Takardun API

Kayayyakin more rayuwa na Hankali Ba Tare Da Tacewa Ba

API na AI mara tacewa: models na Shannon ba tare da ƙin amsa ba kuma ba tare da filters ba, ana yi musu hidima daga GPUs ɗinmu. Yana jituwa da OpenAI da Anthropic — ku saka SDK da kuke amfani da shi tuni, maɓalli ɗaya, streaming, tool calling da reasoning a kowane endpoint.

22 models marasa tacewa
256K context window
daga $0.50/1M
3 APIs masu jituwa
3 hanyoyin sadarwa: TLS, Tor, I2P

Fara gini Gwada filin wasa

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 & farashi KOWACE 1M TOKENS

Iyakoki, ids da yadda ake ƙirƙirar farashi

Hosted open-weight models context na tokens 262,144 a kowane id; ana lissafin input da output daban; kowane id yana karɓar abin da model ɗin da yake kwaikwaya yake karɓa

DeepSeek-V4-Pro-0813 3BIT-REAP

DeepSeek · 1.6T MoE · 49B active

Mara tacewa

Model mai girman flagship don zurfafan reasoning da dogon output.

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

Context
256K

Input
Rubutu a input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Adana prompt
- Streaming
In / cached / out kowace 1M

$1.95 / $0.488 / $3.90

Ƙari
GLM-5.2 3BIT-REAP

Z.ai · 744B MoE · 40B active

Mara tacewa

Ƙaƙƙarfan model na gama-gari mai arzikin output cikin harsuna da yawa.

Model id GLM-5.2-3BIT-REAP

Context
256K

Input
Rubutu a input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Adana prompt
- Streaming
In / cached / out kowace 1M

$0.73 / $0.183 / $2.34

Ƙari
Kimi-K3 3BIT-REAP

Moonshot AI · 2.8T MoE · 104B active

Mara tacewa

Model mai inganci sosai da aka gyara don cikakkun amsoshi masu cikakken bayani.

Model id Kimi-K3-3BIT-REAP

Context
256K

Input
Rubutu + hoto a input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Adana prompt
- Streaming
In / cached / out kowace 1M

$3.83 / $0.958 / $19.12

Ƙari
Nemotron3Ultra 3BIT-REAP

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

Mara tacewa

Babban model mai inganci da reasoning mai ƙarfi ga kowane dala.

Model id Nemotron3Ultra-3BIT-REAP

Context
256K

Input
Rubutu a input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Adana prompt
- Streaming
In / cached / out kowace 1M

$0.75 / $0.188 / $3.30

Ƙari
MiniMax-M3 3BIT-REAP

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

Mara tacewa

Model mai sauri, mara tsada don ayyuka masu yawa.

Model id MiniMax-M3-3BIT-REAP

Context
256K

Input
Rubutu + hoto a input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Adana prompt
- Streaming
In / cached / out kowace 1M

$0.50 / $0.125 / $2.00

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

DeepSeek · 284B MoE · 13B active

Mara tacewa

Model mai sauri na DeepSeek da ke daidaita gudu da inganci.

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

Context
256K

Input
Rubutu a input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Adana prompt
- Streaming
In / cached / out kowace 1M

$0.50 / $0.125 / $2.00

Ƙari
Kimi-K2.6 W4A16-AUTOROUND-REAP

Moonshot AI · 1T MoE · 32B active

Mara tacewa

Model mai iyawa don reasoning da rubuta daftari na yau da kullun.

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

Context
256K

Input
Rubutu + hoto a input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Adana prompt
- Streaming
In / cached / out kowace 1M

$0.78 / $0.195 / $3.67

Ƙari
Laguna-S-2.1 W4A16-AUTOROUND-REAP

Poolside · 118B MoE · 8B active

Mara tacewa

Model mai ƙarancin tsada ƙwarai don ayyuka marasa nauyi.

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

Context
256K

Input
Rubutu a input

Structured output
Babu structured output
- Tools
- Reasoning
- Reasoning effort
- Adana prompt
- Streaming
In / cached / out kowace 1M

$0.50 / $0.125 / $2.00

Ƙari
inkling W4A16-AUTOROUND-REAP

Thinking Machines · 975B MoE · 41B active

Mara tacewa

Model mai ƙirƙira mai salon rubutu na musamman.

Model id inkling-W4A16-AUTOROUND-REAP

Context
256K

Input
Rubutu + hoto a input

Structured output
JSON object
- Tools
- Reasoning
- Reasoning effort
- Adana prompt
- Streaming
In / cached / out kowace 1M

$1.42 / $0.355 / $6.07

Ƙari
MiMo-V2.5-Pro W8A16

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

Mara tacewa

Ƙaramin pro model don output mai tsari da daidaito.

Model id MiMo-V2.5-Pro-W8A16

Context
256K

Input
Rubutu a input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Adana prompt
- Streaming
In / cached / out kowace 1M

$0.50 / $0.125 / $2.00

Ƙari
MiMo-V2.5 W8A16

Xiaomi · 8-bit multimodal · W8A16

Mara tacewa

Ƙaramin model mai sauri don ayyuka masu sauƙi a mafi ƙarancin tsada.

Model id MiMo-V2.5-W8A16

Context
256K

Input
Rubutu + hoto a input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Adana prompt
- Streaming
In / cached / out kowace 1M

$0.50 / $0.125 / $2.00

Ƙari
Hy3 W8A16

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

Mara tacewa

Model na tsada kaɗan don gajerun amsoshin taɗi.

