Quick Reference — All models listed below are accessible through any of our SDKs. See the SDK pages for language-specific usage examples.

​
Available Models

Below is a list of all models currently supported on Tinfoil, including their model IDs, types, repositories, and enclave addresses.

Don’t see the model you need? Contact us at [email protected] and we’ll work with you to add support for your desired model.

​
Chat Models

DeepSeek R1 70B
deepseek-r1-70b

Repository:
tinfoilsh/confidential-deepseek-r1-70b-prod

Enclave:
deepseek-r1-70b-p.model.tinfoil.sh

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

Repository:
tinfoilsh/confidential-mistral-small-3-1-24b-prod

Enclave:
mistral-small-3-1-24b-p.model.tinfoil.sh

Llama 3.3 70B
llama3-3-70b

Repository:
tinfoilsh/confidential-llama3-3-70b-prod

Enclave:
llama3-3-70b-p.model.tinfoil.sh

Qwen 2.5 72B
qwen2-5-72b

Repository:
tinfoilsh/confidential-qwen2.5-72b

Enclave:
qwen2-5-72b-p.model.tinfoil.sh

Description: Chat models support conversational AI capabilities through the standard chat completions API. All chat models follow the OpenAI chat completion format.

​
Audio Models

Whisper Large V3 Turbo
whisper-large-v3-turbo

Repository:
tinfoilsh/confidential-audio-processing

Enclave:
audio-processing.model.tinfoil.sh

Audio Format: Currently supports .mp3 files only

Kokoro
kokoro

Repository:
tinfoilsh/confidential-audio-processing

Enclave:
audio-processing.model.tinfoil.sh

Description: Audio models provide speech-to-text transcription and text-to-speech synthesis capabilities. Supporting both audio file transcription and high-quality speech generation.

​
Embedding Models

Nomic Embed Text
nomic-embed-text

Repository:
tinfoilsh/confidential-nomic-embed-text

Enclave:
nomic-embed-text.model.tinfoil.sh

Description: Embedding models convert text into high-dimensional vectors for semantic search, similarity comparisons, and other vector-based operations.

​
Model Capabilities

​
DeepSeek R1 70B

  • Type: Chat
  • Context: 128K tokens
  • Strengths: Advanced reasoning, complex problem-solving, mathematical computations
  • Best for: Tasks requiring deep analytical thinking and multi-step reasoning

​
Mistral Small 3.1 24B

  • Type: Chat
  • Context: Extended context window
  • Strengths: Multimodal capabilities, efficient performance, strong multilingual support
  • Best for: General-purpose chat applications with diverse language requirements

​
Llama 3.3 70B

  • Type: Chat
  • Context: 128K tokens
  • Strengths: Multilingual understanding, dialogue optimization, strong reasoning
  • Best for: Conversational AI applications and complex dialogue systems

​
Qwen 2.5 72B

  • Type: Chat
  • Context: 128K tokens
  • Strengths: Multilingual capabilities, programming, mathematical reasoning, structured data processing
  • Best for: Complex reasoning tasks, coding applications, mathematical problems, long-form content generation

​
Whisper Large V3 Turbo

  • Type: Audio
  • Capabilities: Speech-to-text transcription
  • Strengths: Fast processing, high accuracy, multiple language support
  • Best for: Audio transcription, voice-to-text applications

​
Kokoro

  • Type: Audio
  • Capabilities: Text-to-speech synthesis
  • Strengths: High-quality speech generation, multiple voice options, natural-sounding output
  • Voices: Supports voice combinations like af_sky, af_bella, af_sky+af_bella
  • Best for: Text-to-speech applications, voice synthesis, audio content creation

​
Nomic Embed Text

  • Type: Embedding
  • Dimensions: 768
  • Strengths: Open-source, outperforms OpenAI Ada-002 on benchmarks
  • Best for: Semantic search, document similarity, clustering

​
Using Models

To use any of these models, you’ll need:

  1. API Key: Get your key from the Tinfoil dashboard
  2. SDK: Install the SDK for your preferred language
  3. Model Configuration: Use the model ID, repository, and enclave address from the cards above

For detailed usage examples and code samples, see the SDK documentation: