Models
Model Catalog
All available models on Tinfoil with their repositories and enclave addresses
Quick Reference — All models listed below are accessible through any of our SDKs. See the SDK pages for language-specific usage examples.
Proxy URL: All models can be accessed through the unified proxy URL
https://inference.tinfoil.sh which automatically routes to the appropriate model based on the model name in the API request.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. We’re working hard to get bigger and more powerful models running with Tinfoil.
Chat Models
Description: Chat models support conversational AI capabilities through the standard chat completions API. All chat models follow the OpenAI chat completion format.
DeepSeek R1 70B
deepseek-r1-70bStrengths: Advanced reasoning, complex problem-solving, mathematical computations
Structured Outputs: Structured response formatting support
Best for: Tasks requiring deep analytical thinking and multi-step reasoning
Mistral Small 3.1 24B
mistral-small-3-1-24bStrengths: Vision capabilities for image analysis, efficient performance, strong multilingual support
Multimodal Support: Supports image inputs (in base64) alongside text for vision tasks
Structured Outputs: Structured response formatting support
Best for: General-purpose chat applications, image analysis, and diverse language requirements
🖼️ Multimodal: See Image Processing Guide for vision examples.
Llama 3.3 70B
llama3-3-70bStrengths: Multilingual understanding, dialogue optimization, strong reasoning
Structured Outputs: Structured response formatting support
Best for: Conversational AI applications and complex dialogue systems
Qwen 2.5 72B
qwen2-5-72bStrengths: Exceptional function calling, multilingual capabilities, programming, mathematical reasoning, structured data processing
Tool Calling: Best-in-class function calling capabilities with high reliability
Structured Outputs: Structured response formatting support
Best for: Complex reasoning tasks, function calling workflows, coding applications, mathematical problems, long-form content generation
🛠️ Excellent Tool Calling: See Tool Calling Guide for implementation examples.
📋 Structured Outputs: All chat models support structured outputs for reliable data extraction and API integration. Full JSON schema validation available in Node.js SDK. See the Structured Outputs Guide for implementation examples.
Audio Models
Description: Audio models provide speech-to-text transcription and text-to-speech synthesis capabilities. Supporting both audio file transcription and high-quality speech generation.
Whisper Large V3 Turbo
whisper-large-v3-turboStrengths: Fast processing, high accuracy, multiple language support
Best for: Audio transcription, voice-to-text applications
Audio Format: Supports .mp3 and .wav files
Kokoro
kokoroStrengths: High-quality speech generation, multiple voice options, natural-sounding output
Voices: Supports voice combinations like
af_sky, af_bella, af_sky+af_bellaBest for: Text-to-speech applications, voice synthesis, audio content creation
Embedding Models
Description: Embedding models convert text into high-dimensional vectors for semantic search, similarity comparisons, and other vector-based operations.
Nomic Embed Text
nomic-embed-textStrengths: 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:- API Key: Get your key from the Tinfoil dashboard
- SDK: Install the SDK for your preferred language
- Model ID: Use the model ID from the cards above in your API requests