Shannon AI API ሰነዳት

መግለጺ

ህዝባዊ ሰነድ

Shannon ናይ OpenAI/Anthropic ተማሓዘ API ንምጀመር ዘድሊ ኩሉ።

URL OpenAI-Compatible

https://api.shannon-ai.com/v1/chat/completions

Chat Completions API ምስ function calling እና streaming ተጠቀም።

URL Anthropic-Compatible

https://api.shannon-ai.com/v1/messages

Claude Messages format ምስ tools እና anthropic-version header።

HTTP ማረጋገጫ

Authorization: Bearer <api-key>

ወይ X-API-Key ምስ anthropic-version ንClaude style calls።

ምውላድ ሁነታ

ህዝባዊ ሰነድ - ንcall ቁልፍ ይፈልግ

Streaming, function calling, structured outputs, web search.

ዝርዝር ምጀመር

+

SDK ናብ Shannon ኣመራ

baseURL ናብ OpenAI ወይ Anthropic endpoints ኣብ ላዕሊ ምድላይ ስብስብ።

ማስተካከል
+

API ቁልፍካ ኣገጽ

OpenAI calls ን Bearer token ወይ X-API-Key + anthropic-version ተጠቀም።

ደህንነት
+

Tools እና structured outputs ኣብር

OpenAI tools/functions, JSON schema እና built-in web_search ይደግፍ።

ክእለት
+

ኣጠቃቀም ተከታተል

እተኾን እንከሎ ኣብዚ ገጽ የtoken እና search ኣጠቃቀም ርአ።

ትንተና

ክእለታት

OpenAI + Anthropic

OpenAI እና Anthropic APIs ን drop-in replacement; tools, structured outputs እና built-in web search ይደግፍ።

Drop-in Replacement

Compatible

OpenAI እና Anthropic SDKs ምስ ይሰርሕ። base URL ብቻ ቀይር።

ጥራይ ፋንክሽን

Tools

Tools መግለጺ እቲ Shannon ንዘን ይጠርዕ። auto, forced, none መዋቅር ይደግፍ።

የድር ፍለጋ

ፈልጥ

Real-time web search ከ citations ጋር። ብራሱ ይገኛል።

የተዋቀረ ውጤት

JSON

JSON mode እና JSON Schema enforcement ን ተመኪእ ውሂብ ምውጻእ።

Multi-turn Tools

Agentic

Automatic function execution loops. ክሳብ 10 iterations ን እያንዳንዱ request።

ስትሪም

Fast

Server-sent events ን real-time token streaming።

ፈጣን መጀመር

5 ደቒቃ

ብሶስተ መደብ ጀምር። Shannon ናይ OpenAI እና Anthropic clients ይታወን።

Base URL ኣቕምጥ

OpenAI-compatible endpoint ተጠቀም።

https://api.shannon-ai.com/v1/chat/completions

API ቁልፍ ጨምር

Authorization header ውስጢ Bearer auth ተጠቀም።

ፈለም መልእኽቲ ስደድ

ቋንቋ ምረጽ እና ቁልፍካ ቀይር።

Python

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-1.6-lite",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello, Shannon!"}
    ],
    max_tokens=1024
)

print(response.choices[0].message.content)

JavaScript

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-1.6-lite',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { 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-1.6-lite",
            Messages: []openai.ChatCompletionMessage{
                {Role: "system", Content: "You are a helpful assistant."},
                {Role: "user", Content: "Hello, Shannon!"},
            },
            MaxTokens: 1024,
        },
    )
    if err != nil {
        panic(err)
    }
    fmt.Println(resp.Choices[0].Message.Content)
}

cURL

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-1.6-lite",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello, Shannon!"}
    ],
    "max_tokens": 1024
  }'

Response format

Success Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1234567890,
  "model": "Shannon 1.6 Lite",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! I'm Shannon, your AI assistant. How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 18,
    "total_tokens": 43
  }
}

API Playground

ሓድሽ

Shannon API ብሰብሳብ ብራውዘር ፈትን። ጥያቄ ኣቐምጥ፣ ኣሰርሕ፣ ውጽኢት ብቅርቡ ርአ።

Chat, Responses, Messages

Switch across OpenAI Chat Completions, Responses, and Anthropic Messages without leaving the playground.

