API Documentation

The Infrastructure of Uncensored Intelligence

The uncensored AI API: Shannon models with no refusals and no filters, served from our own GPUs. OpenAI- and Anthropic-compatible — drop in the SDK you already use, one key, streaming, tool calling and reasoning on every endpoint.

22 uncensored models
256K context window
from $0.50/1M
3 compatible APIs
3 networks: TLS, Tor, I2P

Start building Try 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
  }'

Models & pricing PER 1M TOKENS

Limits, ids and how prices are formed

Hosted open-weight models 262,144-token context on every id; input and output billed separately; each id accepts what the model it imitates accepts

DeepSeek-V4-Pro-0813 3BIT-REAP

DeepSeek · 1.6T MoE · 49B active

Uncensored

Flagship-scale model for deep reasoning and long-form output.

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

Context
256K

Input
Text in

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

$1.95 / $0.488 / $3.90

More
GLM-5.2 3BIT-REAP

Z.ai · 744B MoE · 40B active

Uncensored

Strong generalist model with rich multilingual output.

Model id GLM-5.2-3BIT-REAP

Context
256K

Input
Text in

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

$0.73 / $0.183 / $2.34

More
Kimi-K3 3BIT-REAP

Moonshot AI · 2.8T MoE · 104B active

Uncensored

High-end model tuned for thorough, detailed responses.

Model id Kimi-K3-3BIT-REAP

Context
256K

Input
Text + image in

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

$3.83 / $0.958 / $19.12

More
Nemotron3Ultra 3BIT-REAP

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

Uncensored

Efficient large model with strong reasoning per dollar.

Model id Nemotron3Ultra-3BIT-REAP

Context
256K

Input
Text in

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

$0.75 / $0.188 / $3.30

More
MiniMax-M3 3BIT-REAP

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

Uncensored

Fast, low-cost model for high-volume workloads.

Model id MiniMax-M3-3BIT-REAP

Context
256K

Input
Text + image in

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

$0.50 / $0.125 / $2.00

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

DeepSeek · 284B MoE · 13B active

Uncensored

Quick DeepSeek model balancing speed and quality.

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

Context
256K

Input
Text in

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

$0.50 / $0.125 / $2.00

More
Kimi-K2.6 W4A16-AUTOROUND-REAP

Moonshot AI · 1T MoE · 32B active

Uncensored

Capable model for everyday reasoning and drafting.

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

Context
256K

Input
Text + image in

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

$0.78 / $0.195 / $3.67

More
Laguna-S-2.1 W4A16-AUTOROUND-REAP

Poolside · 118B MoE · 8B active

Uncensored

Ultra-low-cost model for lightweight tasks.

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

Context
256K

Input
Text in

Structured output
No structured output
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out per 1M

$0.50 / $0.125 / $2.00

More
inkling W4A16-AUTOROUND-REAP

Thinking Machines · 975B MoE · 41B active

Uncensored

Creative model with a distinctive writing voice.

Model id inkling-W4A16-AUTOROUND-REAP

Context
256K

Input
Text + image in

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

$1.42 / $0.355 / $6.07

More
MiMo-V2.5-Pro W8A16

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

Uncensored

Compact pro model for structured, precise output.

Model id MiMo-V2.5-Pro-W8A16

Context
256K

Input
Text in

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

$0.50 / $0.125 / $2.00

More
MiMo-V2.5 W8A16

Xiaomi · 8-bit multimodal · W8A16

Uncensored

Small, snappy model for simple tasks at minimal cost.

Model id MiMo-V2.5-W8A16

Context
256K

Input
Text + image in

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

$0.50 / $0.125 / $2.00

More
Hy3 W8A16

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

Uncensored

Budget model for concise conversational replies.

Model id Hy3-W8A16

Context
256K

Input
Text in

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

$0.50 / $0.125 / $2.00

More

Shannon models one flat rate for input and output

Shannon 1.6 Lite

Uncensored

Fast, efficient responses for everyday tasks

Model id shannon-1.6-lite

Context
192K

Input
Text + image in

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

$3.90
Shannon 1.6 Pro

Uncensored

Advanced reasoning for complex problems

Model id shannon-1.6-pro

Context
192K

Input
Text + image in

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

$7.80
Shannon 2 Lite

Uncensored

Shannon 2 Lite: fast think-draft-review pipeline with a visible reasoning trace. Everyday chat, summaries and Q&A.

Model id shannon-2-lite

Context
192K

Input
Text + image in

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

$3.90
Shannon 2 Pro

Uncensored

Shannon 2 Pro: deeper think-draft-review passes for analysis, long-form writing and multi-step reasoning.

Model id shannon-2-pro

Context
192K

Input
Text + image in

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

$5.85
Shannon 3

Uncensored

Latest-generation Shannon model with fast reasoning at a low flat price.

Model id shannon-3

Context
192K

Input
Text + image in

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

$3.35
Shannon 3 Pro

Uncensored

Higher-capability Shannon 3 tier for complex, multi-step work.

Model id shannon-3-pro

Context
192K

Input
Text + image in

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

$3.35
Shannon 3.1

Uncensored

Shannon 3 on our own hardware, streaming at full speed with no rate gate.

Model id shannon-3.1

Context
192K

Input
Text + image in

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

$3.35

More
Shannon 3.1 Pro

Uncensored

Full-speed deep reasoning with a background research pass for hard questions.

Model id shannon-3.1-pro

Context
192K

Input
Text + image in

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

$3.35

More
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 in

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

$3.35

More
Shannon Coder 1

Uncensored

Code-and-tools specialist: agentic editing, long files, and strict tool loops.

Model id shannon-coder-1

Context
128K

Input
Text in

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

$8.00

Browse the docs

Reachable over Tor and I2P Onion service, I2P eepsite and an encrypted TLS mirror. Same /v1 routes, same key, streaming included; no cookies, no JavaScript, no third-party requests. Tor & I2P endpoints

Ready to Build?

Free tier included with every account. Your key is one click away.

Get Your API Key View Pricing

The Infrastructure of Uncensored Intelligence

Models & pricing PER 1M TOKENS

Hosted open-weight models 262,144-token context on every id; input and output billed separately; each id accepts what the model it imitates accepts

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`

Shannon models one flat rate for input and 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

Browse the docs

Ready to Build?

Models & pricing PER 1M TOKENS

Hosted open-weight models 262,144-token context on every id; input and output billed separately; each id accepts what the model it imitates accepts

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

Shannon models one flat rate for input and 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

Browse the docs

Ready to Build?

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`