Start building
Call the OpenAI-compatible API from your application, or connect your agents through the desktop app.
OpenAI-compatible API
Pay as you go
Signed receipt on every response
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://tee.redpill.ai/v1",
apiKey: process.env.REDPILL_API_KEY,
});
const response = await client.chat.completions.create({
model: "openai/gpt-oss-120b",
messages: [{ role: "user", content: "Say hello." }],
});For applications
Point your OpenAI SDK at the Gateway. Chat, completions, and embeddings work unchanged.
1
Create an API key
2
Point your SDK at tee.redpill.ai/v1
3
Verify the response with its receipt
For agents
Connect Claude Code, Codex, Pi, and more through Private AI Proxy. Traffic is protected while a verified session is active.
1
Install Private AI Proxy
2
Turn on Protected
3
Connect your agents
Private AI Model Catalog
Verified TEE providers, one price per token, no minimum spend.
Phala: Qwen3.8 27B Uncensored (Aggressive)NewTrusted Execution Environment
HauhauCS Qwen3.8-27B Uncensored Aggressive, using the pinned Q8_K_P GGUF and BF16 vision projector. Served with SGLang on a Phala TDX-attested H200, with text and image input and a 262144-token context.
- Sep 16, 2026
- 262K context
- $0.30/M input
- $1.50/M output
NVIDIA: Nemotron 3.5 LightningNewBetaTrusted Execution Environment
NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...
- Sep 11, 2026
- 262K context
- $0.07/M input
- $0.20/M output
- $0.04/M cache read
Z.ai: GLM 5.3NewTrusted Execution Environment
GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window. Served as a text-only TEE deployment via Phala.
- Aug 31, 2026
- 1M context
- $1.40/M input
- $4.40/M output
- $0.26/M cache read
Qwen: Qwen3.8 27BNewBetaTrusted Execution Environment
Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be enabled or disabled. Served on Phala in a TDX-attested enclave.
- Aug 24, 2026
- 262K context
- $0.24/M input
- $2.50/M output
- $0.05/M cache read
Why it's private
Every response comes with proof you can check yourself.
Attested enclaves
A TDX quote bound to your nonce proves which code is serving you.
Signed receipts
Every response is signed into a receipt that names the verified upstream session.
Open source
Gateway, verifier, and protocol are public. No trust in RedPill required.
Common questions
Start building in 1 minute
Create a key, point your OpenAI SDK at the Gateway, and send your first private request.