sdkrouter 0.1.2

Unified SDK for AI services with OpenAI compatibility

SDKRouter

Unified Python SDK for AI services with OpenAI compatibility. Access 300+ LLM models through a single interface, plus vision analysis, CDN, URL shortening, and HTML cleaning tools.

Installation

pip install sdkrouter

Quick Start

from sdkrouter import SDKRouter

client = SDKRouter(api_key="your-api-key")

# OpenAI-compatible chat completions
response = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Features

Chat Completions (OpenAI-Compatible)

# Non-streaming
response = client.chat.completions.create(
    model="anthropic/claude-3.5-sonnet",
    messages=[{"role": "user", "content": "Explain quantum computing"}],
    max_tokens=500,
)

# Streaming
for chunk in client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "Count to 5"}],
    stream=True,
):
    print(chunk.choices[0].delta.content or "", end="")

Structured Output (Pydantic)

Get type-safe responses with automatic JSON schema generation:

from pydantic import BaseModel, Field
from sdkrouter import SDKRouter

class Step(BaseModel):
    explanation: str = Field(description="Explanation of the step")
    result: str = Field(description="Result of this step")

class MathSolution(BaseModel):
    steps: list[Step] = Field(description="Solution steps")
    final_answer: float = Field(description="The final answer")

client = SDKRouter()
result = client.parse(
    model="openai/gpt-4o",
    messages=[
        {"role": "system", "content": "You are a math tutor. Show your work."},
        {"role": "user", "content": "Solve: 3x + 7 = 22"},
    ],
    response_format=MathSolution,
)

solution = result.choices[0].message.parsed
for i, step in enumerate(solution.steps, 1):
    print(f"{i}. {step.explanation} → {step.result}")
print(f"Answer: x = {solution.final_answer}")

Vision Analysis

result = client.vision.analyze(
    image_url="https://example.com/image.jpg",
    prompt="Describe this image",
)
print(result.description)
print(f"Cost: ${result.cost_usd:.6f}")

Quality Tiers

Tier	Model	Use Case
fast	gpt-4o-mini	Quick analysis, lower cost
balanced	gpt-4o	Default, good quality/cost ratio
best	claude-3.5-sonnet	Highest accuracy

result = client.vision.analyze(
    image_url="https://example.com/image.jpg",
    model_quality="best",  # fast | balanced | best
)

OCR (Text Extraction)

result = client.vision.ocr(
    image_url="https://example.com/document.jpg",
    language_hint="en",  # optional
)
print(result.text)

OCR Modes

Mode	Speed	Accuracy	Use Case
tiny	Fastest	Basic	Simple text, receipts
small	Fast	Good	Standard documents
base	Medium	High	Default, balanced
maximum	Slow	Best	Complex layouts, handwriting

result = client.vision.ocr(
    image_url="https://example.com/document.jpg",
    mode="maximum",  # tiny | small | base | maximum
)

CDN File Storage

# Upload bytes
file = client.cdn.upload(
    b"file content",
    filename="document.txt",
    is_public=True,
)
print(file.url)
print(file.short_url)

# Upload from URL
file = client.cdn.upload(
    url="https://example.com/image.png",
    filename="image.png",
)

# List files
files = client.cdn.list(page=1, page_size=20)
for f in files.results:
    print(f"{f.filename}: {f.size_bytes} bytes")

# Get file details
file = client.cdn.get("file-uuid")

# Delete file
client.cdn.delete("file-uuid")

# Statistics
stats = client.cdn.stats()
print(f"Total files: {stats.total_files}")
print(f"Total size: {stats.total_size_bytes} bytes")

URL Shortener

# Create short link
link = client.shortlinks.create(
    target_url="https://example.com/very-long-url-here",
    custom_slug="my-link",  # optional
    max_hits=1000,  # optional limit
)
print(link.short_url)
print(link.code)

# List links
links = client.shortlinks.list()
for link in links.results:
    print(f"{link.code}: {link.hit_count} hits")

# Statistics
stats = client.shortlinks.stats()
print(f"Total links: {stats.total_links}")
print(f"Total hits: {stats.total_hits}")

HTML Cleaner

result = client.cleaner.clean(
    html_content,
    output_format="markdown",  # html | markdown | text
    remove_scripts=True,
    remove_styles=True,
    max_tokens=4000,  # optional token limit
)
print(result.cleaned_html)
print(f"Original: {result.original_size} bytes")
print(f"Cleaned: {result.cleaned_size} bytes")
print(f"Compression: {result.compression_ratio:.1f}x")

Web Search

Search the web using Anthropic's web_search tool:

from sdkrouter import SDKRouter, UserLocation

client = SDKRouter()

# Basic web search
result = client.search.query("latest AI developments 2024")
print(result.content)
print(f"Cost: ${result.cost_usd}")

# View citations
for citation in result.citations:
    print(f"- {citation.title}: {citation.url}")

# Search with domain filtering
result = client.search.query(
    "Python tutorials",
    allowed_domains=["python.org", "realpython.com"],
    blocked_domains=["spam-site.com"],
)

# Localized search
result = client.search.query(
    "weather forecast",
    user_location=UserLocation(country="US", city="San Francisco"),
)