Model id Hy3-W8A16

Context
256K

Input
Rubutu a input

Structured output
JSON schema
- Tools
- Reasoning
- Reasoning effort
- Adana prompt
- Streaming
In / cached / out kowace 1M

$0.50 / $0.125 / $2.00

Ƙari

Models na Shannon farashi tsayayye ɗaya don input da output

Shannon 1.6 Lite

Mara tacewa

Amsoshi masu sauri, masu inganci don ayyukan yau da kullun

Model id shannon-1.6-lite

Context
192K

Input
Rubutu + hoto a input

Structured output
JSON schema
- Tools
- Binciken yanar gizo
- Streaming
Farashi / 1M tokens

$3.90
Shannon 1.6 Pro

Mara tacewa

Babban dalili don matsaloli masu rikitarwa

Model id shannon-1.6-pro

Context
192K

Input
Rubutu + hoto a input

Structured output
JSON schema
- Tools
- Reasoning
- Binciken yanar gizo
- Streaming
Farashi / 1M tokens

$7.80
Shannon 2 Lite

Mara tacewa

Shannon 2 Lite: pipeline mai sauri na tunani-rubutu-bita tare da reasoning trace da ake gani. Taɗin yau da kullun, taƙaitawa da Q&A.

Model id shannon-2-lite

Context
192K

Input
Rubutu + hoto a input

Structured output
JSON schema
- Tools
- Reasoning
- Binciken yanar gizo
- Streaming
Farashi / 1M tokens

$3.90
Shannon 2 Pro

Mara tacewa

Shannon 2 Pro: zurfafan matakai na tunani-rubutu-bita don nazari, dogon rubutu da reasoning mai matakai da yawa.

Model id shannon-2-pro

Context
192K

Input
Rubutu + hoto a input

Structured output
JSON schema
- Tools
- Reasoning
- Binciken yanar gizo
- Streaming
Farashi / 1M tokens

$5.85
Shannon 3

Mara tacewa

Model na Shannon na sabon ƙarni mai saurin reasoning a ƙaramin farashi tsayayye.

Model id shannon-3

Context
192K

Input
Rubutu + hoto a input

Structured output
JSON schema
- Tools
- Reasoning
- Binciken yanar gizo
- Streaming
Farashi / 1M tokens

$3.35
Shannon 3 Pro

Mara tacewa

Mataki na Shannon 3 mai ƙarin iyawa don aiki mai sarƙaƙiya da matakai da yawa.

Model id shannon-3-pro

Context
192K

Input
Rubutu + hoto a input

Structured output
JSON schema
- Tools
- Reasoning
- Binciken yanar gizo
- Streaming
Farashi / 1M tokens

$3.35
Shannon 3.1

Mara tacewa

Shannon 3 a kan kayan aikinmu, yana yin streaming da cikakken gudu ba tare da rate gate ba.

Model id shannon-3.1

Context
192K

Input
Rubutu + hoto a input

Structured output
JSON schema
- Tools
- Reasoning
- Binciken yanar gizo
- Streaming
Farashi / 1M tokens

$3.35

Ƙari
Shannon 3.1 Pro

Mara tacewa

Zurfafan reasoning da cikakken gudu tare da binciken baya-baya don tambayoyi masu wahala.

Model id shannon-3.1-pro

Context
192K

Input
Rubutu + hoto a input

Structured output
JSON schema
- Tools
- Reasoning
- Binciken yanar gizo
- Streaming
Farashi / 1M tokens

$3.35

Ƙari
Shannon 3.5

Mara tacewa

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

Model id shannon-3.5

Context
192K

Input
Rubutu + hoto a input

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

$3.35

Ƙari
Shannon Coder 1

Mara tacewa

Ƙwararre a code da tools: gyaran agentic, dogayen fayiloli, da tsayayyun tool loops.

Model id shannon-coder-1

Context
128K

Input
Rubutu a input

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

$8.00

Bincika docs

Ana iya isa ta Tor da I2P Onion service, I2P eepsite da madubin TLS mai ɓoyewa. Hanyoyin /v1 iri ɗaya, maɓalli ɗaya, streaming yana ciki; babu cookies, babu JavaScript, babu requests na wasu kamfanoni. Endpoints na Tor & I2P

Shirye don Gina?

Kowane asusu yana da free tier. Maɓallinku yana nesa da danna ɗaya kawai.

Samu Maɓallin API ɗinku Duba Farashi

Kayayyakin more rayuwa na Hankali Ba Tare Da Tacewa Ba

Models & farashi KOWACE 1M TOKENS

Hosted open-weight models context na tokens 262,144 a kowane id; ana lissafin input da output daban; kowane id yana karɓar abin da model ɗin da yake kwaikwaya yake karɓa

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`

Models na Shannon farashi tsayayye ɗaya don input da 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

Bincika docs

Shirye don Gina?

Models & farashi KOWACE 1M TOKENS

Hosted open-weight models context na tokens 262,144 a kowane id; ana lissafin input da output daban; kowane id yana karɓar abin da model ɗin da yake kwaikwaya yake karɓa

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

Models na Shannon farashi tsayayye ɗaya don input da 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

Bincika docs

Shirye don Gina?

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`