Dokumentasyon ng API

Ang Infrastructure ng Uncensored Intelligence

Ang uncensored AI API: mga Shannon model na walang pagtanggi at walang filter, na pinapatakbo sa sarili naming mga GPU. Compatible sa OpenAI at Anthropic — ipasok lang ang SDK na ginagamit mo na, isang key, streaming, tool calling at reasoning sa bawat endpoint.

22 uncensored na model
256K context window
mula sa $0.50/1M
3 compatible na API
3 network: TLS, Tor, I2P

Magsimulang bumuo Subukan ang Playground

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.shannon-ai.com/v1"
)

response = client.chat.completions.create(
    model="shannon-3",
    messages=[
        {"role": "user", "content": "Hello, Shannon!"}
    ],
    max_tokens=1024
)

print(response.choices[0].message.content)

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.shannon-ai.com/v1'
});

const response = await client.chat.completions.create({
  model: 'shannon-3',
  messages: [
    { role: 'user', content: 'Hello, Shannon!' }
  ],
  max_tokens: 1024
});

console.log(response.choices[0].message.content);

package main

import (
    "context"
    "fmt"
    openai "github.com/sashabaranov/go-openai"
)

func main() {
    config := openai.DefaultConfig("YOUR_API_KEY")
    config.BaseURL = "https://api.shannon-ai.com/v1"
    client := openai.NewClientWithConfig(config)

    resp, err := client.CreateChatCompletion(
        context.Background(),
        openai.ChatCompletionRequest{
            Model: "shannon-3",
            Messages: []openai.ChatCompletionMessage{
                {Role: "user", Content: "Hello, Shannon!"},
            },
            MaxTokens: 1024,
        },
    )
    if err != nil {
        panic(err)
    }
    fmt.Println(resp.Choices[0].Message.Content)
}

curl -X POST "https://api.shannon-ai.com/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "shannon-3",
    "messages": [
      {"role": "user", "content": "Hello, Shannon!"}
    ],
    "max_tokens": 1024
  }'

Mga model at presyo KADA 1M TOKENS

Mga limitasyon, ids at kung paano nabubuo ang mga presyo

Mga hosted open-weight model 262,144-token na context sa bawat id; hiwalay na sinisingil ang input at output; tinatanggap ng bawat id ang tinatanggap ng model na ginagaya nito

DeepSeek-V4-Pro-0813 3BIT-REAP

DeepSeek · 1.6T MoE · 49B active

Uncensored

Flagship-scale na model para sa malalim na reasoning at long-form na output.

Model id DeepSeek-V4-Pro-0813-3BIT-REAP

Context
256K

Input
Text na input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kada 1M

$1.95 / $0.488 / $3.90

Higit pa
GLM-5.2 3BIT-REAP

Z.ai · 744B MoE · 40B active

Uncensored

Malakas na generalist na model na may mayamang multilingual na output.

Model id GLM-5.2-3BIT-REAP

Context
256K

Input
Text na input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kada 1M

$0.73 / $0.183 / $2.34

Higit pa
Kimi-K3 3BIT-REAP

Moonshot AI · 2.8T MoE · 104B active

Uncensored

High-end na model na naka-tune para sa masusi at detalyadong mga sagot.

Model id Kimi-K3-3BIT-REAP

Context
256K

Input
Text + image na input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kada 1M

$3.83 / $0.958 / $19.12

Higit pa
Nemotron3Ultra 3BIT-REAP

NVIDIA · 550B hybrid Mamba-Attention MoE · 55B active

Uncensored

Episyenteng malaking model na may malakas na reasoning kada dolyar.

Model id Nemotron3Ultra-3BIT-REAP

Context
256K

Input
Text na input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kada 1M

$0.75 / $0.188 / $3.30

Higit pa
MiniMax-M3 3BIT-REAP

MiniMax · 428B MoE · 23B active · sparse attention

Uncensored

Mabilis at mura na model para sa mataas na dami ng workload.

Model id MiniMax-M3-3BIT-REAP

Context
256K

Input
Text + image na input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kada 1M

$0.50 / $0.125 / $2.00

Higit pa
DeepSeek-V4-Flash-0731 W4A16-AUTOROUND-REAP

DeepSeek · 284B MoE · 13B active

Uncensored

Mabilis na DeepSeek model na nagbabalanse ng bilis at kalidad.

Model id DeepSeek-V4-Flash-0731-W4A16-AUTOROUND-REAP

Context
256K

Input
Text na input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kada 1M

$0.50 / $0.125 / $2.00

Higit pa
Kimi-K2.6 W4A16-AUTOROUND-REAP

Moonshot AI · 1T MoE · 32B active

Uncensored

Mahusay na model para sa pang-araw-araw na reasoning at pag-draft.

Model id Kimi-K2.6-W4A16-AUTOROUND-REAP

Context
256K

Input
Text + image na input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kada 1M

$0.78 / $0.195 / $3.67

Higit pa
Laguna-S-2.1 W4A16-AUTOROUND-REAP

Poolside · 118B MoE · 8B active

Uncensored

Ultra-low-cost na model para sa magagaang gawain.

Model id Laguna-S-2.1-W4A16-AUTOROUND-REAP

Context
256K

Input
Text na input

Structured output
Walang structured output
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kada 1M

$0.50 / $0.125 / $2.00

Higit pa
inkling W4A16-AUTOROUND-REAP

Thinking Machines · 975B MoE · 41B active

Uncensored

Malikhaing model na may natatanging boses sa pagsusulat.

Model id inkling-W4A16-AUTOROUND-REAP

Context
256K

Input
Text + image na input

Structured output
JSON object
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kada 1M

$1.42 / $0.355 / $6.07

Higit pa
MiMo-V2.5-Pro W8A16

Xiaomi · 1.02T MoE · 42B active · 8-bit

Uncensored

Compact na pro model para sa structured at eksaktong output.

Model id MiMo-V2.5-Pro-W8A16

Context
256K

Input
Text na input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kada 1M

$0.50 / $0.125 / $2.00

Higit pa
MiMo-V2.5 W8A16

Xiaomi · 8-bit multimodal · W8A16

Uncensored

Maliit at mabilis na model para sa simpleng gawain sa pinakamababang halaga.

Model id MiMo-V2.5-W8A16

Context
256K

Input
Text + image na input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kada 1M

$0.50 / $0.125 / $2.00

Higit pa
Hy3 W8A16

Tencent · 295B MoE · 21B active · 8-bit

Uncensored

Budget na model para sa maikli at pakikipag-usap na mga sagot.

Model id Hy3-W8A16

Context
256K

Input
Text na input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out kada 1M

$0.50 / $0.125 / $2.00

Higit pa

Mga Shannon model isang flat na rate para sa input at output

Shannon 1.6 Lite

Uncensored

Mabilis at episyenteng mga sagot para sa pang-araw-araw na gawain

Model id shannon-1.6-lite

Context
192K

Input
Text + image na input

Structured output
JSON schema
- Tools
- Web search
- Streaming
Presyo / 1M tokens

$3.90
Shannon 1.6 Pro

Uncensored

Advanced na reasoning para sa kumplikadong problema

Model id shannon-1.6-pro

Context
192K

Input
Text + image na input

Structured output
JSON schema
- Tools
- Reasoning
- Web search
- Streaming
Presyo / 1M tokens

$7.80
Shannon 2 Lite

Uncensored

Shannon 2 Lite: mabilis na think-draft-review pipeline na may nakikitang reasoning trace. Pang-araw-araw na chat, buod at Q&A.

Model id shannon-2-lite

Context
192K

Input
Text + image na input

Structured output
JSON schema
- Tools
- Reasoning
- Web search
- Streaming
Presyo / 1M tokens

$3.90
Shannon 2 Pro

Uncensored

Shannon 2 Pro: mas malalim na think-draft-review passes para sa analysis, long-form na pagsusulat at multi-step reasoning.

Model id shannon-2-pro

Context
192K

Input
Text + image na input

Structured output
JSON schema
- Tools
- Reasoning
- Web search
- Streaming
Presyo / 1M tokens

$5.85
Shannon 3

Uncensored

Pinakabagong henerasyon ng Shannon model na may mabilis na reasoning sa mababang flat na presyo.

Model id shannon-3

Context
192K

Input
Text + image na input

Structured output
JSON schema
- Tools
- Reasoning
- Web search
- Streaming
Presyo / 1M tokens

$3.35
Shannon 3 Pro

Uncensored

Mas mataas na kakayahang tier ng Shannon 3 para sa kumplikado at multi-step na trabaho.

Model id shannon-3-pro

Context
192K

Input
Text + image na input

Structured output
JSON schema
- Tools
- Reasoning
- Web search
- Streaming
Presyo / 1M tokens

$3.35
Shannon 3.1

Uncensored

Shannon 3 sa sarili naming hardware, nag-i-stream nang buong bilis nang walang rate gate.

Model id shannon-3.1

Context
192K

Input
Text + image na input

Structured output
JSON schema
- Tools
- Reasoning
- Web search
- Streaming
Presyo / 1M tokens

$3.35

Higit pa
Shannon 3.1 Pro

Uncensored

Buong bilis na malalim na reasoning na may background research pass para sa mahihirap na tanong.

Model id shannon-3.1-pro

Context
192K

Input
Text + image na input

Structured output
JSON schema
- Tools
- Reasoning
- Web search
- Streaming
Presyo / 1M tokens

$3.35

Higit pa
Shannon 3.5

Uncensored

One streaming answer that thinks, searches, draws charts and diagrams and writes files inline.

Model id shannon-3.5

Context
192K

Input
Text + image na input

Structured output
JSON schema
- Tools
- Streaming
Presyo / 1M tokens

$3.35

Higit pa
Shannon Coder 1

Uncensored

Espesyalista sa code at tools: agentic editing, mahahabang file, at mahigpit na tool loops.

Model id shannon-coder-1

Context
128K

Input
Text na input

Structured output
JSON schema
- Tools
- Reasoning
- Streaming
Presyo / 1M tokens

$8.00

Mag-browse sa docs

Maaabot sa Tor at I2P Onion service, I2P eepsite at isang encrypted na TLS mirror. Parehong /v1 routes, parehong key, kasama ang streaming; walang cookies, walang JavaScript, walang third-party requests. Mga endpoint ng Tor at I2P

Handa nang bumuo?

May kasamang free tier ang bawat account. Isang click na lang ang iyong key.

Lumikha ng API key Tingnan ang docs

Ang Infrastructure ng Uncensored Intelligence

Mga model at presyo KADA 1M TOKENS

Mga hosted open-weight model 262,144-token na context sa bawat id; hiwalay na sinisingil ang input at output; tinatanggap ng bawat id ang tinatanggap ng model na ginagaya nito

DeepSeek-V4-Pro-0813 `3BIT-REAP`

GLM-5.2 `3BIT-REAP`

Kimi-K3 `3BIT-REAP`

Nemotron3Ultra `3BIT-REAP`

MiniMax-M3 `3BIT-REAP`

DeepSeek-V4-Flash-0731 `W4A16-AUTOROUND-REAP`

Kimi-K2.6 `W4A16-AUTOROUND-REAP`

Laguna-S-2.1 `W4A16-AUTOROUND-REAP`

inkling `W4A16-AUTOROUND-REAP`

MiMo-V2.5-Pro `W8A16`

MiMo-V2.5 `W8A16`

Hy3 `W8A16`

Mga Shannon model isang flat na rate para sa input at output

Shannon 1.6 Lite

Shannon 1.6 Pro

Shannon 2 Lite

Shannon 2 Pro

Shannon 3

Shannon 3 Pro

Shannon 3.1

Shannon 3.1 Pro

Shannon 3.5

Shannon Coder 1

Mag-browse sa docs

Handa nang bumuo?

Mga model at presyo KADA 1M TOKENS

Mga hosted open-weight model 262,144-token na context sa bawat id; hiwalay na sinisingil ang input at output; tinatanggap ng bawat id ang tinatanggap ng model na ginagaya nito

DeepSeek-V4-Pro-0813 3BIT-REAP

GLM-5.2 3BIT-REAP

Kimi-K3 3BIT-REAP

Nemotron3Ultra 3BIT-REAP

MiniMax-M3 3BIT-REAP

DeepSeek-V4-Flash-0731 W4A16-AUTOROUND-REAP

Kimi-K2.6 W4A16-AUTOROUND-REAP

Laguna-S-2.1 W4A16-AUTOROUND-REAP

inkling W4A16-AUTOROUND-REAP

MiMo-V2.5-Pro W8A16

MiMo-V2.5 W8A16

Hy3 W8A16

Mga Shannon model isang flat na rate para sa input at output

Shannon 1.6 Lite

Shannon 1.6 Pro

Shannon 2 Lite

Shannon 2 Pro

Shannon 3

Shannon 3 Pro

Shannon 3.1

Shannon 3.1 Pro

Shannon 3.5

Shannon Coder 1

Mag-browse sa docs

Handa nang bumuo?

DeepSeek-V4-Pro-0813 `3BIT-REAP`

GLM-5.2 `3BIT-REAP`

Kimi-K3 `3BIT-REAP`

Nemotron3Ultra `3BIT-REAP`

MiniMax-M3 `3BIT-REAP`

DeepSeek-V4-Flash-0731 `W4A16-AUTOROUND-REAP`

Kimi-K2.6 `W4A16-AUTOROUND-REAP`

Laguna-S-2.1 `W4A16-AUTOROUND-REAP`

inkling `W4A16-AUTOROUND-REAP`

MiMo-V2.5-Pro `W8A16`

MiMo-V2.5 `W8A16`

Hy3 `W8A16`