Shannon AI API Dokumentasie

Oorsig

Publieke dokumentasie

Alles wat jy nodig het om te stuur met Shannon se OpenAI- en Anthropic-compatibele API.

Basis-URL OpenAI-versoenbaar

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

Gebruik die Chat Completions API met funksie-aanroepe en streaming.

Basis-URL Anthropic-versoenbaar

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

Claude Messages-formaat met gereedskap en anthropic-version-opskrif.

Opskrifte Verifikasie

Authorization: Bearer <api-key>

Of X-API-Key met anthropic-version vir Claude-styl oproepe.

Toegang Status

Publieke dokumentasie - Sleutel benodig vir oproepe

Streaming, funksie-aanroepe, gestruktureerde uitsette, websoek.

Begin-kontrolelys

+

Rig jou SDK na Shannon

Stel baseURL na die OpenAI- of Anthropic-endpunte hierbo.

Opstelling
+

Voeg jou API-sleutel by

Gebruik Bearer-tokens vir OpenAI-oproepe of X-API-Key + anthropic-version.

Sekuriteit
+

Aktiveer gereedskap en gestruktureerde uitsette

Ondersteun OpenAI tools/funksies, JSON-skema en ingeboude web_search.

Vermoëns
+

Volg gebruik

Sien token- en soekverbruik op hierdie bladsy wanneer jy by jou rekening aangemeld is.

Analitika

Vermoëns

OpenAI + Anthropic

Inruilvervanger vir OpenAI- en Anthropic-API's met ingeboude ondersteuning vir gereedskap, gestruktureerde uitvoer en ingeboude websoektog.

Drop‑in‑vervanging

Versoenbaar

Werk met OpenAI en Anthropic SDK's. Verander net die basis‑URL.

Funksie‑aanroep

Gereedskap

Definieer gereedskap; laat Shannon dit aanroep. Ondersteun auto-, forced- en none‑modusse.

Ingeboude Websoek

Soek

Regstreekse websoek met bronverwysings. Outomaties beskikbaar.

Gestruktureerde Uitsette

JSON

JSON‑modus en afdwinging van JSON‑skema vir betroubare data‑onttrekking.

Veelvoudige‑beurt Gereedskap

Agenties

Outomatiese funksie‑uitvoerlusse. Tot 10 iterasies per versoek.

Stroming

Vinnig

Server‑sent events vir regstreekse token‑stroming.

Vinnige begin

5 minute

Begin in drie stappe. Shannon weerspieël OpenAI- en Anthropic‑kliënte.

Stel jou basis‑URL

Gebruik die OpenAI‑versoenbare eindpunt.

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

Voeg jou API‑sleutel by

Gebruik Bearer‑outentisering in die Authorization‑kop.

Stuur jou eerste boodskap

Kies ’n taal en plaas jou sleutel.

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
  }'

Antwoordformaat

Sukses‑antwoord

{
  "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‑speelgrond

Nuut

Toets die Shannon API direk in jou blaaier. Bou jou versoek, voer dit uit en sien die antwoord in regstreekse tyd.

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.

/af/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.

Probeer Speelgrond V2 Kry jou API-sleutel

Verifikasie

Alle API-versoeke vereis verifikasie met jou Shannon API-sleutel.

OpenAI-formaat (Aanbeveel)

HTTP

Authorization: Bearer YOUR_API_KEY

Anthropic

HTTP

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

Modelle

Shannon bied verskeie modelle geoptimaliseer vir verskillende gebruiksgevalle.

shannon-1.6-lite Shannon 1.6 Lite

Vinnige, doeltreffende antwoorde vir alledaagse take

Konteks 128K

Beste vir Chat, V&A, inhoudgenerering

shannon-1.6-pro Shannon 1.6 Pro

Gevorderde redenasie vir komplekse probleme

Konteks 128K

Beste vir Analise, navorsing, komplekse take

shannon-2-lite Shannon 2 Lite

Konteks 128K

Beste vir

shannon-2-pro Shannon 2 Pro

Konteks 128K

Beste vir

shannon-coder-1 Shannon Coder

Geoptimaliseer vir Claude Code CLI met oproep-gebaseerde kwota

Konteks 128K

Beste vir Kodegenerering, gebruik van gereedskap, CLI-integrasie

Oproep-gebaseerde kwota

Funksie-oproepe

Definieer gereedskap wat Shannon kan aanroep om aksies uit te voer of inligting te verkry.

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);
}

Gereedskap-keuse opsies

"auto" Model besluit of n funksie geroep moet word (verstek)

"none" Skakel funksie-aanroepe vir hierdie versoek af

{"type": "function", "function": {"name": "..."}} Forseer n spesifieke funksie-oproep

Funksie-oproep respons

Wanneer model n funksie oproep

{
  "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"
    }
  ]
}

Gestruktureerde uitvoer

Dwing Shannon om met geldige JSON te antwoord wat by jou skema pas.

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" }

Responsformaat-opsies

{"type": "json_object"} Forseer geldige JSON-uitset (geen spesifieke skema)

{"type": "json_schema", "json_schema": {...}} Forseer uitset wat by jou presiese skema pas

Stroming

Aktiveer regstreekse token-stroming met Server-Sent Events vir responsiewe UI's.

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);
}

Wenk: Streaming-antwoorde kom as Server-Sent Events aan. Elke blok bevat n delta met gedeeltelike inhoud.

Websoektog

Shannon sluit 'n ingeboude web_search-funksie in wat outomaties beskikbaar is.

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

Pro-wenk: Websoek-resultate sluit aanhalings in. Shannon sal outomaties bronne aanhaal.

Anthropic

Shannon ondersteun ook Anthropic se Messages API-formaat.

