Zolemba za API

Maziko a Nzeru Yopanda Zoletsa

API ya AI yopanda zoletsa: ma model a Shannon opanda kukana komanso opanda ma filter, ogwira ntchito pa ma GPU athu. Yogwirizana ndi OpenAI ndi Anthropic — ikani SDK yomwe mukugwiritsa kale, kiyi imodzi, streaming, tool calling ndi reasoning pa endpoint iliyonse.

22 ma model opanda zoletsa
256K context window
kuyambira $0.50/1M
3 ma API ogwirizana
3 ma network: TLS, Tor, I2P

Yambani kumanga Yesani 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
  }'

Ma model ndi mitengo PA MA TOKEN 1M

Malire, ma id ndi momwe mitengo imapangidwira

Ma hosted open-weight model context ya ma token 262,144 pa id iliyonse; input ndi output zimawerengedwa mosiyana; id iliyonse imalandira zomwe model yomwe imatsanzira imalandira

DeepSeek-V4-Pro-0813 3BIT-REAP

DeepSeek · 1.6T MoE · 49B active

Yopanda zoletsa

Model yaikulu yoganiza mozama komanso yolemba zazitali.

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

Context
256K

Input
Text yolowa

Structured output
JSON schema
- Ma tool
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out pa 1M

$1.95 / $0.488 / $3.90

Zambiri
GLM-5.2 3BIT-REAP

Z.ai · 744B MoE · 40B active

Yopanda zoletsa

Model yamphamvu ya zolinga zambiri yokhala ndi output yolemera ya zilankhulo zambiri.

Model id GLM-5.2-3BIT-REAP

Context
256K

Input
Text yolowa

Structured output
JSON schema
- Ma tool
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out pa 1M

$0.73 / $0.183 / $2.34

Zambiri
Kimi-K3 3BIT-REAP

Moonshot AI · 2.8T MoE · 104B active

Yopanda zoletsa

Model yapamwamba yokonzedwa kuti ipereke mayankho athunthu komanso atsatanetsatane.

Model id Kimi-K3-3BIT-REAP

Context
256K

Input
Text + chithunzi cholowa

Structured output
JSON schema
- Ma tool
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out pa 1M

$3.83 / $0.958 / $19.12

Zambiri
Nemotron3Ultra 3BIT-REAP

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

Yopanda zoletsa

Model yaikulu yogwira ntchito bwino ndi reasoning yamphamvu pa dola iliyonse.

Model id Nemotron3Ultra-3BIT-REAP

Context
256K

Input
Text yolowa

Structured output
JSON schema
- Ma tool
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out pa 1M

$0.75 / $0.188 / $3.30

Zambiri
MiniMax-M3 3BIT-REAP

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

Yopanda zoletsa

Model yachangu komanso yotsika mtengo ya ntchito zambiri.

Model id MiniMax-M3-3BIT-REAP

Context
256K

Input
Text + chithunzi cholowa

Structured output
JSON schema
- Ma tool
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out pa 1M

$0.50 / $0.125 / $2.00

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

DeepSeek · 284B MoE · 13B active

Yopanda zoletsa

Model yachangu ya DeepSeek yolinganiza liwiro ndi khalidwe.

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

Context
256K

Input
Text yolowa

Structured output
JSON schema
- Ma tool
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out pa 1M

$0.50 / $0.125 / $2.00

Zambiri
Kimi-K2.6 W4A16-AUTOROUND-REAP

Moonshot AI · 1T MoE · 32B active

Yopanda zoletsa

Model yokhoza pa reasoning ya tsiku ndi tsiku ndi kulemba madraft.

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

Context
256K

Input
Text + chithunzi cholowa

Structured output
JSON schema
- Ma tool
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out pa 1M

$0.78 / $0.195 / $3.67

Zambiri
Laguna-S-2.1 W4A16-AUTOROUND-REAP

Poolside · 118B MoE · 8B active

Yopanda zoletsa

Model yotsika mtengo kwambiri ya ntchito zopepuka.

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

Context
256K

Input
Text yolowa

Structured output
Palibe structured output
- Ma tool
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out pa 1M

$0.50 / $0.125 / $2.00

Zambiri
inkling W4A16-AUTOROUND-REAP

Thinking Machines · 975B MoE · 41B active

Yopanda zoletsa

Model yopanga zatsopano yokhala ndi kalembedwe kake kapadera.

Model id inkling-W4A16-AUTOROUND-REAP

Context
256K

Input
Text + chithunzi cholowa

Structured output
JSON object
- Ma tool
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out pa 1M

$1.42 / $0.355 / $6.07

Zambiri
MiMo-V2.5-Pro W8A16

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

Yopanda zoletsa

Model yaying'ono ya pro ya output yokonzedwa komanso yolondola.

Model id MiMo-V2.5-Pro-W8A16

Context
256K

Input
Text yolowa

Structured output
JSON schema
- Ma tool
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out pa 1M

$0.50 / $0.125 / $2.00

Zambiri
MiMo-V2.5 W8A16

Xiaomi · 8-bit multimodal · W8A16

Yopanda zoletsa

Model yaying'ono komanso yachangu ya ntchito zosavuta pa mtengo wochepa kwambiri.

Model id MiMo-V2.5-W8A16

Context
256K

Input
Text + chithunzi cholowa

Structured output
JSON schema
- Ma tool
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out pa 1M

$0.50 / $0.125 / $2.00

Zambiri
Hy3 W8A16

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

Yopanda zoletsa

Model yotsika mtengo yoyankha mwachidule pa kukambirana.

