Skip to main content

Confidential AI Models

RedPill exclusively uses Confidential AI models - AI models running entirely within GPU Trusted Execution Environments (TEE). Your prompts and responses never leave the secure hardware enclave.
Unlike other AI platforms, we don’t route to OpenAI, Anthropic, or other cloud providers. Every model runs in verified TEE infrastructure.

Available Model Providers

RedPill sources Confidential AI models from three verified TEE providers:

Phala Network

8 models including DeepSeek V3, GPT-OSS, Qwen

Tinfoil

4 models including DeepSeek R1, Qwen3 Coder

Near AI

3 models including GLM-4.6, DeepSeek V3.1

Model Catalog

Phala Network Models

ModelParametersBest For
DeepSeek V3.2685B MoELatest reasoning, complex tasks
DeepSeek V3685B MoEGeneral reasoning, analysis
GPT-OSS 120B120BOpen-source GPT alternative
Qwen 2.5 72B72BMultilingual, coding
Qwen 2.5 7B7BFast responses, chat
Gemma 2 27B27BEfficient, balanced
DeepSeek Coder33BCode generation, review
DeepSeek Chat67BConversational AI

Tinfoil Models

ModelParametersBest For
DeepSeek R1685B MoEAdvanced reasoning
Qwen3 Coder 480B480BLarge-scale coding
Llama 3.3 70B70BGeneral purpose, chat
Llama 3.3 8B8BFast, lightweight

Near AI Models

ModelParametersBest For
DeepSeek V3.1685B MoELatest reasoning
GLM-4.69BChinese language, fast
Qwen3 32B32BBalanced performance

Choosing the Right Model

Recommended: DeepSeek V3 or Llama 3.3 70BThese models handle everyday questions, brainstorming, and general assistance well.
Recommended: DeepSeek R1 or DeepSeek V3.2Best for multi-step problems, analysis, and tasks requiring deep thinking.
Recommended: Qwen3 Coder 480B or DeepSeek CoderOptimized for code generation, debugging, and technical documentation.
Recommended: Qwen 2.5 or GLM-4Strong performance in non-English languages, especially Chinese.
Recommended: Qwen 2.5 7B or Llama 3.3 8BSmaller models that respond quickly for simple queries.

Model Usage by Plan

FeatureFreeProEnterprise
Basic models (7B-27B)
Large models (70B+)Limited
Massive models (480B+)
Model switching
Priority access

Why Confidential AI Only?

RedPill is designed for true privacy. Here’s why we only use Confidential AI models:
  1. No third-party exposure - Your data doesn’t go to OpenAI, Anthropic, or Google
  2. Hardware isolation - TEE ensures even the hosting provider can’t see your data
  3. Verifiable execution - Cryptographic attestation proves the model runs in genuine TEE
  4. Consistent privacy - Every model meets the same security standard
Want access to 60+ models including OpenAI GPT-4 and Claude? Use the RedPill API for development - it offers broader model selection with TEE-protected routing.

Attestation & Verification

Every Confidential AI model comes with cryptographic attestation proving it runs in genuine TEE hardware.

Learn about verification

Verify model execution yourself →