End-to-end confidential · TEE-attested

Private
intelligence you own.

Your prompts leave nothing behind: no logs, no training, verifiable in hardware. GLM-5.2 and the leading open models, OpenAI-compatible, no KYC.

Confidentiality TEE · SEALED 0 bytes retained
Deploy GLM-5.2How privacy works
Urgent · the state of AI Network view · live Closed // centralized Aleph Cloud // distributed [ figures illustrative ]
⚠AI today · closed and centralized

Their models.
Their rules.

A handful of closed labs run the AI you depend on. Prompts are stored, profiled and trained on. Access can be re-priced, revoked, or handed to a government overnight.

Your data, your keys

Your data is yours.

Lower cost, top performance and speed. Private inference on a distributed network that never holds your data.

Hover the nodes
Prompts stored
4,271,882,090,113 bytes
Confidentiality
None · logged & profiled
Flagship model · price
$27.40 / 1M · unstable
OpenAI-compatible✦No KYC✦TEE-attested✦Nothing stored✦Subscribe or pay per token✦Leading open models✦Powered by Aleph Cloud✦
OpenAI-compatible✦No KYC✦TEE-attested✦Nothing stored✦Subscribe or pay per token✦Leading open models✦Powered by Aleph Cloud✦
( 01 ) · The models

One endpoint.
The leading open models.

Pay-per-token, no KYC. GLM-5.2 leads; the rest of the catalog is one parameter away.

GLM-5.2Flagship
ToolsVisionReasoning
Online
$1.40
Input · 1M tokens
$4.40
Output · 1M tokens
200K
Context window
~120
Tokens / second

SubscribeFixed price

A flat monthly price for steady usage. Predictable bills, same private endpoint.

CreditsPay per token

No commitment: pay per million tokens. Overflow past your subscription bills at the same per-token rate.

Deploy GLM-5.2 in a minute.

Free to start. No card, no KYC. Keep your OpenAI SDK, change one line.

Get your API key Read the docs
Six more open models on the same endpointOutput $ / 1M+
Hermes 3 8B · TEE$0.08 / $0.30
DeepSeek V4 Flash$0.14 / $0.55
Gemma 4 31B$0.18 / $0.70
Qwen3.6-35B-A3B$0.20 / $0.80
Qwen3 Coder$0.25 / $1.00
Qwen3.5 122B$0.90 / $3.10
( 02 ) · Plans & pricing

Start free. Scale when you do.

Subscribe for steady usage, or pay per token with credits. Pay by card or crypto.

Free
To try it out
€0
Open chat →
Included
  • The private chat, no account
  • Open models
  • No card required
Go
For regular, everyday use
€8/mo
Subscribe →
Everything in Free, plus
  • Access to all models
  • Much higher usage than Free
  • Longer sessions before a cooldown
Plus
For heavy, daily workloads
€20/mo
Subscribe →
Everything in Go, plus
  • 3× higher weekly limit than Go
  • Comfortable for all-day work
  • Great for long documents and coding
Max
For power users and automation
€100/mo
Subscribe →
Everything in Plus, plus
  • 10× higher weekly limit than Plus
  • Built for intensive, sustained use
  • Ideal for automation and agents

Prices incl. VAT. Beyond your plan you pay per token with prepaid credits · card or crypto. Chat is free to start, and LiberClaw agents have their own free tier.

( 03 ) · Cost vs. benchmarkJul 2026

A fraction of the price.

Open models on distributed infrastructure, without a hyperscaler margin. Comparable benchmarks, up to 85% less per token.

LibertAIGLM-5.2$4.40Bench 91
AnthropicOpus 4.8$25.00Bench 93
OpenAIGPT-5.5$30.00Bench 94
$ / 1M output tokens · bench: GPQA Diamond, % correct
( 04 ) · Built for developers

Private by proof.

Most providers ask you to trust a policy. LibertAI is built so there's nothing to trust. Drop-in, OpenAI-compatible APIs where the infrastructure literally can't remember you.

