# LiteLLM Operations Competence Center Switzerland

> LiteLLM consulting and operations in Switzerland. VSHN deploys and manages the unified AI gateway on Kubernetes with Swiss data residency. ISO 27001 certified.


Deploy and operate LiteLLM as your unified AI gateway on Swiss cloud infrastructure. VSHN engineers configure multi-provider routing, cost tracking, and rate limiting on Kubernetes so your teams get one stable API endpoint for all LLM providers - with full Swiss data residency and audit logging. Part of VSHN's [LLM Operations practice](https://www.llmops.ch).


## Pages

- [Homepage](https://www.litellm.ch/): LiteLLM Experts – AI Gateway Consulting Switzerland | VSHN
- [Partner with VSHN on LiteLLM | VSHN](https://www.litellm.ch/partners.md)
- [LiteLLM Sovereignty — Swiss AI Gateway | VSHN](https://www.litellm.ch/sovereignty.md)

## Features

- **Unified AI Gateway**: Route requests to 100+ LLM providers through a single OpenAI-format API with LiteLLM. VSHN deploys and operates your LiteLLM proxy on Kubernetes so your applications can switch between Anthropic, OpenAI, Mistral, and self-hosted models without code changes - all routed through Swiss infrastructure with full request logging and auditability.

- **Cost Tracking and Budget Controls**: Most LLM providers only offer spend limits at the account level, so one user can exhaust the budget for the entire organisation. LiteLLM adds per-user, per-team, and per-project spending caps with real-time cost tracking. VSHN configures budget alerts, spending limits, and chargeback reporting so you always know what your AI workloads cost and can allocate resources across departments without risking runaway spend.

- **Rate Limiting and Guardrails**: Protect your LLM infrastructure with per-user rate limiting, content filtering, and request validation. VSHN configures LiteLLM's guardrail framework on Kubernetes with SSO and RBAC integration so only authorised users and applications can access specific models, with configurable throttling to prevent runaway costs.

- **Multi-Provider Load Balancing**: Distribute LLM requests across multiple providers and model deployments for reliability and cost optimization. VSHN engineers LiteLLM's load balancing with failover routing, latency-based selection, and provider health checks on OpenShift and Kubernetes, ensuring your AI applications stay responsive even when individual providers experience outages.

- **Swiss Data Residency**: LiteLLM proxy logs, API keys, and request metadata stay in Swiss data centers. VSHN operates on Exoscale, Cloudscale, and other Swiss cloud providers, ensuring full GDPR compliance and data residency for organizations that need to control where their LLM prompts and completions are routed and logged. Learn more in our [sovereignty assessment](/sovereignty/).

- **Observability and Analytics**: Monitor request latency, token usage, error rates, and provider performance across your entire LLM gateway. VSHN integrates Prometheus, Grafana, and LiteLLM's analytics dashboards into your platform so you always know which models perform best, where bottlenecks are, and when to adjust routing or scaling policies.


## LiteLLM FAQ

### What platforms does VSHN support for LiteLLM workloads?

VSHN deploys and operates LiteLLM on APPUiO (our managed Kubernetes platform), Red Hat OpenShift, enterprise private cloud infrastructure, and sovereign cloud partners. All platforms run on Swiss or European data centers and are backed by up to 99.99% uptime SLA. We help you choose the right platform based on your compliance, performance, and budget requirements.


### Which cloud providers are available for LiteLLM deployments?

VSHN operates on multiple Swiss cloud providers including Exoscale and Cloudscale, as well as European sovereign cloud partners. LiteLLM itself can route requests to over 100 LLM providers, but the proxy infrastructure and all request logs remain on Swiss servers. All infrastructure is managed under a single SLA with 24/7 support from our operations team.


### How does LiteLLM work as an AI gateway?

LiteLLM acts as a proxy that translates requests into a unified OpenAI-format API, regardless of the backend provider. It adds minimal latency overhead while providing cost tracking, rate limiting, load balancing, and SSO-based access control. VSHN deploys LiteLLM on Kubernetes with high availability, automated scaling, and full observability for production workloads.


### How does VSHN scope and quote LiteLLM consulting engagements?

Every engagement starts with a free architecture consultation where we assess your LLM usage patterns, provider requirements, and compliance constraints. VSHN then delivers a written scope document with a fixed-price or time-and-materials quote in CHF. Typical engagements cover gateway deployment, provider configuration, observability setup, and backup automation for configuration data and logs. There is no commitment at the scoping stage.


### Which LLM providers can I route through LiteLLM?

LiteLLM supports over 100 providers including OpenAI, Anthropic, Mistral, Cohere, Azure OpenAI, and self-hosted models served via vLLM or Ollama, including open-source models like Llama, Apertus (the Swiss AI foundation model), and Qwen. VSHN configures provider connections, API key management, and failover routing on Kubernetes so your applications get a single reliable endpoint regardless of which models you use behind the scenes.


### How does VSHN ensure data sovereignty for LiteLLM workloads?

The LiteLLM proxy, all request logs, API keys, and configuration run in Swiss data centers operated by Swiss or European sovereign cloud providers. All operational access is from Switzerland-based engineers. You control which external LLM providers receive prompts, and we provide audit trails for compliance reporting. See our [sovereignty assessment](/sovereignty/) for details on how VSHN scores against the EU Cloud Sovereignty Framework.


### Can VSHN integrate LiteLLM with existing infrastructure?

Yes. LiteLLM exposes a standard OpenAI-compatible API, so existing applications need no code changes. VSHN also integrates LiteLLM with MCP servers, retrieval-augmented generation pipelines, and managed PostgreSQL with pgvector for vector storage - with automated backups and up to 99.99% SLA as all our managed database services.


### What monitoring and observability does VSHN provide for LiteLLM?

VSHN integrates Prometheus and Grafana into every managed platform, with custom dashboards for LiteLLM-specific metrics: request latency (p50, p95, p99), tokens per request, cost per provider, error rates, and cache hit ratios. Alerting rules notify your team and our 24/7 operations center when metrics breach thresholds, so issues are caught before they affect users.


### How do I get started with VSHN's LiteLLM consulting?

Contact us through the form below for a free initial consultation. We assess your current LLM usage patterns, provider requirements, and compliance constraints, then propose an architecture running on APPUiO, OpenShift, or your preferred infrastructure. LiteLLM consulting is part of VSHN's broader LLM Operations practice -- see [llmops.ch](https://www.llmops.ch) for the full picture.


## Book a LiteLLM consultation

Tell us about your LLM provider landscape and gateway requirements. VSHN provides a free initial consultation covering LiteLLM architecture, provider routing, and a scoped proposal for your deployment.

---

## Partner with VSHN on LiteLLM | VSHN

# Partner with VSHN on Managed LiteLLM

You build AI applications that need reliable LLM access across multiple providers. LiteLLM gives your applications provider failover, cost optimisation, and a unified API, but running the proxy in production requires operations expertise. VSHN handles LiteLLM proxy operations, infrastructure, monitoring, and 24/7 support so your development team stays focused on shipping features.

## How we collaborate

**Lead Partner model.** For each project, one of us is the customer's single point of contact. Who leads depends on the project, agreed per engagement. The Lead Partner drives the project, handles invoicing, and owns first-level support.

**Joint delivery.** You handle consulting, integration, and project management. VSHN handles infrastructure operations, monitoring, backups, and SLA. Or the other way around, depending on the project. Roles are agreed per engagement, not locked into a rigid structure.

**Flexible billing.** Invoice the customer together or separately, agreed per project. Both models are supported: each party invoices their share directly, or one party invoices the full amount and redistributes.

**Protected relationships.** No undercutting. Your customer stays your customer. Existing relationships are respected on both sides, with contractual protections for both parties.

## Division of labour for Managed LiteLLM

| Your role | VSHN's role |
|-----------|-------------|
| AI application development | LiteLLM proxy provisioning and operations |
| Provider failover and routing strategy | Infrastructure management and scaling |
| Cost optimisation across LLM providers | Monitoring, alerting, and 24/7 incident response |
| API integration and client onboarding | LiteLLM upgrades and security patches |
| Project management and customer relationship | SLA with defined response times |

## Partners delivering LiteLLM

Our partner network is growing. See current VSHN partners at [servala.com/partners](https://servala.com/partners/).

## Become a partner

Interested in delivering managed LiteLLM together? Let's explore how we complement each other.

[Book a partnership discovery call](https://aarno.cal.vs.hn/15-llmops?view=compact) or [start a partnership conversation](#contact).


---

## LiteLLM Sovereignty — Swiss AI Gateway | VSHN

# LiteLLM Sovereignty: A Sovereign Gateway for Your LLM Traffic

LiteLLM is an open-source LLM gateway that provides a unified API across multiple LLM providers. Every API call routed through LiteLLM carries metadata: which models you use, how often, what your token consumption looks like, and even the prompts themselves depending on configuration.

When that gateway runs on US infrastructure, all routing decisions, usage analytics, and API keys are governed by US law and accessible under the [CLOUD Act](https://en.wikipedia.org/wiki/CLOUD_Act) without Swiss judicial process. Running LiteLLM on Swiss infrastructure under Swiss law keeps your routing and usage data sovereign.

Sovereignty is more than where the gateway runs. The EU Cloud Sovereignty Framework defines eight dimensions that determine whether your provider is truly sovereign.

## Why LiteLLM is a strong choice for sovereign AI routing

Unlike proprietary API management platforms, LiteLLM gives you:

- **No vendor lock-in**: switch between LLM providers (OpenAI, Anthropic, Mistral, local models) through a single API
- **Full code auditability**: LiteLLM is open source, every routing decision is inspectable
- **Usage data stays local**: token counts, model selection patterns, and cost data remain on your infrastructure
- **API key isolation**: your provider API keys are stored where you control them, not in a third-party SaaS
- **Community-governed**: active open-source project, not dependent on a single vendor's roadmap

VSHN operates LiteLLM on Swiss Kubernetes clusters. Combined with VSHN's Swiss ownership and operations, this creates a fully sovereign AI gateway.

