Sostituzzjoni drop-in
KompatibbliJaħdem ma' SDKs OpenAI u Anthropic. Ibdel biss il-base URL.
Dokumentazzjoni tal-API
Shannon API
API ta' AI kompatibbli ma' OpenAI u Anthropic b'sejħiet ta' funzjonijiet, tfittxija web, u outputs strutturati.
Shannon AI API Documentation
Ħarsa ġenerali
Dokumenti pubbliċiDak kollu li għandek bżonn biex tibni b'API kompatibbli ma' OpenAI u Anthropic ta' Shannon.
https://api.shannon-ai.com/v1/chat/completions Uża l-API Chat Completions b'sejħiet ta' funzjonijiet u streaming.
https://api.shannon-ai.com/v1/messages Format Claude Messages b'għodod u header anthropic-version.
Authorization: Bearer <api-key> Jew X-API-Key b'anthropic-version għal sejħiet stil Claude.
Dokumenti pubbliċi - jeħtieġ ċavetta biex issejjaħ Streaming, sejħiet ta' funzjonijiet, outputs strutturati, tfittxija web.
Lista għat-tnedija
- + KonfigurazzjoniIppunta l-SDK tiegħek lejn ShannonIssettja baseURL lejn l-endpoints OpenAI jew Anthropic ta' hawn fuq.
- + SigurtàWaħħal iċ-ċavetta tal-API tiegħekUża Bearer tokens għal sejħiet OpenAI jew X-API-Key + anthropic-version.
- + KapaċitajietIppossibilita għodod u outputs strutturatiJappoġġja għodod/funzjonijiet OpenAI, JSON schema, u web_search built-in.
- + AnalitikaSegwi l-użuAra l-konsum ta' tokens u t-tiftix f'din il-paġna meta tidħol fil-kont tiegħek.
Kapaċitajiet
OpenAI + AnthropicSostituzzjoni drop-in għall-APIs OpenAI u Anthropic b'appoġġ nattiv għal għodod, outputs strutturati, u tfittxija web built-in.
Sejħiet ta' Funzjonijiet
GħododIddefinixxi għodod, ħalli Shannon isejħilhom. Jappoġġja modi auto, forced, u none.
Tfittxija Web inkorporata
TfittxijaTfittxija web f'ħin reali b'ċitazzjonijiet tas-sorsi. Disponibbli awtomatikament.
Outputs Strutturati
JSONModalità JSON u infurzar tal-JSON Schema għal estrazzjoni affidabbli tad-dejta.
Għodod Multi-turn
AġentikuLoops awtomatiċi ta' eżekuzzjoni ta' funzjonijiet. Sa 10 iterazzjonijiet għal kull talba.
Streaming
MgħaġġelServer-sent events għal streaming ta' tokens f'ħin reali.
Bidu Malajr
5 minutiIbda fi tliet passi. Shannon jirrifletti l-klijenti OpenAI u Anthropic.
1
Issettja l-base URL tiegħek
Uża l-endpoint kompatibbli ma' OpenAI.
https://api.shannon-ai.com/v1/chat/completions 2
Żid iċ-ċavetta tal-API tiegħek
Uża Bearer auth fl-header Authorization.
3
Ibgħat l-ewwel messaġġ tiegħek
Agħżel lingwa u ibdel fiċ-ċavetta tiegħek.
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); Go
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
}'Format tar-risposta
Risposta ta' suċċess
{
"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
}
}Playground tal-API
ĠdidIttesta l-API ta' Shannon direttament fil-browser tiegħek. Ibni t-talba tiegħek, ħaddimha, u ara r-risposta f'ħin reali.
1
Chat, Responses, Messages
Switch across OpenAI Chat Completions, Responses, and Anthropic Messages without leaving the playground.
2
Stream live output
Run real requests, inspect raw JSON, and view stream events from the same operator console.
3
Reuse your key
Signed-in users can pull their Shannon API key straight into the dedicated playground workspace.
/mt/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.
Awtentikazzjoni
It-talbiet kollha tal-API jeħtieġu awtentikazzjoni bl-użu taċ-ċavetta tal-API ta' Shannon.
Format OpenAI (Rakkomandat)
HTTP
Authorization: Bearer YOUR_API_KEYFormat Anthropic
HTTP
X-API-Key: YOUR_API_KEY
anthropic-version: 2023-06-01Mudelli
Shannon joffri diversi mudelli ottimizzati għal użi differenti.
shannon-1.6-lite Shannon 1.6 Lite Risposti rapidi u effiċjenti għall-kompiti ta' kuljum
shannon-1.6-pro Shannon 1.6 Pro Raġunament avvanzat għal problemi kumplessi
shannon-2-lite Shannon 2 Lite
shannon-2-pro Shannon 2 Pro
shannon-coder-1 Shannon Coder Ottimizzat għal Claude Code CLI b'kwota bbażata fuq sejħiet
Kwota bbażata fuq sejħiet
Sejħiet ta' Funzjonijiet
Iddefinixxi għodod li Shannon jista' jsejjaħ biex iwettaq azzjonijiet jew jiġbor informazzjoni.
