Python

Python SDK

Python SDK for Tinfoil’s secure AI inference API
GitHub: tinfoil-python

Overview

The Tinfoil Python SDK provides a drop-in replacement for the official OpenAI Python client, adding automatic attestation verification for secure AI inference. It maintains full compatibility with the OpenAI interface while ensuring your data remains private and secure. View the source code on GitHub.

Installation

pip install tinfoil

Migration from OpenAI

Migrating from OpenAI to Tinfoil is straightforward:

# Before (OpenAI)
- import os
- from openai import OpenAI
- client = OpenAI(api_key=os.getenv("OPENAI_API_KEY"))

# After (Tinfoil)
+ import os
+ from tinfoil import TinfoilAI
+ client = TinfoilAI(api_key=os.getenv("TINFOIL_API_KEY"))

All method signatures and response formats remain the same, ensuring a seamless transition.

Model Examples

Below are specific examples for each supported model. Click on any model to see its configuration and usage example.

Chat Models

DeepSeek R1 - deepseek-r1-0528

import os
from tinfoil import TinfoilAI

# Configure client for DeepSeek R1
client = TinfoilAI(
    api_key=os.getenv("TINFOIL_API_KEY")
)

# Example: Complex reasoning task
response = client.chat.completions.create(
    model="deepseek-r1-0528",
    messages=[
        {
            "role": "system",
            "content": "You are an expert at solving complex mathematical problems step by step."
        },
        {
            "role": "user",
            "content": "Solve this step by step: If a train travels 120 miles in 2 hours, and then increases its speed by 25% for the next 3 hours, how far does it travel in total?"
        }
    ],
    temperature=0.1
)

print(response.choices[0].message.content)

Mistral Small 3.1 24B - mistral-small-3-1-24b

import os
from tinfoil import TinfoilAI

# Configure client for Mistral Small 3.1 24B
client = TinfoilAI(
    api_key=os.getenv("TINFOIL_API_KEY")
)

# Example: Multilingual conversation
response = client.chat.completions.create(
    model="mistral-small-3-1-24b",
    messages=[
        {
            "role": "user",
            "content": "Explain the concept of machine learning in both English and French."
        }
    ],
    temperature=0.7
)

print(response.choices[0].message.content)

Llama 3.3 70B - llama3-3-70b

import os
from tinfoil import TinfoilAI

# Configure client for Llama 3.3 70B
client = TinfoilAI(
    api_key=os.getenv("TINFOIL_API_KEY")
)

# Example: Conversational AI
response = client.chat.completions.create(
    model="llama3-3-70b",
    messages=[
        {
            "role": "system",
            "content": "You are a helpful assistant that provides detailed explanations."
        },
        {
            "role": "user",
            "content": "What are the key differences between renewable and non-renewable energy sources?"
        }
    ],
    temperature=0.8
)

print(response.choices[0].message.content)

Qwen 2.5 72B - qwen2-5-72b

import os
from tinfoil import TinfoilAI

# Configure client for Qwen 2.5 72B
client = TinfoilAI(
    api_key=os.getenv("TINFOIL_API_KEY")
)

# Example: Code generation and analysis
response = client.chat.completions.create(
    model="qwen2-5-72b",
    messages=[
        {
            "role": "user",
            "content": "Write a Python function to calculate the Fibonacci sequence up to n terms, then explain how it works."
        }
    ],
    temperature=0.3
)

print(response.choices[0].message.content)

Audio Models

Whisper Large V3 Turbo - whisper-large-v3-turbo

import os
from tinfoil import TinfoilAI

# Configure client for Whisper Large V3 Turbo
client = TinfoilAI(
    api_key=os.getenv("TINFOIL_API_KEY")
)

# Example: Audio transcription
with open("meeting_recording.mp3", "rb") as audio_file:
    transcription = client.audio.transcriptions.create(
        file=audio_file,
        model="whisper-large-v3-turbo",
        language="en",  # Optional: specify language for better accuracy
        prompt="This is a business meeting discussing quarterly results"  # Optional: provide context
    )

print("Transcription:", transcription.text)

Kokoro - kokoro

import os
from tinfoil import TinfoilAI

# Configure client for Kokoro TTS
client = TinfoilAI(
    api_key=os.getenv("TINFOIL_API_KEY")
)

# Example: Text-to-speech with different voices
text_to_speak = "Welcome to Tinfoil's secure AI platform. Your data remains private and protected."

