Imibhalo ye-API

Ingqalasizinda ye- Ubuhlakani Obungahlungiwe

I-API ye-AI engahlungiwe: ama-model e-Shannon angenazinqaba nasihlungi, asebenza kuma-GPU ethu. Ihambisana ne-OpenAI ne-Anthropic — faka i-SDK osevele uyisebenzisa, i-key eyodwa, i-streaming, ukubiza amathuluzi nokucabanga kuwo wonke ama-endpoint.

22 ama-model angahlungiwe
256K iwindi lomongo
kusuka ku- $0.50/1M
3 ama-API ahambisanayo
3 amanethiwekhi: TLS, Tor, I2P

Qala ukwakha Zama i-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
  }'

Ama-model namanani NGAMA-TOKEN AYI-1M

Imikhawulo, ama-id nendlela amanani akhiwa ngayo

Ama-model e-open-weight ahlinzekiwe umongo wama-token angu-262,144 kuyo yonke i-id; okufakwayo nokuphumayo kubiziswa ngokwehlukana; i-id ngayinye yamukela lokho i-model eyilingisayo eyamukelayo

DeepSeek-V4-Pro-0813 3BIT-REAP

DeepSeek · 1.6T MoE · 49B active

Akuhlungiwe

I-model yezinga eliphezulu yokucabanga okujulile nokuphumayo okude.

I-id ye-model DeepSeek-V4-Pro-0813-3BIT-REAP

Umongo
256K

Okufakwayo
Umbhalo okufakwayo

Okuphumayo okuhleliwe
I-JSON schema
- Amathuluzi
- Ukucabanga
- Umzamo wokucabanga
- I-prompt caching
- I-streaming
Ingene / ecashwe / iphume ngama 1M

$1.95 / $0.488 / $3.90

Okuningi
GLM-5.2 3BIT-REAP

Z.ai · 744B MoE · 40B active

Akuhlungiwe

I-model eyinhlobonhlobo eqinile enokuphumayo okucebile ngezilimi eziningi.

I-id ye-model GLM-5.2-3BIT-REAP

Umongo
256K

Okufakwayo
Umbhalo okufakwayo

Okuphumayo okuhleliwe
I-JSON schema
- Amathuluzi
- Ukucabanga
- Umzamo wokucabanga
- I-prompt caching
- I-streaming
Ingene / ecashwe / iphume ngama 1M

$0.73 / $0.183 / $2.34

Okuningi
Kimi-K3 3BIT-REAP

Moonshot AI · 2.8T MoE · 104B active

Akuhlungiwe

I-model ephezulu elungiselelwe izimpendulo ezijulile nezineminingwane.

I-id ye-model Kimi-K3-3BIT-REAP

Umongo
256K

Okufakwayo
Umbhalo + isithombe okufakwayo

Okuphumayo okuhleliwe
I-JSON schema
- Amathuluzi
- Ukucabanga
- Umzamo wokucabanga
- I-prompt caching
- I-streaming
Ingene / ecashwe / iphume ngama 1M

$3.83 / $0.958 / $19.12

Okuningi
Nemotron3Ultra 3BIT-REAP

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

Akuhlungiwe

I-model enkulu esebenza kahle enokucabanga okuqinile ngedola ngalinye.

I-id ye-model Nemotron3Ultra-3BIT-REAP

Umongo
256K

Okufakwayo
Umbhalo okufakwayo

Okuphumayo okuhleliwe
I-JSON schema
- Amathuluzi
- Ukucabanga
- Umzamo wokucabanga
- I-prompt caching
- I-streaming
Ingene / ecashwe / iphume ngama 1M

$0.75 / $0.188 / $3.30

Okuningi
MiniMax-M3 3BIT-REAP

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

Akuhlungiwe

I-model esheshayo, ebiza kancane yemithwalo yomsebenzi emikhulu.

I-id ye-model MiniMax-M3-3BIT-REAP

Umongo
256K

Okufakwayo
Umbhalo + isithombe okufakwayo

Okuphumayo okuhleliwe
I-JSON schema
- Amathuluzi
- Ukucabanga
- Umzamo wokucabanga
- I-prompt caching
- I-streaming
Ingene / ecashwe / iphume ngama 1M

$0.50 / $0.125 / $2.00

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

DeepSeek · 284B MoE · 13B active

Akuhlungiwe

I-model ye-DeepSeek esheshayo elinganisa ijubane nezinga.

I-id ye-model DeepSeek-V4-Flash-0731-W4A16-AUTOROUND-REAP

Umongo
256K

Okufakwayo
Umbhalo okufakwayo

Okuphumayo okuhleliwe
I-JSON schema
- Amathuluzi
- Ukucabanga
- Umzamo wokucabanga
- I-prompt caching
- I-streaming
Ingene / ecashwe / iphume ngama 1M

$0.50 / $0.125 / $2.00

Okuningi
Kimi-K2.6 W4A16-AUTOROUND-REAP

Moonshot AI · 1T MoE · 32B active

Akuhlungiwe

I-model ekwaziyo yokucabanga nokubhala kwansuku zonke.

