Ditokomane tsa API

Motheo oa Bohlale bo se nang Censorship

API ea AI e se nang censorship: li-model tsa Shannon tse se nang liphatlalatso le li-filter, tse sebeletsoang ho tsoa ho li-GPU tsa rona. E lumellana le OpenAI le Anthropic — sebelisa SDK eo u e sebelisang kaofela, senotlolo se le seng, streaming, tool calling le reasoning ho endpoint e 'ngoe le e 'ngoe.

22 li-model tse se nang censorship
256K fensetere ea context
ho tloha $0.50/1M
3 li-API tse lumellanang
3 marang-rang: TLS, Tor, I2P

Qala ho aha Leka 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
  }'

Li-model le litheko KA 1M TOKENS

Meeli, li-id le hore litheko li thehoa joang

Li-model tse hosted tsa open-weight context ea tokens tse 262,144 ho id e 'ngoe le e 'ngoe; input le output li ntšetsoa chelete ka thoko; id e 'ngoe le e 'ngoe e amohela se amohelang model eo e e etselitsoeng

DeepSeek-V4-Pro-0813 3BIT-REAP

DeepSeek · 1.6T MoE · 49B active

Ha e na censorship

Model ea boholo ba flagship bakeng sa reasoning e tebileng le output e telele.

Id ea model DeepSeek-V4-Pro-0813-3BIT-REAP

Context
256K

Input
Mongolo ho kena

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

$1.95 / $0.488 / $3.90

Tse ling
GLM-5.2 3BIT-REAP

Z.ai · 744B MoE · 40B active

Ha e na censorship

Model e matla ea kakaretso e nang le output e ngata ea lipuo tse ngata.

Id ea model GLM-5.2-3BIT-REAP

Context
256K

Input
Mongolo ho kena

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

$0.73 / $0.183 / $2.34

Tse ling
Kimi-K3 3BIT-REAP

Moonshot AI · 2.8T MoE · 104B active

Ha e na censorship

Model ea boemo bo phahameng e lokiselitsoeng likarabo tse felletseng, tse nang le lintlha.

Id ea model Kimi-K3-3BIT-REAP

Context
256K

Input
Mongolo + setšoantšo ho kena

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

$3.83 / $0.958 / $19.12

Tse ling
Nemotron3Ultra 3BIT-REAP

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

Ha e na censorship

Model e kholo e sebetsang hantle e nang le reasoning e matla ka dolara e 'ngoe le e 'ngoe.

Id ea model Nemotron3Ultra-3BIT-REAP

Context
256K

Input
Mongolo ho kena

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

$0.75 / $0.188 / $3.30

Tse ling
MiniMax-M3 3BIT-REAP

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

Ha e na censorship

Model e potlakileng, ea theko e tlase bakeng sa mosebetsi o moholo.

Id ea model MiniMax-M3-3BIT-REAP

Context
256K

Input
Mongolo + setšoantšo ho kena

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

$0.50 / $0.125 / $2.00

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

DeepSeek · 284B MoE · 13B active

Ha e na censorship

Model e potlakileng ea DeepSeek e leka-lekanyang lebelo le boleng.

Id ea model DeepSeek-V4-Flash-0731-W4A16-AUTOROUND-REAP

Context
256K

Input
Mongolo ho kena

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

$0.50 / $0.125 / $2.00

Tse ling
Kimi-K2.6 W4A16-AUTOROUND-REAP

Moonshot AI · 1T MoE · 32B active

Ha e na censorship

Model e nang le bokhoni bakeng sa reasoning ea letsatsi le letsatsi le ho ngola li-draft.

Id ea model Kimi-K2.6-W4A16-AUTOROUND-REAP

Context
256K

Input
Mongolo + setšoantšo ho kena

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

$0.78 / $0.195 / $3.67

Tse ling
Laguna-S-2.1 W4A16-AUTOROUND-REAP

Poolside · 118B MoE · 8B active

Ha e na censorship

Model ea theko e tlase haholo bakeng sa mesebetsi e bobebe.

Id ea model Laguna-S-2.1-W4A16-AUTOROUND-REAP

Context
256K

Input
Mongolo ho kena

Structured output
Ha ho structured output
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out ka 1M

$0.50 / $0.125 / $2.00

Tse ling
inkling W4A16-AUTOROUND-REAP

Thinking Machines · 975B MoE · 41B active

Ha e na censorship

Model ea boqapi e nang le lentsoe le ikhethang la ho ngola.

Id ea model inkling-W4A16-AUTOROUND-REAP

Context
256K

Input
Mongolo + setšoantšo ho kena

Structured output
Ntho ea JSON
- Tools
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out ka 1M

$1.42 / $0.355 / $6.07

Tse ling
MiMo-V2.5-Pro W8A16

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

Ha e na censorship

Model e kopaneng ea pro bakeng sa output e hlophisitsoeng, e nepahetseng.

Id ea model MiMo-V2.5-Pro-W8A16

Context
256K

Input
Mongolo ho kena

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

$0.50 / $0.125 / $2.00

Tse ling
MiMo-V2.5 W8A16

Xiaomi · 8-bit multimodal · W8A16

Ha e na censorship

Model e nyane, e potlakileng bakeng sa mesebetsi e bonolo ka theko e nyane.