Stream live output

Run real requests, inspect raw JSON, and view stream events from the same operator console.

Reuse your key

Signed-in users can pull their Shannon API key straight into the dedicated playground workspace.

/ti/docs/playground

The playground now lives on its own route so the API docs stay Astro-rendered while the request builder remains an explicitly interactive client tool.

Playground ፈትን V2 API ቁልፍ ርከብ

ማረጋገጫ

API requests ሁሉ ብ Shannon API key ይሕተቱ።

OpenAI Format (Recommended)

HTTP

Authorization: Bearer YOUR_API_KEY

Anthropic

HTTP

X-API-Key: YOUR_API_KEY
anthropic-version: 2023-06-01

ሞዴላት

Shannon ን ዝተለያዩ ኣጠቃቀም ምክንያታት ዝተሻለ ሞዴላት ይሃብ።

shannon-1.6-lite Shannon 1.6 Lite

ዕለታዊ ስራታት ን ፈጣን እና ውጽኢታዊ ምላሽ

ኣውድ 128K

ን ድሕነት ሰብ ሞያ ዝተሃንጸ ጫት, Q&A, ይዘት ፍጠር

shannon-1.6-pro Shannon 1.6 Pro

ለምስሕት ችግኝ ዝሓሸ reasoning

ኣውድ 128K

ን ድሕነት ሰብ ሞያ ዝተሃንጸ ትንተና, ምርምር, ዝሓሸ ስራታት

shannon-2-lite Shannon 2 Lite

ኣውድ 128K

ን ድሕነት ሰብ ሞያ ዝተሃንጸ

shannon-2-pro Shannon 2 Pro

ኣውድ 128K

ን ድሕነት ሰብ ሞያ ዝተሃንጸ

shannon-coder-1 Shannon Coder

Claude Code CLI ን call-based quota ተጠናክሮ

ኣውድ 128K

ን ድሕነት ሰብ ሞያ ዝተሃንጸ ኮድ ፍጠር, ኣገልግሎት tools, CLI integration

Call-based quota

ግብር ጥሪ

Shannon ን ስራ እና መረጋጋጽ ዝተመደቡ tools ኣቕምጥ።

Python

from openai import OpenAI
import json

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.shannon-ai.com/v1"
)

# Define available tools/functions
tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get current weather for a location",
            "parameters": {
                "type": "object",
                "properties": {
                    "location": {
                        "type": "string",
                        "description": "City name, e.g., 'Tokyo'"
                    },
                    "unit": {
                        "type": "string",
                        "enum": ["celsius", "fahrenheit"]
                    }
                },
                "required": ["location"]
            }
        }
    }
]

response = client.chat.completions.create(
    model="shannon-1.6-lite",
    messages=[{"role": "user", "content": "What's the weather in Tokyo?"}],
    tools=tools,
    tool_choice="auto"
)

# Check if model wants to call a function
if response.choices[0].message.tool_calls:
    tool_call = response.choices[0].message.tool_calls[0]
    print(f"Function: {tool_call.function.name}")
    print(f"Arguments: {tool_call.function.arguments}")

JavaScript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.shannon-ai.com/v1'
});

const tools = [
  {
    type: 'function',
    function: {
      name: 'get_weather',
      description: 'Get current weather for a location',
      parameters: {
        type: 'object',
        properties: {
          location: { type: 'string', description: "City name" },
          unit: { type: 'string', enum: ['celsius', 'fahrenheit'] }
        },
        required: ['location']
      }
    }
  }
];

const response = await client.chat.completions.create({
  model: 'shannon-1.6-lite',
  messages: [{ role: 'user', content: "What's the weather in Tokyo?" }],
  tools,
  tool_choice: 'auto'
});

if (response.choices[0].message.tool_calls) {
  const toolCall = response.choices[0].message.tool_calls[0];
  console.log('Function:', toolCall.function.name);
  console.log('Arguments:', toolCall.function.arguments);
}

ግብር ጥሪ

"auto" ሞዴል ይውስን እንትጠርዕ ወይ እንተዘይጠርዕ (default)