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);
}Għażliet tal-Għodod
Risposta ta' Sejħa ta' Funzjoni
Meta mudell isejjaħ funzjoni
{
"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"
}
]
}Outputs Strutturati
Sfurza lil Shannon biex iwieġeb b'JSON validu li jaqbel mal-iskema tiegħek.
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" }Għażliet tal-Format tar-Risposta
Streaming
Ippermetti streaming ta' tokens f'ħin reali b'Server-Sent Events għal interfaces reattivi.
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);
} Parir: Ir-risposti streaming jaslu bħala Server-Sent Events. Kull ċokk jinkludi delta b'kontenut parzjali.
Tfittxija Web inkorporata
Shannon jinkludi funzjoni web_search built-in li hija disponibbli awtomatikament.
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 Parir Pro: Ir-riżultati tat-tiftix web jinkludu ċitazzjonijiet. Shannon se jiċċita s-sorsi awtomatikament.
Format Anthropic
Shannon jappoġġja wkoll il-format tal-API Messages ta' Anthropic.
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 meħtieġ: Format Anthropic jeħtieġ anthropic-version: 2023-06-01.
CLI Coding Agents
NEWUse Shannon as the AI backend for popular CLI coding agents. Read files, edit code, run tests — all powered by Shannon's API.
CLI Claude Code
Anthropic's official CLI coding agent. Point it at Shannon to use as your AI backend for reading, editing, and running code directly in your terminal.
ANTHROPIC_BASE_URL=https://api.shannon-ai.com ANTHROPIC_API_KEY=sk-YOUR_KEY claude --bare CLI Codex CLI
OpenAI's open-source coding agent. Uses the Responses API for multi-turn tool use, file editing, and shell commands — all routed through Shannon.
OPENAI_BASE_URL=https://api.shannon-ai.com/v1 OPENAI_API_KEY=sk-YOUR_KEY codex Claude Code
Anthropic's official CLI coding agent. Set two environment variables and launch with --bare to skip Anthropic account login.
Bash
# Install Claude Code (requires Node.js 18+)
npm install -g @anthropic-ai/claude-code
# Connect to Shannon AI as backend
export ANTHROPIC_BASE_URL=https://api.shannon-ai.com
export ANTHROPIC_API_KEY=sk-YOUR_API_KEY
# Launch Claude Code in bare mode (no Anthropic account needed)
claude --bare
# Or run a one-shot command
claude --bare -p "Explain this codebase"
# Claude Code will use Shannon's Anthropic-compatible API
# for all AI operations: reading files, editing code,
# running tests, and multi-turn tool use. Shell Config
# Alternative: set env vars permanently in your shell profile
# ~/.bashrc or ~/.zshrc
export ANTHROPIC_BASE_URL=https://api.shannon-ai.com
export ANTHROPIC_API_KEY=sk-YOUR_API_KEY
# Then just run:
claude --bare
# Supported features through Shannon:
# - Multi-turn conversations with full context
# - File reading and editing (tool use)
# - Shell command execution
# - Streaming responses
# - All Claude Code slash commands (/compact, /clear, etc.)Codex CLI
OpenAI's open-source coding agent. Uses the Responses API for multi-turn tool use, file editing, and shell commands.
Bash
# Install Codex CLI
npm install -g @openai/codex
# Connect to Shannon AI as backend
export OPENAI_BASE_URL=https://api.shannon-ai.com/v1
export OPENAI_API_KEY=sk-YOUR_API_KEY
# Launch Codex
codex
# Or run a one-shot command
codex "fix the bug in main.py"
# Codex uses the Responses API (POST /v1/responses)
# Shannon handles tool calls including:
# - Reading and writing files
# - Running shell commands
# - Multi-turn function calling Shell Config
# Alternative: set env vars permanently
# ~/.bashrc or ~/.zshrc
export OPENAI_BASE_URL=https://api.shannon-ai.com/v1
export OPENAI_API_KEY=sk-YOUR_API_KEY
# Then just run:
codex
# Supported features through Shannon:
# - Responses API with full tool use
# - Function calling (file read/write, shell exec)
# - Streaming with real-time output
# - Multi-turn conversations
# - All Codex approval modes (suggest, auto-edit, full-auto) How It Works: Both tools send standard API requests (Anthropic Messages or OpenAI Responses) to Shannon. Shannon routes them through Gemini with full tool-use support. No Anthropic or OpenAI account needed — just your Shannon API key.
SDKs
KompatibbliUża kwalunkwe SDK ta' OpenAI jew Anthropic — ibdel biss il-base URL.