CommitmentsWhat we do

Built by developers, for developers, with the open ecosystem in mind.

✓Support developers+
Drop-in OpenAI-compatible APIs, honest docs, and open models you can actually inspect. Keep your SDK, prompts and stack. Point one base URL at us and you're running.
✓Help startups save money+
Open models on distributed infrastructure cost a fraction of the closed flagships, plus up to $10,000 in credits to help early teams build private from day one.
✓Keep you in control+
No lock-in and no gatekeeping. Your choice of model, pay-per-token, no KYC, and everything runs on a decentralized network you can verify.
GuaranteesWhat we don't do

The privacy comes from the architecture, not a promise.

✕No data collection+
Requests are processed and forgotten. No account requirement, no profile, and nothing to subpoena.
✕No training on your data+
Your prompts never become weights, and are never used to train, tune or evaluate any model.
✕No blind trust+
Sensitive workloads run in Trusted Execution Environments with remote attestation. Verify the enclave; you don't have to trust a policy.
( 05 ) · Migration

Start, or switch,
in a minute.

The API is OpenAI-compatible. Fresh project or existing stack, your code already works. It just talks to a different address.

01

Create an account

Email or wallet, no KYC.

02

Generate an API key

One click in the console.

03

Pick GLM-5.2

Or any model in the catalog.

04

Point your client here

Keep your SDK and prompts.

THE ENTIRE MIGRATIONdiff
- base_url="https://api.openai.com/v1"
+ base_url="https://api.libertai.io/v1"
( 06 ) · The sovereign stack
Two particles become linked, so measuring one instantly determines the other. Why is the sky blue? Shorter blue wavelengths scatter more off air molecules than red.
ChatExplore →
Audit auth middleware[running]
Rotate session tokens[running]
Find stale references[done]
Thought for 4.1s · persistent memory
AgentsExplore →
 
$ libertai code
→ launching claude-code
→ backend api.libertai.io · glm-5.2
→ private session · 0 logs
▌
CodeExplore →
search the live web, privately
From $0.002 / query · pays via x402
SearchExplore →
( 07 ) · Sovereign program

$10,000 to build private.

Startup credits for selected companies building on private inference. GLM-5.2 and the full catalog, plus migration support from our team.

Apply for creditsReply within 48h
AmountUp to $10,000
EligibilityEarly-stage teams
UseInference credits
ReviewCase-by-case
( 08 ) · FAQ
How do I know it is actually private?+
You do not have to take our word for it. Every model runs with nothing stored and nothing trained on you. For sensitive workloads, TEE-served models like Hermes 3 8B run inside hardware-sealed enclaves on Aleph Cloud's distributed network that even the node operator cannot inspect, with cryptographic attestation you can verify yourself.
Will my existing code work?+
Yes. The API is OpenAI-compatible: keep your SDK, change the base URL and key, and your code talks to LibertAI. Migration is one line, and the docs cover streaming, tool use and vision.
How does billing work?+
Two ways. Subscribe to a plan that covers steady usage, or buy credits and pay per million tokens; past a plan's allowance, usage bills at the same per-token rate. Top up by card or crypto. No seats, no KYC.
Is there a free way to try it?+
Yes. The private chat at chat.libertai.io is free with no account. LiberClaw's free tier runs two always-on agents with no card required. And the API has no minimum: top up a few dollars and pay only for the tokens you use.
What happens if a node goes down?+
Workloads reschedule across the network. Your endpoint is not one company's datacenter: it is a distributed pool of Aleph Cloud nodes, so no single machine, provider or jurisdiction can take it offline.
Which models can I run?+
GLM-5.2 leads, with open models behind the same endpoint: Qwen, Gemma, DeepSeek, Hermes and more, plus image generation, embeddings, speech and private web search. All open-weight, so nothing can be deprecated out from under you.

Own your
intelligence.

Deploy GLM-5.2Read the docs
Break free. Join the liberation.