Zolemba za Shannon AI API

Chidule

Zolemba zapagulu

Zonse zomwe mukufuna kuti mutulutse ndi API yogwirizana ndi OpenAI ndi Anthropic ya Shannon.

URL Yogwirizana ndi OpenAI

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

Gwiritsani ntchito Chat Completions API yokhala ndi function calling ndi streaming.

URL Yogwirizana ndi Anthropic

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

Claude Messages format yokhala ndi tools ndi anthropic-version header.

HTTP Chitsimikizo

Authorization: Bearer <api-key>

Kapena X-API-Key ndi anthropic-version pa Claude-style calls.

Kufikira Mkhalidwe

Zolemba zapagulu - kiyi ikufunika

Streaming, function calling, structured outputs, web search.

Mndandanda woyambira

+

Lunjikitsani SDK yanu ku Shannon

Setha baseURL ku OpenAI kapena Anthropic endpoints pamwambapa.

Setup
+

Lumikizani API key yanu

Gwiritsani ntchito Bearer tokens pa OpenAI calls kapena X-API-Key + anthropic-version.

Chitetezo
+

Yatsani tools & structured outputs

Imathandizira OpenAI tools/functions, JSON schema, ndi built‑in web_search.

Mphamvu
+

Tsatirani kugwiritsa ntchito

Mukalowa, onani kugwiritsa ntchito token ndi search patsamba ili.

Kusanthula

Mphamvu

OpenAI + Anthropic

Drop‑in m'malo mwa OpenAI ndi Anthropic APIs ndi thandizo la zida, zotuluka zokonzedwa, komanso kusaka pa web komangidwa.

Drop‑in Replacement

Yogwirizana

Imagwira ndi OpenAI ndi Anthropic SDKs. Sinthani base URL kokha.

Kuyitana ntchito

Tools

Fotokozani tools, Shannon adzawayitana. Imathandiza auto, forced, none modes.

Built‑in Web Search

Kusaka

Web search nthawi yeniyeni yokhala ndi citations. Imapezeka yokha.

Zotuluka zokonzedwa

JSON

JSON mode ndi JSON Schema enforcement kuti mutenge data yolondola.

Multi‑turn Tools

Agentic

Automatic function execution loops. Mpaka 10 iterations pa pempho.

Kutsitsa nthawi yeniyeni

Mwamsanga

Server‑Sent Events ya streaming ya token nthawi yeniyeni.

Kuyamba mwachangu

Mphindi 5

Yambani m'masitepe atatu. Shannon imatsanzira makasitomala a OpenAI ndi Anthropic.

Setha base URL yanu

Gwiritsani ntchito OpenAI‑compatible endpoint.

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

Onjezani API key yanu

Gwiritsani ntchito Bearer auth mu Authorization header.

Tumizani uthenga wanu woyamba

Sankhani chilankhulo ndi kuyika kiyi yanu.

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
  }'

Fomati ya yankho

Yankho lopambana

{
  "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

Chatsopano

Yesani Shannon API mwachindunji mu browser yanu. Pangani pempho, yendetsani, ndipo muwone yankho nthawi yeniyeni.

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.

/ny/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.

Yesani Playground V2 Pezani kiyi yanu ya API

Kutsimikizira

Pempho lililonse la API limafuna kutsimikiziridwa pogwiritsa ntchito kiyi yanu ya Shannon API.

OpenAI format (yolimbikitsidwa)

HTTP

Authorization: Bearer YOUR_API_KEY

Anthropic format

HTTP

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

Ma model

Shannon imapereka mitundu ingapo yoikidwa bwino pa ntchito zosiyanasiyana.