I-id ye-model Kimi-K2.6-W4A16-AUTOROUND-REAP

Umongo
256K

Okufakwayo
Umbhalo + isithombe okufakwayo

Okuphumayo okuhleliwe
I-JSON schema
- Amathuluzi
- Ukucabanga
- Umzamo wokucabanga
- I-prompt caching
- I-streaming
Ingene / ecashwe / iphume ngama 1M

$0.78 / $0.195 / $3.67

Okuningi
Laguna-S-2.1 W4A16-AUTOROUND-REAP

Poolside · 118B MoE · 8B active

Akuhlungiwe

I-model ebiza kakhulu kancane yemisebenzi elula.

I-id ye-model Laguna-S-2.1-W4A16-AUTOROUND-REAP

Umongo
256K

Okufakwayo
Umbhalo okufakwayo

Okuphumayo okuhleliwe
Akukho okuphumayo okuhleliwe
- Amathuluzi
- Ukucabanga
- Umzamo wokucabanga
- I-prompt caching
- I-streaming
Ingene / ecashwe / iphume ngama 1M

$0.50 / $0.125 / $2.00

Okuningi
inkling W4A16-AUTOROUND-REAP

Thinking Machines · 975B MoE · 41B active

Akuhlungiwe

I-model edala enezwi lokubhala elihlukile.

I-id ye-model inkling-W4A16-AUTOROUND-REAP

Umongo
256K

Okufakwayo
Umbhalo + isithombe okufakwayo

Okuphumayo okuhleliwe
Into ye-JSON
- Amathuluzi
- Ukucabanga
- Umzamo wokucabanga
- I-prompt caching
- I-streaming
Ingene / ecashwe / iphume ngama 1M

$1.42 / $0.355 / $6.07

Okuningi
MiMo-V2.5-Pro W8A16

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

Akuhlungiwe

I-model ye-pro ehlangene yokuphumayo okuhleliwe nokunembile.

I-id ye-model MiMo-V2.5-Pro-W8A16

Umongo
256K

Okufakwayo
Umbhalo okufakwayo

Okuphumayo okuhleliwe
I-JSON schema
- Amathuluzi
- Ukucabanga
- Umzamo wokucabanga
- I-prompt caching
- I-streaming
Ingene / ecashwe / iphume ngama 1M

$0.50 / $0.125 / $2.00

Okuningi
MiMo-V2.5 W8A16

Xiaomi · 8-bit multimodal · W8A16

Akuhlungiwe

I-model encane, esheshayo yemisebenzi elula ngezindleko ezincane kakhulu.

I-id ye-model MiMo-V2.5-W8A16

Umongo
256K

Okufakwayo
Umbhalo + isithombe okufakwayo

Okuphumayo okuhleliwe
I-JSON schema
- Amathuluzi
- Ukucabanga
- Umzamo wokucabanga
- I-prompt caching
- I-streaming
Ingene / ecashwe / iphume ngama 1M

$0.50 / $0.125 / $2.00

Okuningi
Hy3 W8A16

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

Akuhlungiwe

I-model engabizi yezimpendulo ezimfushane zengxoxo.

I-id ye-model Hy3-W8A16

Umongo
256K

Okufakwayo
Umbhalo okufakwayo

Okuphumayo okuhleliwe
I-JSON schema
- Amathuluzi
- Ukucabanga
- Umzamo wokucabanga
- I-prompt caching
- I-streaming
Ingene / ecashwe / iphume ngama 1M

$0.50 / $0.125 / $2.00

Okuningi

Ama-model e-Shannon izinga elilodwa lokufakwayo nokuphumayo

Shannon 1.6 Lite

Akuhlungiwe

Impendulo esheshayo nenempumelelo emisebenzini yansuku zonke

I-id ye-model shannon-1.6-lite

Umongo
192K

Okufakwayo
Umbhalo + isithombe okufakwayo

Okuphumayo okuhleliwe
I-JSON schema
- Amathuluzi
- Ukusesha kuwebhu
- I-streaming
Intengo / ama-token ayi-1M

$3.90
Shannon 1.6 Pro

Akuhlungiwe

Ukucabanga okujulile ezinkingeni eziyinkimbinkimbi

I-id ye-model shannon-1.6-pro

Umongo
192K

Okufakwayo
Umbhalo + isithombe okufakwayo

Okuphumayo okuhleliwe
I-JSON schema
- Amathuluzi
- Ukucabanga
- Ukusesha kuwebhu
- I-streaming
Intengo / ama-token ayi-1M

$7.80
Shannon 2 Lite

Akuhlungiwe

I-Shannon 2 Lite: i-pipeline esheshayo ye-think-draft-review enomkhondo wokucabanga obonakalayo. Ingxoxo yansuku zonke, amafushane ne-Q&A.

I-id ye-model shannon-2-lite

Umongo
192K

Okufakwayo
Umbhalo + isithombe okufakwayo

Okuphumayo okuhleliwe
I-JSON schema
- Amathuluzi
- Ukucabanga
- Ukusesha kuwebhu
- I-streaming
Intengo / ama-token ayi-1M

$3.90
Shannon 2 Pro

Akuhlungiwe

I-Shannon 2 Pro: izigaba ze-think-draft-review ezijulile zokuhlaziya, ukubhala okude nokucabanga kwezinyathelo eziningi.

