Documentation Index
Fetch the complete documentation index at: https://docs.redpill.ai/llms.txt
Use this file to discover all available pages before exploring further.
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 four verified TEE providers:Chutes
New GLM, Kimi, Qwen, MiniMax, MiMo, and DeepSeek models
Near AI
GLM-5, DeepSeek V3.1, GPT-OSS, and Qwen
Phala Network
Qwen, Gemma, GPT-OSS, GLM, and embeddings
Tinfoil
Qwen Coder, Kimi Thinking, DeepSeek R1, and Llama
Model Catalog
Chutes Models
| Model | Parameters | Best For |
|---|---|---|
| GLM 5.1 | Large | Systems engineering, agent workflows |
| Kimi K2.6 | Large MoE | Visual coding, multimodal work |
| Qwen3.5 397B | 397B MoE | High-quality reasoning |
| Qwen3 Coder Next | Large | Code generation, review |
| MiniMax M2.5 | Large | General purpose |
| MiMo V2 Flash | Large | Fast responses |
| DeepSeek V3.2 | 685B MoE | Latest DeepSeek reasoning |
| Kimi K2.5 | Large MoE | Visual coding |
Near AI Models
| Model | Parameters | Best For |
|---|---|---|
| GLM-5 | Large | Systems engineering |
| DeepSeek V3.1 | 671B MoE | Hybrid reasoning |
| GPT-OSS 120B | 117B MoE | OpenAI-style open-weight reasoning |
| Qwen3 30B | 30B MoE | Balanced performance |
| GLM-4.7 | 130B | Bilingual CN/EN tasks |
Phala Network Models
| Model | Parameters | Best For |
|---|---|---|
| Qwen3.5 27B | 27B | General purpose |
| Qwen3 VL 30B | 30B MoE | Vision + language |
| Qwen3 Embedding 8B | 8B | Confidential embeddings |
| Gemma 3 27B | 27B | Multilingual multimodal work |
| GLM 4.7 Flash | ~30B | Fast agentic coding |
| GPT-OSS 20B | 21B MoE | Efficient OpenAI-style reasoning |
| Qwen 2.5 7B | 7B | Budget-friendly chat |
Tinfoil Models
| Model | Parameters | Best For |
|---|---|---|
| Qwen3 Coder 480B | 480B MoE | Large-scale coding |
| Kimi K2 Thinking | 1T MoE | Agentic reasoning |
| DeepSeek R1 | 685B MoE | Advanced reasoning |
| Llama 3.3 70B | 70B | General purpose chat |
Choosing the Right Model
For general conversations
For general conversations
Recommended: GLM 5.1, GLM-5, or Llama 3.3 70BThese models handle everyday questions, brainstorming, and general assistance well.
For complex reasoning
For complex reasoning
Recommended: GLM 5.1, Qwen3.5 397B, DeepSeek R1, or DeepSeek V3.2Best for multi-step problems, analysis, and tasks requiring deep thinking.
For coding tasks
For coding tasks
Recommended: Qwen3 Coder Next, Qwen3 Coder 480B, or Kimi K2.6Optimized for code generation, debugging, and technical documentation.
For multilingual content
For multilingual content
Recommended: Qwen3.5, GLM-5, or GLM-4.7Strong performance in non-English languages, especially Chinese.
For fast responses
For fast responses
Recommended: MiMo V2 Flash, Qwen 2.5 7B, or GPT-OSS 20BSmaller models that respond quickly for simple queries.
Model Usage by Plan
| Feature | Free | Pro | Enterprise |
|---|---|---|---|
| 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:- No third-party exposure - Your data doesn’t go to OpenAI, Anthropic, or Google
- Hardware isolation - TEE ensures even the hosting provider can’t see your data
- Verifiable execution - Cryptographic attestation proves the model runs in genuine TEE
- Consistent privacy - Every model meets the same security standard
Want access to 50+ models including OpenAI GPT 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 →