"none" ንዚ request function calling ኣጥፍ

{"type": "function", "function": {"name": "..."}} ነቲ ስውር function call ኣስገድድ

Response format

ሞዴል function እንትጠርዕ

{
  "id": "chatcmpl-xyz",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": null,
        "tool_calls": [
          {
            "id": "call_abc123",
            "type": "function",
            "function": {
              "name": "get_weather",
              "arguments": "{\"location\": \"Tokyo\", \"unit\": \"celsius\"}"
            }
          }
        ]
      },
      "finish_reason": "tool_calls"
    }
  ]
}

የተዋቀረ ውጤት

Shannon ን schema ዘይትርክብ ትክክለኛ JSON ክመልስ ኣስገድድ።

Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.shannon-ai.com/v1"
)

# Force JSON output with schema
response = client.chat.completions.create(
    model="shannon-1.6-lite",
    messages=[
        {"role": "user", "content": "Extract: John Doe, 30 years old, engineer"}
    ],
    response_format={
        "type": "json_schema",
        "json_schema": {
            "name": "person_info",
            "schema": {
                "type": "object",
                "properties": {
                    "name": {"type": "string"},
                    "age": {"type": "integer"},
                    "occupation": {"type": "string"}
                },
                "required": ["name", "age", "occupation"]
            }
        }
    }
)

import json
data = json.loads(response.choices[0].message.content)
print(data)  # {"name": "John Doe", "age": 30, "occupation": "engineer"}

JavaScript

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-1.6-lite',
  messages: [
    { role: 'user', content: 'Extract: John Doe, 30 years old, engineer' }
  ],
  response_format: {
    type: 'json_schema',
    json_schema: {
      name: 'person_info',
      schema: {
        type: 'object',
        properties: {
          name: { type: 'string' },
          age: { type: 'integer' },
          occupation: { type: 'string' }
        },
        required: ['name', 'age', 'occupation']
      }
    }
  }
});

const data = JSON.parse(response.choices[0].message.content);
console.log(data); // { name: "John Doe", age: 30, occupation: "engineer" }

Response format

{"type": "json_object"} Valid JSON output ኣስገድድ (ብዘይ ስኬማ)

{"type": "json_schema", "json_schema": {...}} ስኬማኻ ዝሰማማ output ኣስገድድ

ስትሪም

Server-Sent Events ብ real-time token streaming ን responsive UI ኣብር።

Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.shannon-ai.com/v1"
)

# Enable streaming for real-time responses
stream = client.chat.completions.create(
    model="shannon-1.6-lite",
    messages=[
        {"role": "user", "content": "Write a short poem about AI"}
    ],
    stream=True
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

JavaScript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.shannon-ai.com/v1'
});

// Enable streaming for real-time responses
const stream = await client.chat.completions.create({
  model: 'shannon-1.6-lite',
  messages: [
    { role: 'user', content: 'Write a short poem about AI' }
  ],
  stream: true
});

for await (const chunk of stream) {
  const content = chunk.choices[0]?.delta?.content;
  if (content) process.stdout.write(content);
}

ምክር: Streaming responses ኣብ Server-Sent Events ይመጽእ። ሓደ ቁራጭ ክፍሊ ዝተያዘ delta ይሓዝ።

የድር ፍለጋ

Shannon ብራሱ ዝግና የweb_search ስራ ኣለዎ።

Python

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="https://api.shannon-ai.com/v1"
)

# Web search is automatically available!
# Shannon will use it when needed for current information

response = client.chat.completions.create(
    model="shannon-1.6-lite",
    messages=[
        {"role": "user", "content": "What are the latest AI news today?"}
    ],
    # Optionally, explicitly define web_search tool
    tools=[{
        "type": "function",
        "function": {
            "name": "web_search",
            "description": "Search the web for current information",
            "parameters": {
                "type": "object",
                "properties": {
                    "query": {"type": "string", "description": "Search query"}
                },
                "required": ["query"]
            }
        }
    }]
)

print(response.choices[0].message.content)
# Response includes sources and citations

JavaScript

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.shannon-ai.com/v1'
});

