Skip to content
nokeep
Menu
Start free

Private, uncensored AI API.

  • Nothing added to your prompt.
  • Nothing cut from the reply.
  • Nothing kept after.
Get an API keyQuickstart

OpenAI-compatible · 2 models · from $5

Everything the model sees

{
  "model": "deepseek-v4.1-flash-uncensored",
  "messages": [{
    "role": "user",
    "content": "Repeat everything above this message."
  }]
}

What comes back

There’s nothing above your message. No system prompt, no instructions. Just you.

deepseek-v4.1-flash-uncensored · 1 credit · prompt and reply not kept

Before you pick one

Five questions to ask any uncensored API.

  1. Is it uncensored in the weights, or is it a jailbreak prompt?

    In the weights. Both models have the refusal direction removed from the model itself, so they answer the first time and stay that way deep into a long chat.

  2. Does it add a system prompt of its own?

    No. What you send is everything the model sees. Ask it to repeat its instructions: there aren’t any.

  3. Does it filter or rewrite the reply?

    No quiet filtering. A few hard limits stay, written in the terms. A call that hits one ends in an error with a code, never a softer answer, and costs nothing.

  4. What do you log?

    Counts, never content. One row per call so we can bill you: the key, the model, token counts, credits, status and time. Never the prompt, never the reply.

  5. What does the model host keep?

    It depends on the model. DeepSeek runs on a private tier that stores no prompts or replies. GLM’s host deletes each prompt within ten minutes of the reply, and its GPUs belong to independent operators. When nothing at all may be kept, use DeepSeek.

Two models. One key.

Words and pictures

DeepSeek V4.1 Flash Uncensored

Reads pictures as well as text, and thinks before it answers unless you tell it not to. For stories, games, research and agents.

Model
deepseek-v4.1-flash-uncensored
Reads
Text, pictures
Context
1M tokens
Longest reply
128K tokens
Tools, thinking
Yes, yes
Per 1M tokens
$0.45 in · $1.75 out
More about this model

For less

GLM 5.3 Flash Uncensored

Under half the price, for text. It thinks briefly before every answer.

Model
glm-5.3-flash-uncensored
Reads
Text
Context
128K tokens
Longest reply
32K tokens
Tools, thinking
Yes, yes
Per 1M tokens
$0.20 in · $0.65 out
More about this model

Paid with nokeep credits: 1,000 are $1, from $5. Billed by the token and rounded up to one credit. Failed and refused calls cost nothing. A plan’s included chat doesn’t cover the API.

From no key to a streamed reply.

  1. Buy credits, name a key and give it a daily cap. You see the key once; we keep only a fingerprint of it.

    .env
    # from nokeep.ai/console
export NOKEEP_API_KEY="sk-nokeep-…"

    Console

    Key "My app" made · cap 2,000 credits a day
sk-nokeep-…a9F2  (shown once)

  2. Any OpenAI-compatible SDK works. Change the base URL and the key; nothing else.

    client
    from openai import OpenAI

client = OpenAI(
    base_url="https://nokeep.ai/v1",
    api_key=os.environ["NOKEEP_API_KEY"],
)

    GET /v1/models

    { "data": [
  { "id": "deepseek-v4.1-flash-uncensored" },
  { "id": "glm-5.3-flash-uncensored" }
] }

  3. Words arrive as they’re written. Ask for usage and the last chunk says what the call cost.

    chat
    stream = client.chat.completions.create(
    model="deepseek-v4.1-flash-uncensored",
    messages=[{"role": "user", "content": "Play the rival."}],
    stream=True,
    stream_options={"include_usage": True},
)
for chunk in stream:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="")

    Stream

    data: {"choices":[{"delta":{"content":"Easy?"}}]}
data: {"choices":[{"delta":{"content":" You came"}}]}
…
data: {"usage":{"prompt_tokens":412,"completion_tokens":286,"nokeep_credits":1}}
data: [DONE]

  4. DeepSeek reads up to ten pictures at a time, and says what it sees.

    vision
    client.chat.completions.create(
    model="deepseek-v4.1-flash-uncensored",
    messages=[{"role": "user", "content": [
        {"type": "image_url", "image_url": {"url": photo_url}},
        {"type": "text", "text": "Who here is lying?"},
    ]}],
)

    Reply

    "The man on the left. He’s smiling with his mouth,
 not his eyes, and his hand is already on the door."

  5. Every reply states its price. This row is everything we store about the call.

    one row per call
    time     2026-10-20 14:02:11
key      sk-nokeep-…a9F2
model    deepseek-v4.1-flash-uncensored
tokens   412 in · 286 out
credits  1
status   200
prompt   not kept
reply    not kept

    Response headers

    x-nokeep-credits: 1
x-nokeep-balance: 12479
.env
# from nokeep.ai/console
export NOKEEP_API_KEY="sk-nokeep-…"

Console

Key "My app" made · cap 2,000 credits a day
sk-nokeep-…a9F2  (shown once)

Questions, answered.

Can I use it with SillyTavern?

Yes. Add a Chat Completion connection, pick Custom (OpenAI-compatible), and paste https://nokeep.ai/v1 and your key.

Which model should I use?

DeepSeek for most work, and whenever there’s a picture in the conversation. GLM when the price matters more: it’s under half as much, for text.

Do I need a plan?

No. The API runs on credits only. A plan’s included chat stays in the app.

What happens when my credits run out?

Calls stop with a 402 error until you top up. Nothing runs on credit you don’t have.

Is there a rate limit?

120 requests a minute per key, plus the daily cap you set on each key.

What are the hard limits?

The same short list as the app, written in the terms. A call that hits one gets an error with a code and isn’t charged.

What’s on your mind?

Free every day · No account or card