Id ea model MiMo-V2.5-W8A16

Context
256K

Input
Mongolo + setšoantšo ho kena

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

$0.50 / $0.125 / $2.00

Tse ling
Hy3 W8A16

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

Ha e na censorship

Model ea theko e tlase bakeng sa likarabo tse khutšoanyane tsa moqoqo.

Id ea model Hy3-W8A16

Context
256K

Input
Mongolo ho kena

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

$0.50 / $0.125 / $2.00

Tse ling

Li-model tsa Shannon theko e le 'ngoe e sa fetoheng bakeng sa input le output

Shannon 1.6 Lite

Ha e na censorship

Dikarabo tse potlakileng le tse sebetsang bakeng sa mesebetsi ya letsatsi le letsatsi

Id ea model shannon-1.6-lite

Context
192K

Input
Mongolo + setšoantšo ho kena

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

$3.90
Shannon 1.6 Pro

Ha e na censorship

Reasoning e phahameng bakeng sa mathata a rarahaneng

Id ea model shannon-1.6-pro

Context
192K

Input
Mongolo + setšoantšo ho kena

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

$7.80
Shannon 2 Lite

Ha e na censorship

Shannon 2 Lite: pipeline e potlakileng ea nahana-ngola-hlahloba e nang le reasoning trace e bonahalang. Chat ea letsatsi le letsatsi, likakaretso le Q&A.

Id ea model shannon-2-lite

Context
192K

Input
Mongolo + setšoantšo ho kena

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

$3.90
Shannon 2 Pro

Ha e na censorship

Shannon 2 Pro: mekhahlelo e tebileng ea nahana-ngola-hlahloba bakeng sa tlhahlobo, ho ngola mongolo o molelele le reasoning ea mehato e mengata.

Id ea model shannon-2-pro

Context
192K

Input
Mongolo + setšoantšo ho kena

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

$5.85
Shannon 3

Ha e na censorship

Model ea moloko oa morao-rao oa Shannon e nang le reasoning e potlakileng ka theko e tlase e sa fetoheng.

Id ea model shannon-3

Context
192K

Input
Mongolo + setšoantšo ho kena

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

$3.35
Shannon 3 Pro

Ha e na censorship

Tier ea Shannon 3 e nang le bokhoni bo phahameng bakeng sa mosebetsi o rarahaneng oa mehato e mengata.

Id ea model shannon-3-pro

Context
192K

Input
Mongolo + setšoantšo ho kena

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

$3.35
Shannon 3.1

Ha e na censorship

Shannon 3 ho hardware ea rona, e nang le streaming ka lebelo le felletseng ntle le meeli ea rate.

Id ea model shannon-3.1

Context
192K

Input
Mongolo + setšoantšo ho kena

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

$3.35

Tse ling
Shannon 3.1 Pro

Ha e na censorship

Reasoning e tebileng ka lebelo le felletseng e nang le mohato oa lipatlisiso ka morao-rao bakeng sa lipotso tse thata.

Id ea model shannon-3.1-pro

Context
192K

Input
Mongolo + setšoantšo ho kena

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

$3.35

Tse ling
Shannon 3.5

Ha e na censorship

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

Id ea model shannon-3.5

Context
192K

Input
Mongolo + setšoantšo ho kena

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

$3.35

Tse ling
Shannon Coder 1

Ha e na censorship

Setsebi sa code le lisebelisoa: ho fetola code ka agent, lifaele tse telele, le li-loop tse tiileng tsa tool.

Id ea model shannon-coder-1

Context
128K

Input
Mongolo ho kena

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

$8.00

Pheta-pheta litokomane

E fumaneha ka Tor le I2P Onion service, I2P eepsite le mirror e ngotsoeng ea TLS. Litsela tse tšoanang tsa /v1, senotlolo se tšoanang, streaming e kenyelelitsoe; ha ho li-cookie, ha ho JavaScript, ha ho likopo tsa batho ba bang. Li-endpoint tsa Tor le I2P

O lokile ho aha?

Tier ea mahala e kenyelletsoa ho akhaonte e 'ngoe le e 'ngoe. Senotlolo sa hau se hole ka click e le 'ngoe.

Etsa senotlolo sa API Sheba ditokomane

Motheo oa Bohlale bo se nang Censorship

Li-model le litheko KA 1M TOKENS

Li-model tse hosted tsa open-weight context ea tokens tse 262,144 ho id e 'ngoe le e 'ngoe; input le output li ntšetsoa chelete ka thoko; id e 'ngoe le e 'ngoe e amohela se amohelang model eo e e etselitsoeng

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`

Li-model tsa Shannon theko e le 'ngoe e sa fetoheng bakeng sa input le 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

Pheta-pheta litokomane

O lokile ho aha?

Li-model le litheko KA 1M TOKENS

Li-model tse hosted tsa open-weight context ea tokens tse 262,144 ho id e 'ngoe le e 'ngoe; input le output li ntšetsoa chelete ka thoko; id e 'ngoe le e 'ngoe e amohela se amohelang model eo e e etselitsoeng

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

Li-model tsa Shannon theko e le 'ngoe e sa fetoheng bakeng sa input le 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

Pheta-pheta litokomane

O lokile ho aha?

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`