Shannon API
OpenAI & Anthropic compatible AI API with function calling, web search, and structured outputs.
🧭 Overview
Public docsEverything you need to ship with Shannon's OpenAI and Anthropic compatible API. Browse publicly, then sign in to generate or rotate your key.
http://127.0.0.1:5001/shannonai/us-central1/v1/chat/completionsUse the Chat Completions API with function calling and streaming.
http://127.0.0.1:5001/shannonai/us-central1/v1/completeClaude Messages format with tools and anthropic-version header.
Authorization: Bearer <your-key>Or X-API-Key with anthropic-version for Claude-style calls.
Public docs · Key required to callStreaming, function calling, structured outputs, web search.
- SetupPoint your SDK at ShannonSet baseURL to the OpenAI or Anthropic endpoints above.
- SecurityAttach your API keyUse Bearer tokens for OpenAI calls or X-API-Key + anthropic-version.
- CapabilitiesEnable tools & structured outputsSupports OpenAI tools/functions, JSON schema, and built-in web_search.
- AnalyticsTrack usageView token and search consumption on this page when signed in to your account.
This page stays public. Use it to explore endpoints, then sign in to generate or rotate your API key and monitor usage.
⚡ Capabilities at a Glance
OpenAI + AnthropicDrop-in replacement for OpenAI and Anthropic APIs with native support for tools, structured outputs, and built-in web search.
Drop-in Replacement
CompatibleWorks with OpenAI and Anthropic SDKs. Just change the base URL.
Function Calling
ToolsDefine tools, let Shannon call them. Supports auto, forced, and none modes.
Built-in Web Search
SearchReal-time web search with source citations. Automatically available.
Structured Outputs
JSONJSON mode and JSON Schema enforcement for reliable data extraction.
Multi-turn Tools
AgenticAutomatic function execution loops. Up to 10 iterations per request.
Streaming
FastServer-sent events for real-time token streaming.
🚀 Quick Start
5 minutesGet started in three steps. Shannon mirrors OpenAI and Anthropic clients, so you only need to swap the base URL and attach your API key.
Set your base URL
Use the OpenAI-compatible endpoint for chat completions and tools.
http://127.0.0.1:5001/shannonai/us-central1/v1/chat/completionsAdd your API key
Use Bearer auth in the Authorization header to authenticate every request.
Authorization: Bearer YOUR_API_KEYSend your first message
Pick a language example and swap in your key. Streaming and tools are on.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="http://127.0.0.1:5001/shannonai/us-central1/v1"
)
response = client.chat.completions.create(
model="shannon-balanced-grpo",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello, Shannon!"}
],
max_tokens=1024
)
print(response.choices[0].message.content)Response format
{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"created": 1234567890,
"model": "shannon-balanced-grpo",
"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
}
}🔐 Authentication
All API requests require authentication using your Shannon API key. Sign in to get your API key.
OpenAI Format (Recommended)
Use the Authorization header with Bearer token:
Authorization: Bearer YOUR_API_KEYAnthropic Format
Use the X-API-Key header along with the version header:
X-API-Key: YOUR_API_KEY
anthropic-version: 2023-06-01🤖 Models
Shannon offers multiple models optimized for different use cases. All models support function calling, structured outputs, and web search.
shannon-balanced-grpoBalancedFast, efficient responses for everyday tasks
shannon-deep-dapoDeepAdvanced reasoning for complex problems
Model Selection
Specify the model in your request:
{
"model": "shannon-balanced-grpo", // or "shannon-deep-dapo"
"messages": [...]
}🛠️ Function Calling
Define tools that Shannon can call to perform actions or retrieve information. Supports OpenAI's tools format and legacy functions format.
Defining Tools
from openai import OpenAI
import json
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="http://127.0.0.1:5001/shannonai/us-central1/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-balanced-grpo",
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}")Tool Choice Options
Function Call Response
{
"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"
}
]
}📋 Structured Outputs
Force Shannon to respond with valid JSON that matches your schema. Perfect for data extraction, API integrations, and automation workflows.
JSON Schema Mode
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="http://127.0.0.1:5001/shannonai/us-central1/v1"
)
# Force JSON output with schema
response = client.chat.completions.create(
model="shannon-balanced-grpo",
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"}Response Format Options
🔍 Built-in Web Search
Shannon includes a built-in web_search function that's automatically available when you have search quota. Get real-time information with source citations.
Automatic Web Search
Shannon automatically searches the web when questions require current information. You can also explicitly define the web_search tool:
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="http://127.0.0.1:5001/shannonai/us-central1/v1"
)
# Web search is automatically available!
# Shannon will use it when needed for current information
response = client.chat.completions.create(
model="shannon-balanced-grpo",
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🔀 Anthropic Format
Shannon also supports Anthropic's Messages API format for tool use. Use the Anthropic SDK with Shannon's endpoint.
Endpoint
http://127.0.0.1:5001/shannonai/us-central1/v1/completeAnthropic SDK Example
import anthropic
client = anthropic.Anthropic(
api_key="YOUR_API_KEY",
base_url="http://127.0.0.1:5001/shannonai/us-central1"
)
response = client.messages.create(
model="shannon-balanced-grpo",
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)anthropic-version: 2023-06-01 header.⚠️ Error Handling
Shannon uses standard HTTP status codes and returns detailed error messages in both OpenAI and Anthropic formats.
Error Codes
Error Response Format
{
"error": {
"message": "Invalid API key provided",
"type": "authentication_error",
"code": "invalid_api_key"
}
}Ready to Build?
Get your API key and start building with Shannon AI today. Full OpenAI and Anthropic SDK compatibility.