Tokomane ea Shannon AI API

Kakaretso

Docs tsa setjhaba

Tsohle tseo o di hlokang ho qala ka API ya Shannon e lumellanang le OpenAI le Anthropic.

URL E tsamaisana le OpenAI

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

Sebelisa Chat Completions API ka function calling le streaming.

URL E tsamaisana le Anthropic

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

Mokgwa wa Claude Messages ka tools le anthropic-version header.

HTTP Tiisetso

Authorization: Bearer <api-key>

Kapa X-API-Key le anthropic-version bakeng sa Claude-style calls.

Phihlello Boemo

Docs tsa setjhaba - senotlolo se a hlokahala

Streaming, ho bitsa mesebetsi, dihahisong tse hlophisitsoeng, web search.

Lenane la ho qala

+

Supisa SDK ya hao ho Shannon

Seta baseURL ho OpenAI kapa Anthropic endpoints tse kahodimo.

Setapa
+

Hokela API key ya hao

Sebelisa Bearer tokens ho OpenAI calls kapa X-API-Key + anthropic-version.

Tshireletso
+

Bulela tools & structured outputs

E tshehetsa OpenAI tools/functions, JSON schema, le built-in web_search.

Bokgoni
+

Latela tshebediso

Ha o kene, sheba tshebediso ya token le search leqepheng lena.

Tlhahlobo

Bokgoni

OpenAI + Anthropic

Drop‑in replacement bakeng sa OpenAI le Anthropic APIs ka tshehetso ya disebediswa, diphumo tse hlophisitsoeng le patlo ya webe e hahiloeng ka hare.

Drop‑in Replacement

E tsamaisana

E sebetsa le OpenAI le Anthropic SDKs. Fetola base URL feela.

Ho bitsa mesebetsi

Lisebelisoa

Hlalosa tools, Shannon o tla di bitsa. E tshehetsa auto, forced, none modes.

Built‑in Web Search

Patlisiso

Web search ka nako ya nnete ka citations. E fumaneha ka bohona.

Dihlahiso tse hlophisitsoeng

JSON

JSON mode le JSON Schema enforcement bakeng sa data e tshepehang.

Multi‑turn Tools

Agentic

Automatic function execution loops. Ho fihla ho 10 iterations ka kopo.

Phallela

Potlako

Server‑Sent Events bakeng sa streaming ya token ka nako ya nnete.

Qalo e potlakileng

5 metsotso

Qala ka mehato e meraro. Shannon e etsisa bareki ba OpenAI le Anthropic.

Seta base URL ya hao

Sebelisa OpenAI‑compatible endpoint.

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

Eketsa API key ya hao

Sebelisa Bearer auth ho Authorization header.

Romela molaetsa wa hao wa pele

Kgetha puo le ho kenya key ya hao.

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
  }'

Fomate ya karabo

Karabo e atlehileng

{
  "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

Ntjha

Lekola Shannon API ka kotloloho ho browser ya hao. Haha kopo, tsamaisa, mme o bone karabo ka nako ya nnete.

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.

/st/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.

Leka Playground V2 Fumana senotlolo sa hao sa API

Netefatso

Dikopo tsohle tsa API di hloka netefatso ka senotlolo sa hao sa Shannon API.

OpenAI format (e kgothaletswang)

HTTP

Authorization: Bearer YOUR_API_KEY

Anthropic format

HTTP

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

Dimodelo

Shannon e fana ka dimodelo tse mmalwa tse ntlafalitsoeng bakeng sa tshebediso e fapaneng.

shannon-1.6-lite Shannon 1.6 Lite

Dikarabo tse potlakileng le tse sebetsang bakeng sa mesebetsi ya letsatsi le letsatsi

Konteksti 128K

E molemohadi bakeng sa Chat, Q&A, Tlhahiso ya dikahare

shannon-1.6-pro Shannon 1.6 Pro

Reasoning e phahameng bakeng sa mathata a rarahaneng

Konteksti 128K

E molemohadi bakeng sa Tlhahlobo, Diphuputso, Mesebetsi e rarahaneng

shannon-2-lite Shannon 2 Lite

Konteksti 128K

E molemohadi bakeng sa

shannon-2-pro Shannon 2 Pro

Konteksti 128K

E molemohadi bakeng sa

shannon-coder-1 Shannon Coder

E lokiselitsoe Claude Code CLI ka call‑based quota

Konteksti 128K

E molemohadi bakeng sa Tlhahiso ya khoutu, Tshebediso ya tools, CLI Integration

Call‑based quota

Mekhosi ya mesebetsi

Hlalosa disebediswa tseo Shannon e ka di bitsang ho etsa diketso kapa ho fumana tlhahisoleseding.

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);
}

Likgetho tsa tool

"auto" Model e etsa qeto haeba e tla bitsa function (default)

"none" Tima function calling bakeng sa kopo ena

{"type": "function", "function": {"name": "..."}} Qobella function e itseng

Karabo ya Function Call

Ha model e bitsa 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"
    }
  ]
}

Diphumo tse hlophisitsoeng

Qobella Shannon ho arabela ka JSON e nepahetseng e tsamaellanang le schema ya hao.

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" }

Likgetho tsa fomate ya karabo

{"type": "json_object"} Qobella JSON output e nepahetseng (ho se na schema e itseng)

{"type": "json_schema", "json_schema": {...}} Qobella output e tsamaisanang le schema ya hao

Phallela

Bulela token streaming ya nako‑nnete ka Server‑Sent Events bakeng sa UI e arabelang.

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);
}

Tlhahiso: Streaming responses di tla ka Server‑Sent Events. Chunk e nngwe le e nngwe e na le delta e nang le karolo ya dikahare.

Patlo ya webe

Shannon e na le web_search e hahiloeng ka hare e fumanehang ka bohona.

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

Keletso ea Pro: Web search results di na le citations. Shannon o tla qotsa mehlodi ka bohona.

Anthropic

Shannon e tshehetsa le format ya 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 e hlokahalang: Anthropic format e hloka anthropic-version: 2023-06-01.

SDKs

E tsamaisana

Sebedisa SDK efe kapa efe ya OpenAI kapa Anthropic — fetola feela base URL.

OpenAI‑Compatible SDKs

SDK Python

Official OpenAI Python SDK - e sebetsa le Shannon

pip install openai

Bona Docs ->

SDK JavaScript / TypeScript

Official OpenAI Node.js SDK - e sebetsa le Shannon

npm install openai

Bona Docs ->

SDK Go

Community Go client bakeng sa OpenAI‑compatible APIs

go get github.com/sashabaranov/go-openai

Bona Docs ->

SDK Ruby

Community Ruby client bakeng sa OpenAI‑compatible APIs

gem install ruby-openai

Bona Docs ->

SDK PHP

Community PHP client bakeng sa OpenAI‑compatible APIs

composer require openai-php/client

Bona Docs ->

SDK Rust

Async Rust client bakeng sa OpenAI‑compatible APIs

cargo add async-openai

Bona Docs ->

Anthropic‑Compatible SDKs

SDK Python (Anthropic)

Official Anthropic Python SDK - e sebetsa le Shannon

pip install anthropic

Bona Docs ->

SDK TypeScript (Anthropic)

Official Anthropic TypeScript SDK - e sebetsa le Shannon

npm install @anthropic-ai/sdk

Bona Docs ->

Diphoso

Shannon e sebedisa dikhoutu tsa boemo ba HTTP tse tlwaelehileng mme e khutlisa melaetsa ya phoso e qaqileng.