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);

Vereiste opskrif: Anthropic-formaat vereis anthropic-version: 2023-06-01.

SDK's

Versoenbaar

Gebruik enige OpenAI- of Anthropic-SDK — verander net die basis-URL.

OpenAI-Compatible SDKs

SDK Python

Amptelike OpenAI Python SDK - werk met Shannon

pip install openai

Bekyk dokumentasie ->

SDK JavaScript / TypeScript

Amptelike OpenAI Node.js SDK - werk met Shannon

npm install openai

Bekyk dokumentasie ->

SDK Go

Gemeenskaps-Go-kliënt vir OpenAI-versoenbare APIs

go get github.com/sashabaranov/go-openai

Bekyk dokumentasie ->

SDK Ruby

Gemeenskaps-Ruby-kliënt vir OpenAI-versoenbare APIs

gem install ruby-openai

Bekyk dokumentasie ->

SDK PHP

Gemeenskaps-PHP-kliënt vir OpenAI-versoenbare APIs

composer require openai-php/client

Bekyk dokumentasie ->

SDK Rust

Asinchroniese Rust-kliënt vir OpenAI-versoenbare APIs

cargo add async-openai

Bekyk dokumentasie ->

Anthropic-Compatible SDKs

SDK Python (Anthropic)

Amptelike Anthropic Python SDK - werk met Shannon

pip install anthropic

Bekyk dokumentasie ->

SDK TypeScript (Anthropic)

Amptelike Anthropic TypeScript SDK - werk met Shannon

npm install @anthropic-ai/sdk

Bekyk dokumentasie ->

Fouthantering

Shannon gebruik standaard HTTP‑statuskodes en gee gedetailleerde foutboodskappe terug.

400 Ongeldige versoek Ongeldige versoekformaat of parameters

401 Ongemagtig Ongeldige of ontbrekende API‑sleutel

402 Kwota oorskry Token- of soekkwota oorskry

429 Tempo beperk Te veel versoeke, vertraag

500 Bedienerfout Interne fout, probeer later weer

Foutantwoordformaat

Foutantwoord

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

Veranderingslog

LOG

Onlangse opdaterings en verbeterings aan die Shannon API.

v2.1.0

2025-01-03

Nuut shannon-coder-1 model bygevoeg vir Claude Code CLI-integrasie
Nuut Oproep-gebaseerde kwotastelsel vir Coder-model
Verbeter Betroubaarheid van funksie-aanroepe verbeter

v2.0.0

2024-12-15

Nuut Anthropic Messages API-versoenbaarheid bygevoeg
Nuut Multi-beurt gereedskapuitvoering (tot 10 iterasies)
Nuut JSON Schema-responsformaat ondersteuning
Verbeter Websoek verbeter met beter aanhalings

v1.5.0

2024-11-20

Nuut shannon-deep-dapo model bygevoeg vir komplekse redenasie
Nuut Ingeboude web_search-funksie
Verbeter Laer latensie vir streaming-antwoorde

v1.0.0

2024-10-01

Nuut Aanvanklike API-vrystelling
Nuut OpenAI-versoenbare chat completions-endpunt
Nuut Funksie-aanroep ondersteuning
Nuut Streaming via Server-Sent Events

Jou API‑sleutel

Toegang

Gebruik Bearer-tokens vir OpenAI-oproepe of X-API-Key + anthropic-version.

YOUR_API_KEY

Kry jou API-sleutel

Hou jou API‑sleutel geheim. Hergenereer skep ’n nuwe sleutel en maak die oue ongeldig.

Jou gebruik

Sien token- en soekverbruik op hierdie bladsy wanneer jy by jou rekening aangemeld is.

-- API‑oproepe

-- Gebruikte tokens

Shannon API

Oorsig

Vermoëns

Drop‑in‑vervanging

Funksie‑aanroep

Ingeboude Websoek

Gestruktureerde Uitsette

Veelvoudige‑beurt Gereedskap

Stroming

Vinnige begin

Stel jou basis‑URL

Voeg jou API‑sleutel by

Stuur jou eerste boodskap

Antwoordformaat

API‑speelgrond

Chat, Responses, Messages

Stream live output

Reuse your key

Verifikasie

OpenAI-formaat (Aanbeveel)

Anthropic

Modelle

Funksie-oproepe

Gereedskap-keuse opsies

Funksie-oproep respons

Gestruktureerde uitvoer

Responsformaat-opsies

Stroming

Websoektog

Anthropic

SDK's

OpenAI-Compatible SDKs

Anthropic-Compatible SDKs

Fouthantering

Foutantwoordformaat

Veranderingslog

Jou API‑sleutel

Jou gebruik

Shannon Coder (shannon-coder-1)

Gereed om te bou?

Shannon AI API Documentation

Oorsig

Vermoëns

Drop‑in‑vervanging

Funksie‑aanroep

Ingeboude Websoek

Gestruktureerde Uitsette

Veelvoudige‑beurt Gereedskap

Stroming

Vinnige begin

Stel jou basis‑URL

Voeg jou API‑sleutel by

Stuur jou eerste boodskap

Antwoordformaat

API‑speelgrond

Chat, Responses, Messages

Stream live output

Reuse your key

Verifikasie

OpenAI-formaat (Aanbeveel)

Anthropic

Modelle

Funksie-oproepe

Gereedskap-keuse opsies

Funksie-oproep respons

Gestruktureerde uitvoer

Responsformaat-opsies

Stroming

Websoektog

Anthropic

SDK's

OpenAI-Compatible SDKs

Anthropic-Compatible SDKs

Fouthantering

Foutantwoordformaat

Veranderingslog

Jou API‑sleutel

Jou gebruik

Shannon Coder (shannon-coder-1)

Gereed om te bou?