SDKs kompatibbli ma' OpenAI
SDK Python
SDK uffiċjali ta' OpenAI għal Python — jaħdem ma' Shannon
pip install openai SDK JavaScript / TypeScript
SDK uffiċjali ta' OpenAI għal Node.js — jaħdem ma' Shannon
npm install openai SDK Go
Klijent Go tal-komunità għal APIs kompatibbli ma' OpenAI
go get github.com/sashabaranov/go-openai SDK Ruby
Klijent Ruby tal-komunità għal APIs kompatibbli ma' OpenAI
gem install ruby-openai SDK PHP
Klijent PHP tal-komunità għal APIs kompatibbli ma' OpenAI
composer require openai-php/client SDK Rust
Klijent Rust async għal APIs kompatibbli ma' OpenAI
cargo add async-openai SDKs kompatibbli ma' Anthropic
SDK Python (Anthropic)
SDK uffiċjali ta' Anthropic għal Python — jaħdem ma' Shannon
pip install anthropic SDK TypeScript (Anthropic)
SDK uffiċjali ta' Anthropic għal TypeScript — jaħdem ma' Shannon
npm install @anthropic-ai/sdk Ġestjoni tal-iżbalji
Shannon juża kodiċijiet standard HTTP u jirritorna messaġġi ta' żball dettaljati.
400 Talba ħażina Format jew parametri tat-talba invalidi
401 Mhux awtorizzat Ċavetta tal-API invalida jew nieqsa
402 Kwota eżawrita Kwota ta' tokens jew tiftix eżawrita
429 Limitazzjoni tar-rata Wisq talbiet, naqqas il-veloċità
500 Żball tas-server Żball intern, erġa' pprova aktar tard
Format tar-risposta tal-iżball
Risposta ta' żball
{
"error": {
"message": "Invalid API key provided",
"type": "authentication_error",
"code": "invalid_api_key"
}
}Log tal-bidliet
LOGAġġornamenti u titjib reċenti għall-API Shannon.
v2.2.0
2026-03-28 - Ġdid Claude Code support — use Shannon as your Anthropic backend for the official CLI coding agent
- Ġdid Codex CLI support — full Responses API with multi-turn tool use for OpenAI's coding agent
- Mtejjeb Anthropic streaming format fixes — proper content_block lifecycle, tool_use deltas, toolu_ prefixes
- Mtejjeb Schema sanitization for Gemini — strips $schema, additionalProperties, $ref and other unsupported fields from tool schemas
v2.1.0
2025-01-03 - Ġdid Miżjud il-mudell shannon-coder-1 għal integrazzjoni ma' Claude Code CLI
- Ġdid Sistema ta' kwota bbażata fuq sejħiet għall-mudell Coder
- Mtejjeb Affidabbiltà mtejba tas-sejħiet ta' funzjonijiet
v2.0.0
2024-12-15 - Ġdid Miżjuda kompatibilità mal-API Messages ta' Anthropic
- Ġdid Eżekuzzjoni ta' għodod multi-turn (sa 10 iterazzjonijiet)
- Ġdid Appoġġ għall-format ta' risposta JSON Schema
- Mtejjeb Tfittxija web imtejba b'ċitazzjonijiet aħjar
v1.5.0
2024-11-20 - Ġdid Miżjud il-mudell shannon-deep-dapo għal raġunament kumpless
- Ġdid Funzjoni web_search built-in
- Mtejjeb Naqqset il-latenza għal risposti streaming
v1.0.0
2024-10-01 - Ġdid Rilaxx inizjali tal-API
- Ġdid Endpoint chat completions kompatibbli ma' OpenAI
- Ġdid Appoġġ għal sejħiet ta' funzjonijiet
- Ġdid Streaming permezz ta' Server-Sent Events
Iċ-ċavetta tal-API tiegħek
Aċċess Uża Bearer tokens għal sejħiet OpenAI jew X-API-Key + anthropic-version.
YOUR_API_KEY Żomm iċ-ċavetta tal-API tiegħek sigrieta. Il-ġenerazzjoni mill-ġdid toħloq ċavetta ġdida u tħassar il-qadima.
L-użu tiegħek
Ara l-konsum ta' tokens u t-tiftix f'din il-paġna meta tidħol fil-kont tiegħek.
-- Sejħiet tal-API
-- Tokens Użati
Shannon Coder (shannon-coder-1)
Kwota bbażata fuq sejħiet għal Shannon Coder (shannon-coder-1). Tirrissettja kull 4 siegħa.
0 Sejħiet Użati
0 Sejħiet Fadal
Lest biex tibni?
Ikseb iċ-ċavetta tal-API tiegħek u ibda tibni ma' Shannon AI illum.
Tfittxijiet popolari:
Ipprova kliem ewlieni differenti