400 Kopo e fosahetseng Fomate ya kopo e fosahetseng kapa dipharamitha

401 Ha e na tumello API key e fosahetseng kapa e sieo

402 Quota e fetilwe Token kapa search quota e fetilwe

429 Rate Limit Dikopo tse ngata, fokotsa lebelo

500 Phoso ya seva Phoso ya kahare, leka hape

Fomate ya karabo ya phoso

Karabo ya phoso

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

Rekoto ya diphetoho

LOG

Dintlafatso le ntlafatso tsa moraorao tsa Shannon API.

v2.1.0

2025-01-03

Ntjha Ho eketswa shannon-coder-1 model bakeng sa Claude Code CLI integration
Ntjha Call‑based quota system bakeng sa Coder model
E ntlafaditswe Ho tshepeha ha function calling ho ntlafaditswe

v2.0.0

2024-12-15

Ntjha Anthropic Messages API compatibility e ekeditswe
Ntjha Multi‑turn tool execution (ho fihla 10 iterations)
Ntjha Tshehetso ya JSON Schema response format
E ntlafaditswe Web search e ntlafaditswe ka citations tse betere

v1.5.0

2024-11-20

Ntjha Ho eketswa shannon-deep-dapo model bakeng sa reasoning e rarahaneng
Ntjha Built‑in web_search function
E ntlafaditswe Latency ya streaming responses e fokoditswe

v1.0.0

2024-10-01

Ntjha API release ya pele
Ntjha OpenAI‑compatible chat completions endpoint
Ntjha Tshehetso ya function calling
Ntjha Streaming ka Server‑Sent Events

Senotlolo sa API

Phihlello

Sebelisa Bearer tokens ho OpenAI calls kapa X-API-Key + anthropic-version.

YOUR_API_KEY

Fumana senotlolo sa hao sa API

Boloka API key ya hao e le sephiri. Ho hlahisa hape ho etsa key e ntjha le ho hlakola ya kgale.

Tshebediso

Ha o kene, sheba tshebediso ya token le search leqepheng lena.

-- Mehala ya API

-- Tokeni tse sebedisitsoeng

Shannon API

Kakaretso

Bokgoni

Drop‑in Replacement

Ho bitsa mesebetsi

Built‑in Web Search

Dihlahiso tse hlophisitsoeng

Multi‑turn Tools

Phallela

Qalo e potlakileng

Seta base URL ya hao

Eketsa API key ya hao

Romela molaetsa wa hao wa pele

Fomate ya karabo

API Playground

Chat, Responses, Messages

Stream live output

Reuse your key

Netefatso

OpenAI format (e kgothaletswang)

Anthropic format

Dimodelo

Mekhosi ya mesebetsi

Likgetho tsa tool

Karabo ya Function Call

Diphumo tse hlophisitsoeng

Likgetho tsa fomate ya karabo

Phallela

Patlo ya webe

Anthropic

SDKs

OpenAI‑Compatible SDKs

Anthropic‑Compatible SDKs

Diphoso

Fomate ya karabo ya phoso

Rekoto ya diphetoho

Senotlolo sa API

Tshebediso

Shannon Coder (shannon-coder-1)

O lokile ho aha?

Shannon AI API Documentation

Kakaretso

Bokgoni

Drop‑in Replacement

Ho bitsa mesebetsi

Built‑in Web Search

Dihlahiso tse hlophisitsoeng

Multi‑turn Tools

Phallela

Qalo e potlakileng

Seta base URL ya hao

Eketsa API key ya hao

Romela molaetsa wa hao wa pele

Fomate ya karabo

API Playground

Chat, Responses, Messages

Stream live output

Reuse your key

Netefatso

OpenAI format (e kgothaletswang)

Anthropic format

Dimodelo

Mekhosi ya mesebetsi

Likgetho tsa tool

Karabo ya Function Call

Diphumo tse hlophisitsoeng

Likgetho tsa fomate ya karabo

Phallela

Patlo ya webe

Anthropic

SDKs

OpenAI‑Compatible SDKs

Anthropic‑Compatible SDKs

Diphoso

Fomate ya karabo ya phoso

Rekoto ya diphetoho

Senotlolo sa API

Tshebediso

Shannon Coder (shannon-coder-1)

O lokile ho aha?