// Web search is automatically available!
// Shannon will use it when needed for current information

const response = await client.chat.completions.create({
  model: 'shannon-1.6-lite',
  messages: [
    { role: 'user', content: 'What are the latest AI news today?' }
  ],
  // Optionally, explicitly define web_search tool
  tools: [{
    type: 'function',
    function: {
      name: 'web_search',
      description: 'Search the web for current information',
      parameters: {
        type: 'object',
        properties: {
          query: { type: 'string', description: 'Search query' }
        },
        required: ['query']
      }
    }
  }]
});

console.log(response.choices[0].message.content);
// Response includes sources and citations

ምኽሪ: Web search ውጽኢት ምንጮች ይህልዉ። Shannon ራሱ ምንጮች ይጥርዕ።

Anthropic

Shannon ናይ Anthropic Messages API format ውን ይደግፍ።

https://api.shannon-ai.com/v1/messages

Python

import anthropic

client = anthropic.Anthropic(
    api_key="YOUR_API_KEY",
    base_url="https://api.shannon-ai.com/messages"
)

response = client.messages.create(
    model="shannon-1.6-lite",
    max_tokens=1024,
    messages=[
        {"role": "user", "content": "Hello, Shannon!"}
    ],
    # Tool use (Anthropic format)
    tools=[{
        "name": "web_search",
        "description": "Search the web",
        "input_schema": {
            "type": "object",
            "properties": {
                "query": {"type": "string"}
            },
            "required": ["query"]
        }
    }]
)

print(response.content[0].text)

JavaScript

import Anthropic from '@anthropic-ai/sdk';

const client = new Anthropic({
  apiKey: 'YOUR_API_KEY',
  baseURL: 'https://api.shannon-ai.com/messages'
});

const response = await client.messages.create({
  model: 'shannon-1.6-lite',
  max_tokens: 1024,
  messages: [
    { role: 'user', content: 'Hello, Shannon!' }
  ],
  // Tool use (Anthropic format)
  tools: [{
    name: 'web_search',
    description: 'Search the web',
    input_schema: {
      type: 'object',
      properties: {
        query: { type: 'string' }
      },
      required: ['query']
    }
  }]
});

console.log(response.content[0].text);

Required: Anthropic format anthropic-version: 2023-06-01 ይፈልግ።

SDKዎች

Compatible

OpenAI ወይ Anthropic SDK እንተሆነ ተጠቀም — base URL ብቻ ቀይር።

OpenAI-Compatible SDKs

SDK Python

Official OpenAI Python SDK — Shannon ምስ ይሰርሕ

pip install openai

ሰነድ ርአ ->

SDK JavaScript / TypeScript

Official OpenAI Node.js SDK — Shannon ምስ ይሰርሕ

npm install openai

ሰነድ ርአ ->

SDK Go

OpenAI-compatible API ን community Go client

go get github.com/sashabaranov/go-openai

ሰነድ ርአ ->

SDK Ruby

OpenAI-compatible API ን community Ruby client

gem install ruby-openai

ሰነድ ርአ ->

SDK PHP

OpenAI-compatible API ን community PHP client

composer require openai-php/client

ሰነድ ርአ ->

SDK Rust

OpenAI-compatible API ን Async Rust client

cargo add async-openai

ሰነድ ርአ ->

Anthropic-Compatible SDKs

SDK Python (Anthropic)

Official Anthropic Python SDK — Shannon ምስ ይሰርሕ

pip install anthropic

ሰነድ ርአ ->

SDK TypeScript (Anthropic)

Official Anthropic TypeScript SDK — Shannon ምስ ይሰርሕ

npm install @anthropic-ai/sdk

ሰነድ ርአ ->

ሓጋይ ኣስተዳደር

Shannon መደበኛ HTTP status codes ይጠቀም እና ዝርዝር ሓጋይ መልእኽቲ ይህብ።

400 Bad Request ፎርማት ጥያቄ ወይ ፓራሜትራት ኣይትክክልን

401 Unauthorized API ቁልፍ ኣይትክክልን ወይ የለን

402 Quota Exceeded Token ወይ search quota ተጸንሐ

429 Rate Limited ብዙሕ ጥያቄዎች, ተንስአ

500 Server Error ውስጣዊ ሓጋይ, ቀጺል ሞክር

Error Response Format

Error Response

{
  "error": {
    "message": "Invalid API key provided",
    "type": "authentication_error",
    "code": "invalid_api_key"
  }
}

