Akumi
EU-hosted OpenAI-compatible inference API with data residency, PII pseudonymization and per-request audit trails
Akumi is an OpenAI-compatible inference API served entirely from EU infrastructure, aimed at teams whose data cannot be sent to US-hosted providers. The application, the models and the request data all run in the EU.
Beyond the API it adds a governance layer: a policy-based model router with fallback, a PII firewall that pseudonymizes data before models see it, a guard for blocking off-policy content, caching, and a metadata-only audit trail. Recall provides memory and document retrieval, exposed to AI clients through an MCP server.
There is no free tier. Pay-as-you-go carries no monthly fee but needs a EUR 10 minimum top-up, with credits drawn at list price; Team is EUR 179/month and Business EUR 599/month, and governance features meter separately when active. Operated by a Netherlands-registered company (KvK 98356623).
Pricing: Monthly subscriptions
Akumi Alternatives
Explore 96 products in the Inference APIs category. View all Akumi alternatives.
AI Gateway HQ
LLM gateway built around spend limits enforced before a request reaches a provider
Cloudflare Workers AI
Run AI models at the edge on Cloudflare's global network with serverless inference
novita.ai
APIs, Serverless and GPU Instance In One AI Cloud
Replicate
Run and fine-tune open-source models. Deploy custom models at scale. All with one line of code.
fal
Build the next generation of creativity with fal. Lightning fast inference.
Work on Akumi? Feature it at the top of Inference APIs.
Is your product missing?