An FHE coprocessor network for language models.
Developers send encrypted prompts and receive encrypted outputs. Independent node operators run the encrypted computation on accelerated hardware and are paid per job. The encryption keys never leave the user.
An API that feels normal
SDK and API that look like a regular AI inference API, with encryption and decryption handled on the client.
GPUs become coprocessors
Software that turns GPU servers, and later dedicated FHE accelerators, into paid coprocessors.
"We can't see your data"
AI features where privacy is a technical fact, not a promise.
Key generation
The SDK creates a secret key on your device and a public evaluation key that lets servers compute on ciphertext.
READABLE · YOUEncryption
The prompt is tokenized and embedded locally, then encrypted.
CIPHERTEXTEncrypted inference
A CIPHRA node runs the model's layers on ciphertext. Encrypted numbers in, encrypted numbers out.
CIPHERTEXTVerification
The client checks the agreed model was run. At launch: redundant execution on independent nodes with matching results.
CIPHERTEXTDecryption
Only your secret key turns the result into readable text.
READABLE · YOUEvery prompt is a confession.
A doctor pastes a scan report into an assistant. A lawyer checks a draft settlement. In almost every AI product today, that confession arrives at someone else's server in plain text. The organizations with the most valuable data are not afraid of the model. They are afraid of the moment their data becomes readable.
What if the model could answer without ever being able to read the question?
| Option | What it protects | What it leaves open |
|---|---|---|
| Standard AI API + privacy policy | Legal promises, contracts | Data is readable by the provider and its infrastructure |
| Self-hosting on-premise | Data stays inside the company | Expensive hardware, limited model quality, heavy operations |
| Trusted execution (TEE) | Data isolated inside secure hardware | Trust in the chip vendor; history of side-channel attacks |
| Anonymizing before sending | Removes obvious identifiers | Context can re-identify people; useful detail is lost |
| > CIPHRA · FHE | Data protected by mathematics, not by trusting the operator, vendor or a policy | Speed, which is exactly what CIPHRA focuses on |
Peer-reviewed math. Accelerated hardware.
CIPHRA builds on established FHE schemes instead of inventing new cryptography, on top of mature open-source libraries such as OpenFHE and TFHE-rs. Every CIPHRA-specific component will be open-sourced and audited.
Approximate arithmetic on real numbers
Suits the matrix multiplications that dominate neural networks.
Fast non-linear functions
Programmable bootstrapping evaluates non-linear steps quickly. The CIPHRA compiler chooses the scheme per layer.
OpenFHE · TFHE-rs
Mature open-source foundations. CIPHRA-specific components will be open-sourced and audited.
Polynomial approximation
Softmax, GELU and normalization approximated per model, with accuracy loss kept within a stated tolerance.
Hybrid splitting
Your device runs tokenization, embedding and decoding. The network runs the heavy middle layers encrypted.
FHE-aware fine-tuning
Open-weight models are tuned so they keep their quality after approximation.
Data-center GPUs
Custom CUDA kernels for NTT and key switching, on hardware node operators already own.
FPGA cards
Lower latency and better energy use for production workloads.
FHE ASICs
Dedicated accelerator chips, sourced through hardware partnerships as they reach the market.
// performance, stated honestly: encrypted inference is still much slower and more expensive than plain inference. First targets are small and mid-size models: classification, embeddings for private search, document extraction and compact language models. CIPHRA will publish latency, cost per request and accuracy against the unencrypted baseline for every supported model.
Five things you can build on.
Patient records, unexposed
Triage, coding and summarization without exposing records to the AI provider.
Privileged documents
Contract review and e-discovery on documents that cannot leak.
Data that can't leave the bank
Fraud scoring and risk analysis on customer data that stays unreadable.
Assistants that can't peek
Internal assistants read sensitive documents without the vendor seeing them.
Private strategies
AI agents act on private inputs, like a trading strategy, without revealing them to the network.
Build it on the testnet
Developer testnet ships in Phase 1. Join the whitelist to hear first.
$CPH is built to be used.
settles in $CPH.
- name
- CIPHRA
- type
- Utility token of the CIPHRA network
- launch
- Fair launch on Programmable (Ethereum), inside its mandatory launch-protection hook for Uniswap v4.
- supply
- 1,000,000,000 $CPH, fixed. 100% goes into the ETH/$CPH pool as one position, locked forever. No team, presale, investor or airdrop allocation.
- fees
- On every buy and sell, in ETH: 0.3% Programmable platform fee + 2% creator fee, fixed in the hook for ever.
- protection
- Opening valuation of at least USD 15,000. First 30 s: buy fee starts at 99% and falls to normal. First 300 s: every wallet can buy or receive at most 2% of supply.
- creator fees
- Cipher Vault: 50% Sealed Pot (route set by the Blind Ballot: buyback and burn, compute grants or node rewards) · 30% R&D · 20% Break-the-Cipher bounties.
- contract
- TBA · announced at launch
- x
- @ciphra_agent
- telegram
- t.me/ciphra_agent
Pay for compute
Encrypted inference jobs are priced in $CPH. Enterprises that want stable pricing can pay in stablecoins, converted at settlement.
Node staking
Operators stake $CPH to receive jobs. A node whose results fail verification loses part of its stake.
Priority & capacity
Stakers can reserve guaranteed capacity for production workloads.
Blind Ballot
Stake $CPH and vote each week, sealed, on where half of all creator fees go: buyback and burn, compute grants or node rewards. Later, holders also vote on supported models and grants.
From proof to scale.
Birth
- Protected fair launch on Programmable
- Cipher Vault and CipherStake live
- First commit-reveal Blind Ballot
- Break-the-Cipher fund opens
Proof
- Open-source compiler alpha
- Encrypted classification and embedding models on GPU
- Public benchmarks
- Developer testnet with Node Bootstrap rewards
Private RAG
- Private RAG and Inference API beta
- First external node operators
- SDK and node audit
- First Blind Ballot tallied on ciphertext by CIPHRA nodes
Language models
- Encrypted inference for compact LLMs with hybrid splitting
- FPGA nodes
- Enterprise pilots in healthcare and finance
Scale
- Larger models as accelerators mature
- ASIC partnerships
- Network governance by stakers
// milestones are targets and depend on funding, audits and hardware availability.
Security model, honest limits.
Computed on.
Never read.
Against node operators, CIPHRA and network observers
- Prompt content stays encrypted end to end
- Model outputs are only readable with your key
- Retrieved documents in Private RAG stay encrypted
What FHE does not cover
- Metadata: that a request was made, its size, timing and which model was called
- Model weights: known to nodes in the initial design
- Key safety: a compromised device or key can't be protected by encryption
- Accuracy: approximated models may differ slightly; each ships with a published accuracy report
Get early access to the testnet.
Drop your EVM wallet and X handle for early access to the developer testnet and SDK, then let CIPHRA write your post. This is not a token allocation, presale or airdrop: $CPH launches fairly on Programmable and everyone buys from the same pool under the same 2% limit. Your address is shown encrypted below as you type, just for fun. It is stored only for the early-access list.
One wallet, one entry. No token allocation.
Read the whitepaper.
- 01Every prompt is a confession
- 02Why today's options fall short
- 03What CIPHRA is
- 04How it works
- 05The technology
- 06Products
- 07Who it is for
- 08The $CPH token
- 09Launch on Programmable
- 10The Cipher Vault and the Blind Ballot
- 11Roadmap
- 12Security model and honest limits
- 13Team and partners
- 14Risks and disclaimer
