Why Obsidian Peaks
Your own RTX 5090, the same machine every month. Owned by us and run in the Stockholm region, from a Swedish company.
The GPU
The GPU itself.
Root access on hardware nobody else uses during your term. CUDA, so what runs on an RTX 5090 runs here. Any open model on Hugging Face, pulled when the box starts.
- Root access
- Yours alone during your term
- Disk wiped at teardown
Sweden
In the Stockholm region, by a Swedish company.
Our RTX 5090s are owned by us and run in the Stockholm region, Sweden. Public traffic exits through our server in Helsinki (EU). The contract, the invoice and the support come from Obsidian Peaks Technologies AB in Stockholm, under Swedish law.
- Owned hardware, Stockholm region
- Swedish law
- Support in English and Swedish
Dedicated
Dedicated inference box.
Your model, your OpenAI-compatible URL, on an RTX 5090 that is yours by the month: 8 000 SEK/month ex VAT, 7 200 SEK/month on a 12-month term.
- OpenAI-compatible endpoint (vLLM)
- Any open model
- Root access
Per token or GPU
Why the Peaks are higher than Berget
Berget AI sells a per-token API; we rent you the GPU.
| Per-token API vs your own GPU | Per-token API | Your own GPU |
|---|---|---|
| What you buy | Tokens | The GPU |
| Who else runs on the hardware | A shared pool | Nobody during your term |
| Models | Their shelf | Any |
| Access | API only | Root + API on your box |
| Pricing | Per token, prepaid plan required | Per month, published |
| When it wins | Small or bursty volume | Steady volume, isolation, custom stacks, fine-tuning |
Break-even
Where the line goes.
One dedicated 5090 at 8 000 SEK/month costs about the same as 1.5 billion output tokens at a typical Swedish per-token API’s list price. Below that, tokens are cheaper. Above it, or when you need isolation, a custom stack or fine-tuning, the GPU wins.
List price used: €0.50 per million output tokens, the published price of a 31B open model at a Swedish per-token API on 23 Sep 2026; 8 000 SEK/month converted at about 11 SEK per euro. Ex VAT.
Tokens
A month, priced both ways.
What one box makes in a month at full load, and what that month costs at their price.
| Model | A month at full load, one box | That month at Berget | Obsidian Peaks |
|---|---|---|---|
| Kimi-K3about 20 boxes of memory, in one chassis · €3.00 · €15.00 per M tokens | — | — | on request |
| Qwen3.8-27B-FP8one box, tight fit · €0.40 · €3.00 per M tokens | 1.3 B tokens (~500/s) | about 43 000 SEK | 8 000 SEKtwo boxes, room for context: 16 000 SEK |
| GLM-5.3-Flashsize not public · €0.25 · €0.50 per M tokens | — | — | — |
| Gemma-4-31Bone box, 4-bit · €0.25 · €0.50 per M tokens | 2.6 B tokens (~1 000/s) | about 14 000 SEK | 8 000 SEKtwo boxes, FP8: 16 000 SEK |
| Mistral-Small-3.2-24Bone box · €0.30 · €0.30 per M tokens | 2.6 B tokens (~1 000/s) | about 8 600 SEK | 8 000 SEK |
| KB-Whisper (speech-to-text)one box · €0.12 per hour of audio | 43 200 hours of audio (~60× realtime) | about 56 000 SEK | 8 000 SEK |
| E5 embeddingsone box · €0.03 per M tokens | 51.8 B tokens (~20 000/s) | about 17 000 SEK | 8 000 SEK |
| FLUX.1 (image generation)one box · not on their list | 1.0 M images (~24 a minute) | not on their list | 8 000 SEK |
The month’s output is our estimate for one 5090 kept busy around the clock, output tokens only; measured figures from our own boxes will replace it. Send less than that and their API is cheaper on price alone. Send more, or want what the box adds, and the box wins.
Their prices: api.berget.ai model list, 23 Sep 2026; 11 SEK per euro; bought through a prepaid plan from €25 a month, credits non-refundable, usage past the credit at list price. Kimi-K3 is a trillion-parameter-class model: about 600 GB at 4-bit, twenty boxes’ worth of memory in one chassis; for Kimi, their API is the sane buy.
On top
What the box adds.
What a GPU of your own adds that no token can.
Yours alone
One tenant per GPU. Prompts, files and weights stay on your box; traffic to it passes through our relay in Helsinki (EU).
Any model
Text, vision, speech, image generation, your own fine-tunes: whatever fits in 32 GB.
Agents that never stop
Coding agents and pipelines in Docker, around the clock, no meter. Their coding seats are €150–500 per person a month, rate-limited; one box serves the whole team.
Root access
SSH in, install what you like, keep the state between jobs.
One price
No per-token bill, no rate limit, no prepaid plan. Locked for your term.
Questions
Questions and answers.
- What do I get when I rent a GPU?
- One whole machine with an NVIDIA RTX 5090 (32 GB of VRAM), owned by us and run in the Stockholm region, Sweden: yours by the month under a signed agreement, the same machine every month, with root access.
- How does billing work?
- A published monthly price: 8 000 SEK/month ex VAT, or 7 200 SEK/month on a 12-month term, for companies. Storage, traffic and electricity are included, and the invoice comes from Obsidian Peaks Technologies AB.
- What does “only you” mean?
- During your agreement nobody else runs on the machine: it is yours alone. We keep an operations key for support, restores, urgent security maintenance and incidents; every use is logged and we tell you afterwards.
- Which models can I run?
- Any open model on Hugging Face, pulled when the box starts. CUDA: what runs on an RTX 5090 runs here.
- Where is the hardware, and whose company is it?
- Our RTX 5090s are owned by us and run in the Stockholm region, Sweden. Public traffic exits through our server in Helsinki (EU). The contract, the invoice and the support come from Obsidian Peaks Technologies AB in Stockholm, under Swedish law.