shannon-1.6-lite Shannon 1.6 Lite

Mayankho othamanga komanso ogwira ntchito pa ntchito za tsiku ndi tsiku

Malo 128K

Zabwino kwambiri Chat, Q&A, Kupanga Zomwe Zili

shannon-1.6-pro Shannon 1.6 Pro

Reasoning yapamwamba pa zovuta

Malo 128K

Zabwino kwambiri Kusanthula, Kafukufuku, Ntchito Zovuta

shannon-2-lite Shannon 2 Lite

Malo 128K

Zabwino kwambiri

shannon-2-pro Shannon 2 Pro

Malo 128K

Zabwino kwambiri

shannon-coder-1 Shannon Coder

Yokonzedwa kwa Claude Code CLI yokhala ndi call‑based quota

Malo 128K

Zabwino kwambiri Kupanga Kachidindo, Kugwiritsa Tools, CLI Integration

Call‑based quota

Kuyitana mafunkseni

Tanthauzirani zida zomwe Shannon angathe kuyitana kuti achite zochita kapena atenge zambiri.

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);
}

Zosankha za tool

"auto" Model amasankha ngati ayitana function (default)

"none" Tsekani function calling pa pempho ili

{"type": "function", "function": {"name": "..."}} Kakamizani function inayake

Yankho la Function Call

Pamene model wayitana function

{
  "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"
    }
  ]
}

Zotuluka zokonzedwa

Kakamizani Shannon kuyankha ndi JSON yolondola yomwe ikugwirizana ndi schema yanu.

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" }

Zosankha za fomati ya yankho

{"type": "json_object"} Kakamizani valid JSON output (popanda schema inayake)

{"type": "json_schema", "json_schema": {...}} Kakamizani output yofanana ndi schema yanu

Kutsitsa nthawi yeniyeni

Yatsani token streaming ya nthawi yeniyeni ndi Server‑Sent Events kuti UI ikhale yothamanga.

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);
}

Malangizo: Streaming responses zimabwera ngati Server‑Sent Events. Chunk iliyonse ili ndi delta yokhala ndi mbali ya content.

Kusaka pa web

Shannon ili ndi web_search yomangidwira yomwe imapezeka yokha.

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

Tip: Zotsatira za web search zili ndi citations. Shannon adzatchula masamba yokha.

Anthropic

Shannon imathandizanso mtundu wa Anthropic Messages API.

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);

Header yofunikira: Anthropic format imafuna anthropic-version: 2023-06-01.

SDKs

Yogwirizana

Gwiritsani ntchito OpenAI kapena Anthropic SDK iliyonse — ingosinthani base URL.

OpenAI‑Compatible SDKs

SDK Python

Official OpenAI Python SDK - imagwira ndi Shannon

pip install openai

Onani Docs ->

SDK JavaScript / TypeScript

Official OpenAI Node.js SDK - imagwira ndi Shannon

npm install openai

Onani Docs ->

SDK Go

Community Go client ya OpenAI‑compatible APIs

go get github.com/sashabaranov/go-openai

Onani Docs ->

SDK Ruby

Community Ruby client ya OpenAI‑compatible APIs

gem install ruby-openai

Onani Docs ->

SDK PHP

Community PHP client ya OpenAI‑compatible APIs

composer require openai-php/client

Onani Docs ->

SDK Rust

Async Rust client ya OpenAI‑compatible APIs

cargo add async-openai

Onani Docs ->

Anthropic‑Compatible SDKs

SDK Python (Anthropic)

Official Anthropic Python SDK - imagwira ndi Shannon

pip install anthropic

Onani Docs ->

SDK TypeScript (Anthropic)

Official Anthropic TypeScript SDK - imagwira ndi Shannon

npm install @anthropic-ai/sdk

Onani Docs ->

Zolakwika

Shannon imagwiritsa ntchito ma HTTP status code okhazikika ndipo imabwezera mauthenga olakwika atsatanetsatane.

