Quick Reference — All models listed below are accessible through any of our SDKs. See the SDK pages for language-specific usage examples.
Orchestration Server: All models can be accessed through the unified orchestration server 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
DeepSeek R1
deepseek-r1-0528
Parameters: 671B Context: 128K tokens
Strengths: State-of-the-art reasoning, advanced mathematical capabilities, enhanced function calling, reduced hallucination rate
Structured Outputs: Structured response formatting support
Best for: Complex reasoning tasks, mathematical problem-solving, advanced coding, and tasks requiring deep analytical thinking

OpenAI
GPT-OSS 120B
gpt-oss-120b
Parameters: 117B Context: 128K tokens
Strengths: Powerful reasoning, configurable reasoning effort levels, full chain-of-thought access, native agentic abilities including function calling, web browsing, and Python code execution
Structured Outputs: Structured response formatting support
Best for: Production use cases requiring high reasoning capabilities, agentic operations, and specialized applications

Mistral
Mistral Small 3.1 24B
mistral-small-3-1-24b
Context: 128K tokens
Strengths: 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
Llama 3.3 70B
llama3-3-70b
Context: 128K tokens
Strengths: Multilingual understanding, dialogue optimization, strong reasoning
Structured Outputs: Structured response formatting support
Best for: Conversational AI applications and complex dialogue systems

Qwen
Qwen3 Coder 480B
qwen3-coder-480b
Parameters: 480B total (35B activated)
Context: 128K tokens
Strengths: Advanced agentic coding capabilities, repository-scale understanding, browser automation, exceptional tool calling with specialized function call format
Tool Calling: State-of-the-art agentic coding and function calling capabilities
Structured Outputs: Structured response formatting support
Best for: Agentic coding workflows, large codebase analysis, browser automation, complex multi-step programming tasks, repository-level code understanding
Advanced Agentic Coding: Optimized for CLINE, Qwen Code, and other agentic platforms. See Tool Calling Guide for implementation examples.

Qwen
Qwen 2.5 72B
qwen2-5-72b
Context: 128K tokens
Strengths: 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.

OpenAI
Whisper Large V3 Turbo
whisper-large-v3-turbo
Capabilities: Speech-to-text transcription
Strengths: Fast processing, high accuracy, multiple language support
Best for: Audio transcription, voice-to-text applications
Audio Format: Supports .mp3 and .wav files

Kokoro
Kokoro
kokoro
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

​
Embedding Models

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

Nomic
Nomic Embed Text
nomic-embed-text
Dimensions: 768
Strengths: Open-source, outperforms OpenAI Ada-002 on benchmarks
Best for: Semantic search, document similarity, clustering

​
Document Processing Models

Description: Document processing models handle file conversion, text extraction, and document parsing operations.

Docling
Docling Document Processing
docling
Capabilities: Document processing and conversion service
Strengths: PDF processing, Word document parsing, text extraction, format conversion with high accuracy
Best for: Document upload, processing, conversion, and text extraction workflows
📄 File Support: Supports PDF, Word documents, and other common document formats. See Document Processing Guide for usage examples.

​
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 ID: Use the model ID from the cards above in your API requests
For detailed usage examples and code samples, see the SDK documentation: