FeaturesHow it worksDevelopers
Dashboard

Abliterated AI models for developers

Open models.Private inference.

Build with open and abliterated models for uncensored intelligence. Keep your prompts inside hardware-isolated enclaves, private from the people running the infrastructure.

Go to Dashboard Try the consumer app

OpenAI-compatible. Change your base URL. Keep your code.

Backed by

  • a16z
  • SV Angel
  • NVIDIA Inception Program
  • Coinbase Ventures
  • Illia PolosukhinCo-author of the Transformer paper · Co-founder of NEAR
Capabilities

Private by design.
Open by default.

DreamGuard dashboard showing API requests, spending, token usage, latency, and usage charts
01

OpenAI-compatible API

Point your existing client at api.dreamguard.ai/v1 and swap in a dg_live_ key. No SDK rewrites, no new abstractions.

02

Attested TEE execution

Every model runs inside a hardware-isolated GPU enclave with remote attestation and zero prompt retention.

03

Abliterated model catalog

Qwen, Llama, Mistral, and DeepSeek variants with refusal directions removed — plus the original weights for baseline comparison.

04

Keys, logs, and spend controls

Project-scoped API keys with per-key limits, full request logs, and per-token billing with credit auto-recharge — all in one dashboard.

AB

Our model offerings

Think it. See it. Bring it to life.

From the first word to the final frame. Explore text, image, and video models for whatever you’re building next.

Text

Intelligence for every conversation.

Build assistants, reason through complex problems, and turn unstructured ideas into useful output.

  • Chat & reasoning
  • Code
  • Structured output
Explore text models
Image

Give your ideas a visual language.

Explore image models for creating original visuals, developing concepts, and bringing a new perspective to your work.

  • Image generation
  • Visual exploration
Explore image models
Video

Take your story beyond a still.

Explore video models that turn creative direction into moving scenes, from the first concept to the next sequence.

  • Video generation
  • Motion & storytelling
Explore video models
Find the right model for your next idea.Browse the model catalog
Security

Your data is
never exposed.

DreamGuard combines confidential computing, encrypted transport, and attestable model execution so private inference stays private from request to response.

SOC 2ISO 27001HIPAAGDPRCCPA

Remote attestation

Verify the exact enclave and model measurement before releasing sensitive context.

Encrypted memory

Protect prompts, outputs, and working context while inference runs inside the TEE.

Operator blind spots

Cloud operators can provide compute, but cannot inspect your inputs, outputs, or model weights.

Policy enforcement

Set model, region, and data-handling policies that are checked before inference begins.

For developers

Drop-in compatible.
Private by default.

Keep your stack and your client. Change the base URL and key, and every request runs inside an attested enclave.

OpenAI-compatible

Drop-in replacement — change the base URL and key.

Attested by default

Enclave measurements verified before payloads leave your app.

Project-scoped keys

dg_live_ keys with per-key spend limits and revocation.

Per-token billing

Transparent per-model pricing with credit auto-recharge.

from openai import OpenAI
client = OpenAI(
    base_url="https://api.dreamguard.ai/v1",
    api_key="dg_live_..."
)
client.chat.completions.create(
    model="qwen-32b-abliterated",
    messages=[{"role": "user", "content": "Hello"}],
)
Read the docs|Try the playground

Ready to make
inference private?

Grab a dg_live_ key and point your client at our OpenAI-compatible endpoint. Your first $5 of credits is on us — no plaintext prompts, no exposed weights.

Get an API key

OpenAI-compatible · Zero prompt retention · Attested TEE