# Fetch and analyze specific URL
result = client.search.fetch(
    "https://example.com/article",
    prompt="Extract the main points from this article",
)

Embeddings

Create text embeddings for semantic search and similarity:

# Single text embedding
result = client.embeddings.create("Hello, world!")
embedding = result.data[0].embedding
print(f"Dimensions: {len(embedding)}")

# Batch embeddings
texts = ["Python programming", "JavaScript coding", "Machine learning"]
result = client.embeddings.create(texts)
for i, item in enumerate(result.data):
    print(f"[{i}] {len(item.embedding)} dimensions")

# Custom model (larger dimensions)
result = client.embeddings.create(
    "Hello, world!",
    model="openai/text-embedding-3-large",  # 3072 dimensions
)

Available Models

Model	Dimensions	Use Case
openai/text-embedding-3-small	1536	Fast, cheap, default
openai/text-embedding-3-large	3072	Higher quality
openai/text-embedding-ada-002	1536	Legacy

LLM Models API

# List available models with pagination
models = client.models.list(page=1, page_size=50)
for m in models.results:
    print(f"{m.model_id}: context={m.context_length}")

# Get model details
model = client.models.get("openai/gpt-4o")
print(f"Context: {model.context_length} tokens")
print(f"Vision: {model.supports_vision}")
print(f"Price: ${model.pricing.prompt}/M input")

# List providers
providers = client.models.providers()
for p in providers.providers:
    print(f"{p.name}: {p.model_count} models")

# Calculate cost
cost = client.models.calculate_cost(
    "openai/gpt-4o",
    input_tokens=1000,
    output_tokens=500,
)
print(f"Input: ${cost.input_cost_usd:.6f}")
print(f"Output: ${cost.output_cost_usd:.6f}")
print(f"Total: ${cost.total_cost_usd:.6f}")

# Statistics
stats = client.models.stats()
print(f"Total models: {stats.total_models}")
print(f"Vision models: {stats.vision_models}")

Token Utilities

from sdkrouter.utils import count_tokens, count_messages_tokens

# Count tokens in text
tokens = count_tokens("Hello, world!")
print(f"Tokens: {tokens}")

# Count tokens in messages
messages = [
    {"role": "system", "content": "You are helpful."},
    {"role": "user", "content": "Hello!"},
]
tokens = count_messages_tokens(messages)
print(f"Message tokens: {tokens}")

Async Support

All features support async operations:

from sdkrouter import AsyncSDKRouter
import asyncio

async def main():
    client = AsyncSDKRouter(api_key="your-api-key")

    # Async chat
    response = await client.chat.completions.create(
        model="openai/gpt-4o",
        messages=[{"role": "user", "content": "Hello!"}]
    )

    # Async structured output
    result = await client.parse(
        model="openai/gpt-4o",
        messages=[...],
        response_format=MyModel,
    )

    # Parallel requests
    results = await asyncio.gather(
        client.vision.analyze(image_url="..."),
        client.cdn.list(),
        client.models.stats(),
    )

asyncio.run(main())

Configuration

from sdkrouter import SDKRouter

# Environment variables (auto-loaded)
# SDKROUTER_API_KEY - API key
# SDKROUTER_BASE_URL - Custom base URL

# Direct configuration
client = SDKRouter(
    api_key="your-key",
    base_url="https://your-server.com",
    timeout=60.0,
    max_retries=3,
)

# Use OpenRouter directly
client = SDKRouter(
    openrouter_api_key="your-openrouter-key",
    use_self_hosted=False,
)

Type Safety

All responses are fully typed with Pydantic models:

from sdkrouter.tools import (
    VisionAnalyzeResponse,
    OCRResponse,
    CDNFileDetail,
    ShortLinkDetail,
    CleanResponse,
    LLMModelDetail,
)

# IDE autocomplete works
result: VisionAnalyzeResponse = client.vision.analyze(...)
result.description  # str
result.cost_usd     # float
result.usage.total_tokens  # int

Examples

See the examples directory for complete working examples:

Example	Description
01_quickstart.py	Quick start with all features
02_chat.py	Chat completions, streaming, multi-turn
03_structured_output.py	Pydantic structured output
04_vision.py	Vision analysis with quality tiers
05_cdn.py	File upload, download, management
06_shortlinks.py	URL shortening
07_models.py	LLM models listing, cost calculation
08_cleaner.py	HTML cleaning and compression
09_keys.py	API key management
10_tokens.py	Token counting utilities
11_async.py	Advanced async patterns
12_search.py	Web search with domain filtering
13_embeddings.py	Text embeddings for similarity

Supported Models

Access 300+ models from providers:

• OpenAI: GPT-4o, GPT-4 Turbo, GPT-4o-mini, o1, o1-mini
• Anthropic: Claude 3.5 Sonnet, Claude 3 Opus, Claude 3 Haiku
• Google: Gemini 2.0 Flash, Gemini 1.5 Pro
• Meta: Llama 3.3, Llama 3.2, Llama 3.1
• Mistral: Mistral Large, Mixtral, Codestral
• DeepSeek: DeepSeek V3, DeepSeek R1
• And many more via OpenRouter

License

MIT