---
title: "WestAI / KI:Inferenz.nrw LLM Hosting free inference"
description: "No-cost research and development inference across 6 models; not unrestricted production use."
canonical_url: "https://freeinferencing.com/provider/westai_ki_inferenz_nrw/"
md_url: "https://freeinferencing.com/provider/westai_ki_inferenz_nrw.md"
last_updated: "2026-09-19"
---

# WestAI / KI:Inferenz.nrw LLM Hosting

> No-cost research and development inference across 6 models; not unrestricted production use.

## Classification

- **Directory:** Current
- **Free access:** Research / development
- **Status:** Restricted access
- **Confidence:** High
- **Payment card:** Unknown
- **Account:** Not documented
- **Equivalent paid value:** Not quantifiable
- **API endpoint:** `https://chat.kiconnect.nrw/api/v1`

## Models mentioned

- `Mistral-Small-3.2-24B`
- `Mistral-Small-4-119B-2603`
- `Apertus-70B`
- `gpt-oss-120B`
- `Devstral-Small-2-24B-Instruct-2512`
- `Qwen3-Embedding-8B`

## Limits and terms

```yaml
westai_request_limit: none_currently_established
westai_token_limit: none_currently_established
kiconnect_limits: Dynamic per model and user group; parallel-request cap applies.
service_stage: beta
```

## What happens to your prompts?

**Partially private.** WestAI says prompts are processed in real time without being saved or logged, but explicit training, improvement, access, and deletion terms remain incomplete.

Privacy is audited separately from price. Review the current governing terms before sending sensitive or regulated data.

## Data governance and agreements

```yaml
data_governance:
  review_status: partial
  plan_scope: WestAI approved inference and KI:connect access to listed self-hosted models.
  prompt_retention: Prompt content is processed in real time and is not saved, logged, or stored.
  response_retention: not_documented
  ordinary_logging: Prompt-content logging is excluded; metadata fields and
    retention are not fully enumerated.
  model_training: No public route-specific no-training statement was found.
  product_improvement: not_documented
  human_or_operator_access: Persistent prompt review is constrained by no storage;
    transient support/security access is not described.
  subprocessors_and_routing: Models are self-hosted on participating
    university/RWTH infrastructure with institutional identity systems.
  deletion_controls: No stored prompt should remain; metadata/account/response
    deletion controls are unspecified.
```

## Eligibility

```yaml
nrw_access: Members of participating NRW universities through KI:connect
westai_access: Reviewed affiliation and exploratory research or prototyping use case
commercial_product_use: false
initial_provision_cost_to_nrw_universities: 0
```

## API compatibility and modalities

- **Compatibility:** OpenAI Compatible
- **Modalities:** Text generation, Embeddings
- **Geography:** Germany

## Before you build with WestAI / KI:Inferenz.nrw LLM Hosting

### Read the classification narrowly

This record describes the bounded offer supported by evidence on 2026-09-19; it does not guarantee permanence, production suitability, uptime, latency, model quality, or access from every account and region. “Research / development” should be interpreted together with the Current directory placement, High confidence, Unknown payment-card status, and the plan-specific sources below.

### Resolve the live model route

The snapshot records 6 model IDs. Match the exact ID against the provider's current catalog before using it in code because zero-price routes, aliases, context limits, and feature support can rotate while an older documentation page remains online.

### Match the quota to the workload shape

Translate the allowance into peak requests per minute, input and output tokens, concurrency, retries, and every daily or monthly ceiling that applies to the intended account. The first limit reached by the workload is the practical ceiling. A large token pool can still fail interactive bursts, and a high request limit can still fail long-context work. Include tool calls and retry traffic, test the largest realistic payload, and treat research, experimental, and community access as conditional on their eligibility and fair-use terms.

### Preserve billing and privacy boundaries

The recorded payment-card requirement is Unknown, and account access is not documented. Confirm both in the live signup flow, set provider-side budgets when charges are possible, and observe the balance or usage fields after a complete request. The prompt-handling classification is **Partially private** because WestAI says prompts are processed in real time without being saved or logged, but explicit training, improvement, access, and deletion terms remain incomplete. Re-read the terms for the exact route and plan before sending sensitive, regulated, or proprietary content.

### Follow the evidence, then re-check it

This record links 5 first-party sources covering the offer, catalog, limits, pricing, terms, privacy, or adoption evidence available to the audit. Prefer the newest and most specific governing document or live catalog when sources disagree. A dated finding can become stale even when the page remains online, so retain the source and snapshot that supported the decision and submit a correction when a provider changes a material term.

### Plan fallback without policy drift

A fallback should preserve modality, context length, streaming, structured output, tools, safety controls, and data terms, not only API syntax. Decide which errors may retry, cap retry storms, and prevent an exhausted free route from silently switching to a billable model. Rotating aliases and free pools can change behavior without changing the endpoint, so retain the response model field and test at least one substitute route before the primary offer becomes unavailable.

### Monitor the offer as a dependency

Capture the model ID, response model, rate-limit headers, usage fields, latency, HTTP status, and provider request identifier. Watch authorization failure, quota exhaustion, catalog removal, policy revision, and balance movement as separate failure modes. Re-check the live catalog and governing sources on a schedule proportionate to the workload's importance, and keep an owner and exit path for any production dependency on volatile free capacity.

### Test one complete request before scaling

Start with the smallest permitted request using the exact credential, model ID, endpoint, region, and account type intended for deployment. Record the status, headers, usage fields, response model, latency, and dashboard balance movement. Then exercise an invalid model, quota exhaustion, or rate limit so failure is explicit and cannot silently switch to a paid route. Validate streaming, structured output, and tool calls separately because a free model can expose fewer features than its paid counterpart. Keep a budget ceiling outside the application whenever billing is possible, and do not send sensitive data until the observed route matches the reviewed agreement.

## Primary sources

- [Accessing LLMs](https://help.itc.rwth-aachen.de/service/5a9d03f1675f4f85ac9b3fd7bb853d44/article/80525f9e55c443af86d2698d0cbed743/): Official Docs
- [Available models](https://help.itc.rwth-aachen.de/service/5a9d03f1675f4f85ac9b3fd7bb853d44/article/eefe9314f19a42bd99d64b4df68780d5/): Official Catalog
- [KI-Inferenz NRW launch](https://www.itc.rwth-aachen.de/cms/it-center/it-center/aktuelle-meldungen/aktuelle-meldungen/~bndmqb/ki-inferenz-nrw-ki-modelle-fuer-hochsch/): Official Announcement
- [WestAI](https://westai.de/): Official Product
- [LLM Hosting](https://help.itc.rwth-aachen.de/service/5a9d03f1675f4f85ac9b3fd7bb853d44/): Official Docs

## Sitemap

See the full [semantic sitemap](/sitemap.md) for every page and markdown mirror.