EU-resident inference API for open-weight language models
Stage
Not given
MVP
Founded
Not given
Not given
Based in
Not given
ES
Pricing model
Paid
Contact for pricing
Pricing
Model-based pricing: FLUX.1 [dev] $0.0125 per image, FLUX.1 [schnell] $0.0015 per image, FLUX.1 [pro] $0.02 per image, Stable Diffusion XL $0.002 per image, Wan 2.1 Video $0.2 per video, Hunyuan 3D $0.025 per 3D model. Hardware pricing billed by the second: Nvidia H100 GPU $0.00083 per second, Nvidi
Not given
Key features
Image generation
Video generation
Image restoration
Image captioning
Model fine-tuning
Speech generation
Automatic scaling
Sub-100ms latency
Python, JavaScript, and REST API support
99.9% uptime guarantee
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
What makes it different
Cheapest serverless AI API pricing, saving up to 62% compared to competitors
One-line code deployment
Pay only for what you use, scale to zero when idle
Access to 100+ production-ready AI models
Up to 4x faster performance on diffusion models
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
Synexa
Zarx