EU-resident inference API for open-weight language models
Confidential and open LLM inference for agents, paid per request in USDC
Stage
MVP
Not given
Founded
Not given
Not given
Based in
ES
US
Pricing model
Contact for pricing
Paid
Pricing
Not given
LLM inference: Models priced per million tokens input and output, ranging from $0.043 to $3.63 for input and $0.22 to $18.15 for output (e.g., Qwen3.8 27B route C: $0.043/$1.375, Kimi K3 route B: $3.63/$18.15). Virtual machines: Starter $0.159-$0.169/hour, Standard $0.318-$0.335/hour, Pro $0.636-$0.
Key features
OpenAI-compatible Responses and Chat Completions endpoints
Streaming with Server-Sent Events
Function calling and tool use
Structured JSON output with schema validation
Audio transcription with file and live WebSocket modes
Text-to-speech with built-in and customizable voices
Speech-to-speech translation
Time series forecasting up to 1,000 periods
Per-key usage tracking and limits
Servers owned and operated by NPAW in EU
Attested confidential model execution on Intel TDX hardware
Open tier LLM inference without attestation
Price shown before model execution
No account or API key required
Virtual machines for AI swarms by the hour
Phone numbers and calling with metered pricing
Email inboxes with sending allowances
Access via HTTP without signup
416 open source models available
What makes it different
Data residency in EU with no US sub-processor in the data path
OpenAI-compatible API so teams can keep existing integrations
Three capability levels—Z Ultra, Z Pro, Z Fast—on the same API
Operated by NPAW, which has run its own data infrastructure since 2008
ISO 27001, ISO 27701, ISO 42001 and ENS High certified
Encrypted memory and disk in processor with no company access to keys
Price transparent and settled before request execution
No account signup, payment via wallet address
Automatic enforcement of calling and messaging consent rules
Zarx
Agentgates