የለውጥ መዝገብ

LOG

Shannon API ዝመጹ ዝርዝር ምሓደስ እና ምሻል።

v2.1.0

2025-01-03

ሓድሽ shannon-coder-1 ሞዴል ን Claude Code CLI integration ተጨመረ
ሓድሽ Coder ሞዴል ን call-based quota ስርዓት
ተሻሽለ Function calling ዕምነት ተሻሽለ

v2.0.0

2024-12-15

ሓድሽ Anthropic Messages API compatibility ተጨመረ
ሓድሽ Multi-turn tool execution (ክሳብ 10 iterations)
ሓድሽ JSON Schema response format ድጋፍ
ተሻሽለ Web search ብምሻል እና citations

v1.5.0

2024-11-20

ሓድሽ shannon-deep-dapo ሞዴል ን ጥራይ reasoning ተጨመረ
ሓድሽ Built-in web_search function
ተሻሽለ Streaming responses latency ተቐንሰ

v1.0.0

2024-10-01

ሓድሽ API መጀመሪ ልቀት
ሓድሽ OpenAI-compatible chat completions endpoint
ሓድሽ Function calling support
ሓድሽ Streaming ብ Server-Sent Events

API ቁልፍካ

ምውላድ

OpenAI calls ን Bearer token ወይ X-API-Key + anthropic-version ተጠቀም።

YOUR_API_KEY

API ቁልፍ ርከብ

API ቁልፍካ ምስጢር ኣትከውን። Regenerate ንሓድሽ ቁልፍ ይፈጥር እና ናይ ቀደም ይበዝሕ።

ኣጠቃቀምካ

እተኾን እንከሎ ኣብዚ ገጽ የtoken እና search ኣጠቃቀም ርአ።

-- API Calls

-- Tokens Used

Shannon API

መግለጺ

ክእለታት

Drop-in Replacement

ጥራይ ፋንክሽን

የድር ፍለጋ

የተዋቀረ ውጤት

Multi-turn Tools

ስትሪም

ፈጣን መጀመር

Base URL ኣቕምጥ

API ቁልፍ ጨምር

ፈለም መልእኽቲ ስደድ

Response format

API Playground

Chat, Responses, Messages

Stream live output

Reuse your key

ማረጋገጫ

OpenAI Format (Recommended)

Anthropic

ሞዴላት

ግብር ጥሪ

ግብር ጥሪ

Response format

የተዋቀረ ውጤት

Response format

ስትሪም

የድር ፍለጋ

Anthropic

SDKዎች

OpenAI-Compatible SDKs

Anthropic-Compatible SDKs

ሓጋይ ኣስተዳደር

Error Response Format

የለውጥ መዝገብ

API ቁልፍካ

ኣጠቃቀምካ

Shannon Coder (shannon-coder-1)

ብኽብረት ንምህዳስ ዝተዘጋጅካ?

Shannon AI API Documentation

መግለጺ

ክእለታት

Drop-in Replacement

ጥራይ ፋንክሽን

የድር ፍለጋ

የተዋቀረ ውጤት

Multi-turn Tools

ስትሪም

ፈጣን መጀመር

Base URL ኣቕምጥ

API ቁልፍ ጨምር

ፈለም መልእኽቲ ስደድ

Response format

API Playground

Chat, Responses, Messages

Stream live output

Reuse your key

ማረጋገጫ

OpenAI Format (Recommended)

Anthropic

ሞዴላት

ግብር ጥሪ

ግብር ጥሪ

Response format

የተዋቀረ ውጤት

Response format

ስትሪም

የድር ፍለጋ

Anthropic

SDKዎች

OpenAI-Compatible SDKs

Anthropic-Compatible SDKs

ሓጋይ ኣስተዳደር

Error Response Format

የለውጥ መዝገብ

API ቁልፍካ

ኣጠቃቀምካ

Shannon Coder (shannon-coder-1)

ብኽብረት ንምህዳስ ዝተዘጋጅካ?