# Single voice
response = client.audio.speech.create(
    model="kokoro",
    voice="af_sky",
    input=text_to_speak,
    response_format="mp3"
)
response.write_to_file("speech_single.mp3")

# Combined voices for richer sound
response = client.audio.speech.create(
    model="kokoro",
    voice="af_sky+af_bella",
    input=text_to_speak,
    response_format="mp3"
)
response.write_to_file("speech_combined.mp3")

print("Speech files generated successfully!")

Embedding Models

Nomic Embed Text - nomic-embed-text

import os
from tinfoil import TinfoilAI
import numpy as np

# Configure client for Nomic Embed Text
client = TinfoilAI(
    api_key=os.getenv("TINFOIL_API_KEY")
)

# Example: Generate embeddings for similarity search
documents = [
    "Artificial intelligence is transforming modern technology.",
    "Machine learning enables computers to learn from data.",
    "The weather today is sunny and warm.",
    "Deep learning uses neural networks with multiple layers."
]

# Generate embeddings for all documents
embeddings = []
for doc in documents:
    response = client.embeddings.create(
        model="nomic-embed-text",
        input=doc
    )
    embeddings.append(response.data[0].embedding)

# Calculate similarity between first two documents
emb1 = np.array(embeddings[0])
emb2 = np.array(embeddings[1])
similarity = np.dot(emb1, emb2) / (np.linalg.norm(emb1) * np.linalg.norm(emb2))

print(f"Similarity between first two AI-related documents: {similarity:.3f}")
print(f"Embedding dimension: {len(embeddings[0])}")

Async Usage

Simply import AsyncTinfoilAI instead of TinfoilAI and use await with each API call:

import os
import asyncio
from tinfoil import AsyncTinfoilAI

client = AsyncTinfoilAI(
    api_key=os.getenv("TINFOIL_API_KEY")
)

async def main() -> None:
    # start a streaming chat completion
    stream = await client.chat.completions.create(
        model="<MODEL_NAME>",
        messages=[{"role": "user", "content": "Say this is a test"}],
        stream=True,
    )
    async for chunk in stream:
        if chunk.choices and chunk.choices[0].delta.content is not None:
            print(chunk.choices[0].delta.content, end="", flush=True)
    print()

asyncio.run(main())

Functionality between the synchronous and asynchronous clients is otherwise identical.

API Documentation

This library is a drop-in replacement for the official OpenAI Python client that can be used with Tinfoil. All methods and types are identical. See the OpenAI Python client documentation for complete API usage and documentation.

Guides

Tool Calling

Learn how to use function calling capabilities with AI models.

Structured Outputs

Use JSON schema validation for reliable data extraction.

Image Processing

Process images with multimodal AI models.

Document Processing

Upload and process documents securely.

Getting Started

Models

SDKs

Guides

Enclave Verification

Tutorials

Resources

Python SDK

Overview

Installation

Migration from OpenAI

Model Examples

Chat Models

Audio Models

Embedding Models

Async Usage

API Documentation

Guides

Tool Calling

Structured Outputs

Image Processing

Document Processing

Getting Started

Models

SDKs

Guides

Enclave Verification

Tutorials

Resources

Python SDK

​Overview

​Installation

​Migration from OpenAI

​Model Examples

​Chat Models

​Audio Models

​Embedding Models

​Async Usage

​API Documentation

​Guides

Tool Calling

Structured Outputs

Image Processing

Document Processing

Overview

Installation

Migration from OpenAI

Model Examples

Chat Models

Audio Models

Embedding Models

Async Usage

API Documentation

Guides