Model id Hy3-W8A16

Context
256K

Input
Text yolowa

Structured output
JSON schema
- Ma tool
- Reasoning
- Reasoning effort
- Prompt caching
- Streaming
In / cached / out pa 1M

$0.50 / $0.125 / $2.00

Zambiri

Ma model a Shannon mtengo umodzi wokhazikika wa input ndi output

Shannon 1.6 Lite

Yopanda zoletsa

Mayankho othamanga komanso ogwira ntchito pa ntchito za tsiku ndi tsiku

Model id shannon-1.6-lite

Context
192K

Input
Text + chithunzi cholowa

Structured output
JSON schema
- Ma tool
- Web search
- Streaming
Mtengo / ma token 1M

$3.90
Shannon 1.6 Pro

Yopanda zoletsa

Reasoning yapamwamba pa zovuta

Model id shannon-1.6-pro

Context
192K

Input
Text + chithunzi cholowa

Structured output
JSON schema
- Ma tool
- Reasoning
- Web search
- Streaming
Mtengo / ma token 1M

$7.80
Shannon 2 Lite

Yopanda zoletsa

Shannon 2 Lite: pipeline yachangu ya kuganiza-kulemba-kuunikanso ndi reasoning trace yooneka. Chat ya tsiku ndi tsiku, ma summary ndi Q&A.

Model id shannon-2-lite

Context
192K

Input
Text + chithunzi cholowa

Structured output
JSON schema
- Ma tool
- Reasoning
- Web search
- Streaming
Mtengo / ma token 1M

$3.90
Shannon 2 Pro

Yopanda zoletsa

Shannon 2 Pro: kuganiza-kulemba-kuunikanso mozama pa kusanthula, kulemba zazitali ndi reasoning ya masitepe ambiri.

Model id shannon-2-pro

Context
192K

Input
Text + chithunzi cholowa

Structured output
JSON schema
- Ma tool
- Reasoning
- Web search
- Streaming
Mtengo / ma token 1M

$5.85
Shannon 3

Yopanda zoletsa

Model ya Shannon ya m'badwo waposachedwa ndi reasoning yachangu pa mtengo wotsika wokhazikika.

Model id shannon-3

Context
192K

Input
Text + chithunzi cholowa

Structured output
JSON schema
- Ma tool
- Reasoning
- Web search
- Streaming
Mtengo / ma token 1M

$3.35
Shannon 3 Pro

Yopanda zoletsa

Gawo la Shannon 3 lamphamvu kwambiri pa ntchito zovuta za masitepe ambiri.

Model id shannon-3-pro

Context
192K

Input
Text + chithunzi cholowa

Structured output
JSON schema
- Ma tool
- Reasoning
- Web search
- Streaming
Mtengo / ma token 1M

$3.35
Shannon 3.1

Yopanda zoletsa

Shannon 3 pa hardware yathu, streaming pa liwiro lonse popanda rate gate.

Model id shannon-3.1

Context
192K

Input
Text + chithunzi cholowa

Structured output
JSON schema
- Ma tool
- Reasoning
- Web search
- Streaming
Mtengo / ma token 1M

$3.35

Zambiri
Shannon 3.1 Pro

Yopanda zoletsa

Reasoning yozama pa liwiro lonse ndi kafukufuku wakumbuyo pa mafunso ovuta.

Model id shannon-3.1-pro

Context
192K

Input
Text + chithunzi cholowa

Structured output
JSON schema
- Ma tool
- Reasoning
- Web search
- Streaming
Mtengo / ma token 1M

$3.35

Zambiri
Shannon 3.5

Yopanda zoletsa

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

Model id shannon-3.5

Context
192K

Input
Text + chithunzi cholowa

Structured output
JSON schema
- Ma tool
- Streaming
Mtengo / ma token 1M

$3.35

Zambiri
Shannon Coder 1

Yopanda zoletsa

Katswiri wa code ndi ma tool: kusintha kwa agentic, ma file aatali ndi ma tool loop okhwima.

Model id shannon-coder-1

Context
128K

Input
Text yolowa

Structured output
JSON schema
- Ma tool
- Reasoning
- Streaming
Mtengo / ma token 1M

$8.00

Sakatulani zolemba

Mutha kufika kudzera pa Tor ndi I2P Onion service, I2P eepsite ndi TLS mirror yosungidwa mwachinsinsi. Ma route a /v1 omwewo, kiyi yomweyo, streaming ikuphatikizidwa; popanda ma cookie, popanda JavaScript, popanda mapempho a anthu ena. Ma endpoint a Tor ndi I2P

Wakonzeka kupanga?

Plan yaulere ikuphatikizidwa ndi akaunti iliyonse. Kiyi yanu ili pafupi kwambiri.

Pangani kiyi ya API Onani zolemba

Maziko a Nzeru Yopanda Zoletsa

Ma model ndi mitengo PA MA TOKEN 1M

Ma hosted open-weight model context ya ma token 262,144 pa id iliyonse; input ndi output zimawerengedwa mosiyana; id iliyonse imalandira zomwe model yomwe imatsanzira imalandira

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`

Ma model a Shannon mtengo umodzi wokhazikika wa input ndi 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

Sakatulani zolemba

Wakonzeka kupanga?

Ma model ndi mitengo PA MA TOKEN 1M

Ma hosted open-weight model context ya ma token 262,144 pa id iliyonse; input ndi output zimawerengedwa mosiyana; id iliyonse imalandira zomwe model yomwe imatsanzira imalandira

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

Ma model a Shannon mtengo umodzi wokhazikika wa input ndi 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

Sakatulani zolemba

Wakonzeka kupanga?

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`