# Aleph Alpha | European inference provider profile and prices

[Directories](/directories/) › [European Inference](/eu/) › Aleph Alpha

![Aleph Alpha logo](/logos/aleph-alpha.png)

Verified

Aleph Alpha is a Germany-based provider in the Model builder category with 2 listed models. No cached-input rate is published.

EU-owned EU hosting Model builder

[Visit website ↗](https://aleph-alpha.com) [API docs ↗](https://api.aleph-alpha.com)

Overview Models Pricing Infrastructure Access Compliance Benchmarks Performance

## At a glance

Record

Ownership

Aleph Alpha GmbH

Headquarters

Heidelberg, Germany

Hosting region

EU (Heidelberg, Germany)

Founded

Not published

Website

[aleph-alpha.com](https://aleph-alpha.com)

## Summary

Scope

Aleph Alpha is a Germany-based provider in the Model builder category with 2 listed models. No cached-input rate is published.

No public per-token price. Legacy Luminous list prices appear in third-party trackers but conflict ($4.50 vs $30 vs $219 per 1M) , treat as stale. Pharia-1-LLM-7B is open-weight.

[Source: aleph-alpha.com ↗](https://aleph-alpha.com) · Updated Nov 4, 2026

### API access

Responses API compatible

### Access

API

### KYC

Not published

### Compliance

GDPREU AI ActBSI C5 (claimed)DPA

## Key models

2 listed

Pharia-1-LLM-7B-control 8K context · quote only Inference \- / -

Pharia-1-Embedding-4608-control , context · quote only Embedding \- / -

## Pricing

List rates · EUR

Model Type Input price Caching price Output price

Pharia-1-LLM-7B-control8K context · quote only Inference \- \- \-

Pharia-1-Embedding-4608-control, context · quote only Embedding \- \- \-

List rates. Cached input shown where published; "-" means the provider does not publish a cache rate. Units follow the source rate card.

## Infrastructure

Hosting

Region**EU**

Cities**Heidelberg, Germany**

Provider group**Model builder**

ZDR**yes (no prompt storage claimed)**

DPA**Available**

Cached input policy**No public per-token rates (quote only).**

## Access

API & payments

API shape**Responses API compatible**

Access**API**

KYC**Not published**

Cached input policy**No public per-token rates (quote only).**

## Compliance

Source-backed

DPA**Available**

ZDR**yes (no prompt storage claimed)**

Retention**ZDR: yes (no prompt storage claimed). DPA published.**

Certifications

GDPREU AI ActBSI C5 (claimed)DPA

## Benchmarks

Coming soon

Coming soon.

## Performance

Coming soon

Latency

### Time to first token

Median and p95 response times for short and long prompts, measured from repeatable probes rather than vendor claims.

Coming soon

Throughput

### Tokens per second

Streaming output rate and request throughput under steady load, with concurrency and context length recorded.

Coming soon

Efficiency

### Cost per workload

Blended cost for a fixed workload, including cache reads and output tokens, so speed and price can be compared together.

Coming soon

Independent performance probes are being added. Vendor-reported numbers are not mixed into this section.

[PreviousScaleway](/eu/providers/scaleway)