I-id ye-model shannon-2-pro

Umongo
192K

Okufakwayo
Umbhalo + isithombe okufakwayo

Okuphumayo okuhleliwe
I-JSON schema
- Amathuluzi
- Ukucabanga
- Ukusesha kuwebhu
- I-streaming
Intengo / ama-token ayi-1M

$5.85
Shannon 3

Akuhlungiwe

I-model ye-Shannon yesizukulwane sakamuva enokucabanga okusheshayo ngentengo ephansi eyodwa.

I-id ye-model shannon-3

Umongo
192K

Okufakwayo
Umbhalo + isithombe okufakwayo

Okuphumayo okuhleliwe
I-JSON schema
- Amathuluzi
- Ukucabanga
- Ukusesha kuwebhu
- I-streaming
Intengo / ama-token ayi-1M

$3.35
Shannon 3 Pro

Akuhlungiwe

Izinga le-Shannon 3 elinamandla amaningi lomsebenzi oyinkimbinkimbi onezinyathelo eziningi.

I-id ye-model shannon-3-pro

Umongo
192K

Okufakwayo
Umbhalo + isithombe okufakwayo

Okuphumayo okuhleliwe
I-JSON schema
- Amathuluzi
- Ukucabanga
- Ukusesha kuwebhu
- I-streaming
Intengo / ama-token ayi-1M

$3.35
Shannon 3.1

Akuhlungiwe

I-Shannon 3 ku-hardware yethu, isakaza ngejubane eligcwele ngaphandle komkhawulo wezinga.

I-id ye-model shannon-3.1

Umongo
192K

Okufakwayo
Umbhalo + isithombe okufakwayo

Okuphumayo okuhleliwe
I-JSON schema
- Amathuluzi
- Ukucabanga
- Ukusesha kuwebhu
- I-streaming
Intengo / ama-token ayi-1M

$3.35

Okuningi
Shannon 3.1 Pro

Akuhlungiwe

Ukucabanga okujulile ngejubane eligcwele nesigaba socwaningo ngemuva kwemibuzo enzima.

I-id ye-model shannon-3.1-pro

Umongo
192K

Okufakwayo
Umbhalo + isithombe okufakwayo

Okuphumayo okuhleliwe
I-JSON schema
- Amathuluzi
- Ukucabanga
- Ukusesha kuwebhu
- I-streaming
Intengo / ama-token ayi-1M

$3.35

Okuningi
Shannon 3.5

Akuhlungiwe

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

I-id ye-model shannon-3.5

Umongo
192K

Okufakwayo
Umbhalo + isithombe okufakwayo

Okuphumayo okuhleliwe
I-JSON schema
- Amathuluzi
- I-streaming
Intengo / ama-token ayi-1M

$3.35

Okuningi
Shannon Coder 1

Akuhlungiwe

Uchwepheshe wekhodi namathuluzi: ukuhlela kwe-agentic, amafayela amade, nezikhawu eziqinile zamathuluzi.

I-id ye-model shannon-coder-1

Umongo
128K

Okufakwayo
Umbhalo okufakwayo

Okuphumayo okuhleliwe
I-JSON schema
- Amathuluzi
- Ukucabanga
- I-streaming
Intengo / ama-token ayi-1M

$8.00

Pheqa imibhalo

Kufinyeleleka nge-Tor ne-I2P Isevisi ye-onion, i-eepsite ye-I2P ne-mirror ye-TLS ekhiywe. Imizila efanayo ye-/v1, i-key efanayo, kuhlanganise ne-streaming; akukho ama-cookie, akukho JavaScript, akukho zicelo zezinhlangothi zesithathu. Ama-endpoint e-Tor ne-I2P

Usukulungele ukwakha?

Izinga lamahhala lifakiwe ku-akhawunti ngayinye. I-key yakho iyiklikhi eyodwa kude.

Thola i-API key Buka amanani

Ingqalasizinda ye- Ubuhlakani Obungahlungiwe

Ama-model namanani NGAMA-TOKEN AYI-1M

Ama-model e-open-weight ahlinzekiwe umongo wama-token angu-262,144 kuyo yonke i-id; okufakwayo nokuphumayo kubiziswa ngokwehlukana; i-id ngayinye yamukela lokho i-model eyilingisayo eyamukelayo

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`

Ama-model e-Shannon izinga elilodwa lokufakwayo nokuphumayo

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

Pheqa imibhalo

Usukulungele ukwakha?

Ama-model namanani NGAMA-TOKEN AYI-1M

Ama-model e-open-weight ahlinzekiwe umongo wama-token angu-262,144 kuyo yonke i-id; okufakwayo nokuphumayo kubiziswa ngokwehlukana; i-id ngayinye yamukela lokho i-model eyilingisayo eyamukelayo

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

Ama-model e-Shannon izinga elilodwa lokufakwayo nokuphumayo

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

Pheqa imibhalo

Usukulungele ukwakha?

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`