400 Pempho lolakwika Fomati yolakwika ya pempho kapena ma paramita

401 Osaloledwa API key yolakwika kapena yosowa

402 Quota yatha Token kapena search quota yadutsa

429 Rate Limit Mapempho ambiri, chepetsani liwiro

500 Vuto la seva Vuto la mkati, yesaninso

Fomati ya yankho la cholakwika

Yankho la cholakwika

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

Mbiri ya kusintha

LOG

Zosintha zaposachedwa ndi kukonza kwa Shannon API.

v2.1.0

2025-01-03

Chatsopano Yawonjezera shannon-coder-1 model ya Claude Code CLI integration
Chatsopano Call‑based quota system ya Coder model
Zasintha Kudalirika kwa function calling kwasintha

v2.0.0

2024-12-15

Chatsopano Anthropic Messages API compatibility yawonjezedwa
Chatsopano Multi‑turn tool execution (mpaka 10 iterations)
Chatsopano Thandizo la JSON Schema response format
Zasintha Web search yasinthidwa ndi citations zabwinoko

v1.5.0

2024-11-20

Chatsopano Yawonjezera shannon-deep-dapo model ya reasoning yovuta
Chatsopano Built‑in web_search function
Zasintha Latency ya streaming responses yachepetsedwa

v1.0.0

2024-10-01

Chatsopano Kutulutsidwa koyamba kwa API
Chatsopano OpenAI‑compatible chat completions endpoint
Chatsopano Thandizo la function calling
Chatsopano Streaming kudzera mu Server‑Sent Events

Kiyi ya API

Kufikira

Gwiritsani ntchito Bearer tokens pa OpenAI calls kapena X-API-Key + anthropic-version.

YOUR_API_KEY

Pezani kiyi yanu ya API

Sungani API key yanu mwachinsinsi. Kubwezeretsa kumapanga key yatsopano ndikuchotsa yakale.

Kugwiritsa ntchito

Mukalowa, onani kugwiritsa ntchito token ndi search patsamba ili.

-- API Calls

-- Ma token ogwiritsidwa ntchito

Shannon API

Chidule

Mphamvu

Drop‑in Replacement

Kuyitana ntchito

Built‑in Web Search

Zotuluka zokonzedwa

Multi‑turn Tools

Kutsitsa nthawi yeniyeni

Kuyamba mwachangu

Setha base URL yanu

Onjezani API key yanu

Tumizani uthenga wanu woyamba

Fomati ya yankho

API Playground

Chat, Responses, Messages

Stream live output

Reuse your key

Kutsimikizira

OpenAI format (yolimbikitsidwa)

Anthropic format

Ma model

Kuyitana mafunkseni

Zosankha za tool

Yankho la Function Call

Zotuluka zokonzedwa

Zosankha za fomati ya yankho

Kutsitsa nthawi yeniyeni

Kusaka pa web

Anthropic

SDKs

OpenAI‑Compatible SDKs

Anthropic‑Compatible SDKs

Zolakwika

Fomati ya yankho la cholakwika

Mbiri ya kusintha

Kiyi ya API

Kugwiritsa ntchito

Shannon Coder (shannon-coder-1)

Wakonzeka kupanga?

Shannon AI API Documentation

Chidule

Mphamvu

Drop‑in Replacement

Kuyitana ntchito

Built‑in Web Search

Zotuluka zokonzedwa

Multi‑turn Tools

Kutsitsa nthawi yeniyeni

Kuyamba mwachangu

Setha base URL yanu

Onjezani API key yanu

Tumizani uthenga wanu woyamba

Fomati ya yankho

API Playground

Chat, Responses, Messages

Stream live output

Reuse your key

Kutsimikizira

OpenAI format (yolimbikitsidwa)

Anthropic format

Ma model

Kuyitana mafunkseni

Zosankha za tool

Yankho la Function Call

Zotuluka zokonzedwa

Zosankha za fomati ya yankho

Kutsitsa nthawi yeniyeni

Kusaka pa web

Anthropic

SDKs

OpenAI‑Compatible SDKs

Anthropic‑Compatible SDKs

Zolakwika

Fomati ya yankho la cholakwika

Mbiri ya kusintha

Kiyi ya API

Kugwiritsa ntchito

Shannon Coder (shannon-coder-1)

Wakonzeka kupanga?