| What it does | Private AI inference and confidential GPU computing infrastructure
| The Context Gateway for AI systems
|
|---|
| Stage | Not given
| Not given
|
|---|
| Founded | Not given
| Not given
|
|---|
| Based in | US
| CH
|
|---|
| Pricing model | Paid
| Freemium
|
|---|
| Pricing | Confidential Inference: DeepSeek V4.1 Flash $0.30 input and $1.20 output per 1M tokens; Kimi K3 $3.00 input and $15.00 output per 1M tokens; GLM 5.3 $1.40 input and $4.40 output per 1M tokens; Qwen3.8 27B $0.30 input and $1.80 output per 1M tokens. Confidential VMs: B300 at $7.50 per GPU-hour, B200
| Community: Free (open-source, local use). Pro: $9/month or $90/year (personal cloud sync, 1 GB hosted index). Team: $29/month per seat or $290/year per seat (team server, shared workspace, 20 GB index, 1-25 seats). Enterprise: Contact for pricing.
|
|---|
| Key features | - OpenAI-compatible endpoint for private LLM inference
- Hardware-encrypted VMs on Intel TDX, AMD SEV-SNP and NVIDIA GPUs
- Client attestation verification before sending requests
- Support for multiple open-weight models including DeepSeek, Kimi, GLM, Qwen
- Confidential Kubernetes for data center scale deployments
- Confidential training and fine-tuning on licensed stack
- Root access over SSH to confidential VMs
- Encrypted GPU communications with NVLink encryption on B200 and B300
- Confidential agents runtime support
- Prompt caching with cached input billing
| - Source selection and retrieval with task-relevant context at configurable depth
- Access controls via PathJail boundary enforcement and role-based permissions
- Read-time content filters for injection patterns and personal data detection
- Memory and continuity to retain findings and connections across sessions
- Evidence and outcomes recording with source references and usage audit trails
- Integration with AI tools via SDK, MCP, hooks and supported client adapters
- Local, VPC, on-premises and offline deployment options
- Optional production intelligence for planning, ranking and routing enhancements
- SDK with five stable primitives and six Agent Tools language contracts
- Context cache, reference routing and usage accounting
|
|---|
| What makes it different | - Prompts and model weights verified by clients with cryptographic attestation before any data is sent
- Operator-blind inference: data remains unreadable to the company and hosting provider
- Flexible deployment: choice of hosted cloud, rented VMs, or licensed stack on own infrastructure
- Open-weight models only, no closed-source frontier models
- Full cryptographic verification stack including open-source tools
| - Deterministic, model-agnostic context processing independent of AI provider choice
- Governs context without controlling model calls, keeping AI decisions under user ownership
- Records measurable impact with 64.1% reported context reduction in field use
- Open-source core (Apache 2.0) with commercial tiers for teams and enterprises
- Transparent governance with separate evaluation of task outcome from context delivery
|
|---|
| Community votes | 0 | 0 |
|---|
| DR (Domain Rating by Ahrefs) | 12 ▲ +1 (up) since last check | 42 ● no change since last check |
|---|
| Trust Flow (Majestic) | 7 | 3 |
|---|
| Citation Flow (Majestic) | 26 | 35 |
|---|
| Referring domains (Majestic) | 36 | 212 |
|---|
Confidential AI
LeanCTX