensored. The daily real-model check records whether the model answering it is unchanged. See the daily check.
The stock Kimi K2 line refuses some prompts too. Kimi K2.6 Uncensored is the K2 line served without a filter on the same key, as kimi-k2.6-uncensored at $1.17 / $7.34 per million tokens in / out; Kimi K3 Uncensored is the K3 flagship at $5.745 / $28.68 per million tokens in / out. See Kimi K2.6 Uncensored.
Your prompts go to Unrestrictable's own routes and are billed per token on a prepaid balance; nothing is sent to Moonshot AI. The model answers prompts the stock build declines, so what you do with it is covered by the acceptable-use terms: nothing involving minors and no real person's likeness without consent. See acceptable use.
Kimi K3 is Moonshot AI's 2.8T-parameter open-weight flagship with 104B active parameters and a one-million-token context window, released under the Kimi K3 License (moonshotai/Kimi-K3 card, read 2026-10-26). Kimi K3 Uncensored is that model served without a content filter, as kimi-k3-uncensored at $5.745 / $28.68 per million tokens in / out.
Neither: it is prepaid credit from $10, billed per token, with no monthly fee. One reply of 300 tokens on 4,000 tokens of context costs about $0.0316 at the live price, and 100 such replies $3.1584.
The stock Kimi K3 is open weights (2.8T total, 104B active, Kimi K3 License on moonshotai/Kimi-K3, read 2026-10-26), and community uncensored conversions are published on Hugging Face at the same size. Sending kimi-k3-uncensored to https://api.unrestrictable.ai/v1 needs no download and no GPU: 100 replies cost $3.1584 at the live price.
$2.583 for 100 chat turns of 2,000 input and 500 output tokens each, at $5.745 input and $28.68 output per million tokens, from prepaid credit with no subscription.
Yes, with the settings above: Chat Completion with a Custom (OpenAI-compatible) source and https://api.unrestrictable.ai/v1 as the endpoint in SillyTavern; the proxy URL https://api.unrestrictable.ai/v1/chat/completions and kimi-k3-uncensored as the model in Janitor AI. See the SillyTavern guide.