# evroc | European inference provider profile and prices

[Directories](/directories/) › [European Inference](/eu/) › evroc

![evroc logo](/logos/evroc.svg)

Verified

evroc is a Sweden-based provider in the Sovereign cloud category with 16 listed models. No cached-input rate is published.

EU-owned EU hosting Sovereign cloud

[Visit website ↗](https://evroc.com) [API docs ↗](https://models.think.evroc.com/v1)

Overview Models Pricing Infrastructure Access Compliance Benchmarks Performance

## At a glance

Record

Ownership

evroc AB

Headquarters

Stockholm, Sweden

Hosting region

EU (Sweden)

Founded

Not published

Website

[evroc.com](https://evroc.com)

## Summary

Scope

evroc is a Sweden-based provider in the Sovereign cloud category with 16 listed models. No cached-input rate is published.

European cloud + AI; catalogue includes its own 'roc' model. 15-16 model listings.

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

### API access

OpenAI-compatible

### Access

API

### KYC

Not published

### Compliance

EU provider (sovereign cloud)

## Key models

16 listed

GLM-5.2 524K context · per 1M tokens Inference $1.44 / $5.75

roc 262K context · per 1M tokens Multimodal $2.88 / $11.52

Mistral Medium 3.5 128B 262K context · per 1M tokens Multimodal $1.73 / $6.9

Kimi K2.6 262K context · per 1M tokens Multimodal $1.44 / $5.75

Qwen3.8 27B 262K context · per 1M tokens Multimodal $0.87 / $3.5

Qwen3.6 35B A3B 262K context · per 1M tokens Multimodal $0.34 / $1.38

Gemma 4 26B A4B IT 262K context · per 1M tokens Multimodal $0.14 / $0.57

GPT OSS 120B 66K context · per 1M tokens Inference $0.23 / $0.92

Llama 3.3 70B Instruct FP8 128K context · per 1M tokens Inference $1.15 / $1.15

Qwen3 Embedding 8B 41K context · per 1M tokens Embedding $0.12 / $0

Qwen3 Reranker 4B 32K context · per 1M tokens Rerank $0.06 / $0

E5 Multilingual Large Instruct 512 context · per 1M tokens Embedding $0.11 / $0

Voxtral Small 24B 32K context · per 1M tokens Speech $0.0023 / $0

KB-Whisper Large 448 context · per 1M tokens Speech $0.0023 / $0

Whisper Large v3 448 context · per 1M tokens Speech $0.0023 / $0

Whisper Large v3 Turbo 448 context · per 1M tokens Speech $0.0023 / $0

## Pricing

List rates · USD

Model Type Input price Caching price Output price

GLM-5.2524K context · per 1M tokens Inference $1.44 \- $5.75

roc262K context · per 1M tokens Multimodal $2.88 \- $11.52

Mistral Medium 3.5 128B262K context · per 1M tokens Multimodal $1.73 \- $6.9

Kimi K2.6262K context · per 1M tokens Multimodal $1.44 \- $5.75

Qwen3.8 27B262K context · per 1M tokens Multimodal $0.87 \- $3.5

Qwen3.6 35B A3B262K context · per 1M tokens Multimodal $0.34 \- $1.38

Gemma 4 26B A4B IT262K context · per 1M tokens Multimodal $0.14 \- $0.57

GPT OSS 120B66K context · per 1M tokens Inference $0.23 \- $0.92

Llama 3.3 70B Instruct FP8128K context · per 1M tokens Inference $1.15 \- $1.15

Qwen3 Embedding 8B41K context · per 1M tokens Embedding $0.12 \- $0

Qwen3 Reranker 4B32K context · per 1M tokens Rerank $0.06 \- $0

E5 Multilingual Large Instruct512 context · per 1M tokens Embedding $0.11 \- $0

Voxtral Small 24B32K context · per 1M tokens Speech $0.0023 \- $0

KB-Whisper Large448 context · per 1M tokens Speech $0.0023 \- $0

Whisper Large v3448 context · per 1M tokens Speech $0.0023 \- $0

Whisper Large v3 Turbo448 context · per 1M tokens Speech $0.0023 \- $0

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**Sweden**

Provider group**Sovereign cloud**

ZDR**not stated**

DPA**Not published**

Cached input policy**No cached-input rate published.**

## Access

API & payments

API shape**OpenAI-compatible**

Access**API**

KYC**Not published**

Cached input policy**No cached-input rate published.**

## Compliance

Source-backed

DPA**Not published**

ZDR**not stated**

Retention**ZDR: not stated.**

Certifications

EU provider (sovereign cloud)

## 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.

[PreviousBerget AI](/eu/providers/berget) [NextScaleway](/eu/providers/scaleway)