## LiteLLM sovereignty compared

| Dimension | Proprietary API Gateways (US SaaS) | Self-hosted on US Cloud | VSHN Managed LiteLLM |
|-----------|-----------------------------------|------------------------|---------------------|
| **Ownership** | Various US companies | Customer (on US infrastructure) | VSHN AG (Switzerland) |
| **Governing law** | US law | US law (cloud provider) | Swiss law |
| **CLOUD Act** | Exposed | Exposed (via cloud provider) | Not exposed |
| **Data location** | USA | Depends on region (US-controlled) | Switzerland (Cloudscale, Exoscale, or your choice) |
| **Gateway software** | Proprietary | Open source (self-managed) | Open source (LiteLLM, VSHN-managed) |
| **Usage data access** | Provider has access | Cloud provider has infrastructure access | VSHN has operational access only for authorized support — never used for model training |
| **Operations team** | USA | Customer's team | Switzerland ([Swiss-only option](https://products.vshn.ch/support_plans.html#_option_switzerland_only_support)) |
| **Certifications** | Varies | Depends on cloud provider | [ISO 27001](https://www.vshn.ch/wp-content/uploads/2025/12/ISO-27001-certificate-VSHN-2024.pdf), ISAE 3402 Type II |

## VSHN sovereignty self-assessment

We applied the EU's [Cloud Sovereignty Framework](https://commission.europa.eu/document/09579818-64a6-4dd5-9577-446ab6219113_en) (v1.2.1, October 2025) to our own services. This framework was used to score providers in the EU's [EUR 180M sovereign cloud tender](https://ec.europa.eu/commission/presscorner/detail/en/ip_26_833) in April 2026. Three pure-European providers achieved SEAL-3, while a consortium involving Google Cloud scored only SEAL-2.

*This is a self-assessment, not a formal SEAL certification. We publish it for transparency so customers can evaluate our sovereignty profile using the same structured criteria the EU uses.*

| # | Dimension | Weight | Assessment | Evidence |
|---|-----------|--------|-----------|----------|
| SOV-1 | Strategic | 15% | **Strong** | Swiss AG, no foreign parent, all shareholders Swiss citizens ([Commercial Register](https://zh.chregister.ch/cr-portal/auszug/auszug.xhtml?uid=CHE-275.566.226)) |
| SOV-2 | Legal | 10% | **Strong** | Swiss law ([GTC](https://products.vshn.ch/legal/gtc_en.html)), no CLOUD Act, [EU adequacy decision](https://commission.europa.eu/law/law-topic/data-protection/international-dimension-data-protection/adequacy-decisions_en) |
| SOV-3 | Data & AI | 10% | **Strong** | Swiss DCs by default. Sovereign key management via [Managed OpenBao](https://www.openbao.ch) + [Swiss HSM](https://cloud.securosys.com/cloudhsm) |
| SOV-4 | Operational | 15% | **Strong** | Swiss 24/7 ops, [Swiss-only support option](https://products.vshn.ch/support_plans.html#_option_switzerland_only_support). All services on vanilla Kubernetes |
| SOV-5 | Supply Chain | 20% | **Strong** | Infrastructure-agnostic — [customer chooses provider](https://servala.com/providers/). Open-source software |
| SOV-6 | Technology | 15% | **Strong** | 100% open source. VSHN contributes to [K8up](https://github.com/k8up-io) (CNCF), [Crossplane providers](https://github.com/vshn), [Project Syn](https://github.com/projectsyn) |
| SOV-7 | Security | 10% | **Strong** | [ISO 27001](https://www.vshn.ch/wp-content/uploads/2025/12/ISO-27001-certificate-VSHN-2024.pdf), ISAE 3402 Type II, Swiss SOC. [FINMA-regulated customers](https://www.vshn.ch/en/solutions/solutions-for-banks-and-financial-service-providers/) |
| SOV-8 | Environmental | 5% | **Moderate** | DC operators: Green Datacenter AG (ISO 22301/27001/27701), [Exoscale sustainability](https://www.exoscale.com/sustainability/). [VSHN CSR policy](https://handbook.vshn.ch/corporate_social_responsibility_policy.html) |

**Overall: SEAL-3 equivalent**, the same level achieved by the winners of the EU's own sovereignty tender. No provider worldwide achieved SEAL-4: it requires fully EU/EEA-sourced hardware supply chains and open-source foundations, structural gaps shared by every cloud provider.

Try Swiss infrastructure: [APPUiO](https://www.appuio.ch) (managed Kubernetes, free trial), [Exoscale]({{partner:exoscale.signup_url}}) (Swiss IaaS). Want help choosing? [Contact us](#contact).

## Get a sovereignty assessment for your AI gateway

If you're routing LLM traffic through US-hosted services or evaluating sovereign alternatives, we can assess your current setup against the EU framework and design a LiteLLM deployment that keeps your routing data, API keys, and usage analytics under Swiss jurisdiction.