One key. Big open-weight AI models. Credits that keep piling up.
Virsilipas is our OpenAI-compatible AI API. Point any tool that takes a base URL at it and use GLM-5.3, DeepSeek-V4-Pro and six more open-weight models, plus Kimi K3.1 Pro, on one key, paid in credits that currently never expire.
Get credits from 9.99€ a month See it running live
Live numbers: requests, tokens and success rate of the last 7 days are on virsilipas.mcx.fi.
What you get
The big models
GLM-5.3, DeepSeek-V4-Pro and Kimi K3.1 Pro with a context of a million tokens, plus thinking and instant variants. Fast models for the everyday work, and models with few refusals when you need them.
Works with your tools
OpenAI-compatible chat completions at https://virsilipas.mcx.fi/v1. The same key also speaks the Anthropic Messages format (Claude Code) and the Gemini API format (Gemini CLI).
Credits that stay
Credits currently never expire. What you do not use this month is still there next month, and every renewal adds more on top.
Virsilipas AI Credit Plans
- Virsilipas 100
- 9.99€
monthly billing - 9,990,000 credits every month
- Every euro you pay comes back as credits
- Up to 6.2 million input tokens on GLM-5.3
- Or up to 37.3 million on the fast default model
- Credits on your key within minutes of payment
- Currently never expire
- Virsilipas 125
- 49.99€
monthly billing - 62,487,500 credits every month
- 25 % more credits per euro
- Up to 38.9 million input tokens on GLM-5.3
- Or up to 233 million on the fast default model
- Credits on your key within minutes of payment
- Currently never expire
- Virsilipas 150
- 299.99€
monthly billing - 449,985,000 credits every month
- 50 % more credits per euro
- Up to 280 million input tokens on GLM-5.3
- Or up to 1.7 billion on the fast default model
- Credits on your key within minutes of payment
- Currently never expire
+5,000,000 credits with your first payment when you order from this page: the buttons add the code VIRSILIPAS. Each customer can use it on one order, for the first 250 orders that use the code; every eligible plan in that order gets the bonus. A refund takes these credits back too.
We may change the plans and their credit amounts at any time.
Months on the plan, credits left if none are spent. Under the current rules nothing expires; spend them whenever you like.
Need more? Order a plan several times: each one adds its own credits every month, all to the same key. Prices exclude VAT, like all our listed prices. A refund takes back the credits that payment added.
The models
Ask for a model by its alias. The two main large models lead the list, and xl runs Kimi K3.1 Pro for the hardest reasoning and coding tasks; every alias below is on the same key and the same balance.
GLM-5.3 · large
A large model with one million tokens of context that thinks before it answers. large-think thinks at length, large-instant answers straight away.
1.61€ per million input tokens, 7.15€ per million output tokens on the 9.99€ plan.
DeepSeek-V4-Pro · alt-large
A second large model with a different style: one million tokens of context, answers directly, and alt-large-think reasons first.
2.32€ per million input tokens, 4.64€ per million output tokens on the 9.99€ plan.
| Alias | Model | Context | € / M input | € / M cached input | € / M output | Good for |
|---|---|---|---|---|---|---|
large | GLM-5.3 | 1M | 1.61 | 0.36 | 7.15 | Large, thinks before it answers |
alt-large | DeepSeek-V4-Pro | 1M | 2.32 | 0.18 | 4.64 | Large, answers directly; -think to reason |
xl | Kimi K3.1 Pro | 1M | 3.57 | 0.36 | 17.87 | Hardest reasoning and coding, always reasons |
default | GLM-5.3-Flash | 1M | 0.27 | 0.05 | 0.89 | Fast everyday model, the cheapest |
alt | DeepSeek-V4.1-Flash-1017 | 1M | 0.36 | 0.01 | 1.07 | Fast, very cheap on repeated input |
nolimits-story | L3.1-70B-Euryale-v2.2 | 128k | 1.52 | 1.52 | 1.52 | Fiction and role-play |
nolimits-flash | GLM-5.3-Flash uncensored | 1M | 0.36 | 0.13 | 1.43 | Few refusals, newest generation |
nolimits-qwen | Qwen3.8-27B uncensored | 1M | 1.79 | 0.39 | 5.36 | Few refusals, mid-size |
nolimits-mimo | MiMo-V2.6-Flash | 1M | 0.89 | 0.49 | 2.68 | Few refusals, fast reasoning |
Euro prices are on the 9.99€ plan, where 1,000,000 credits cost 1€. The 49.99€ plan gives 1.25 times and the 299.99€ plan 1.5 times the credits per euro, so the same tokens cost a fifth and a third less there. Claude Code (the Anthropic Messages format) works with every alias except xl, nolimits-flash, nolimits-qwen and nolimits-mimo. Prices as of 28 October 2026; the live prices, aliases and descriptions are on the model cards.
Why Virsilipas
The model provider does not learn who you are. Your request goes on with our account, from our server, among every other customer's requests; your name, account, IP address and key stay with us. What you or your app put in the request, the prompt included, does reach the provider, and we cannot audit what they keep, so leave passwords and personal details out of it.
We do not keep your prompts. The credit service is open source, mcxVirsilipas on GitHub, and its code never stores or logs the text of your prompts or answers; per request it records counts such as tokens and credits, the model, status and timing.
If a provider fails, your request moves on. GLM-5.3, GLM-5.3-Flash, DeepSeek-V4-Pro and DeepSeek-V4.1-Flash-1017 have a second provider behind them: when the first one fails before the answer starts, the second takes the request at the same price. This covers chat and Gemini-format requests. The Claude Code format, xl and the models with few refusals have one provider each.
Your credits keep adding up. Under the current rules credits never expire. Buy a plan for a busy month and the leftovers wait for the next project.
Watch it run. Requests, tokens, success rate and the model mix are public, hour by hour, on virsilipas.mcx.fi.
Already a customer? Your services already earn credits on every invoice you pay, seedboxes and storage boxes included, on this same key: see AI credits. A plan adds to that.
Pick your planStart in three steps
1 Pick a plan above and pay the invoice. Your credits land on your key within minutes, and again every month the plan renews.
2 Open your key: Client Area, then AI credits, then Virsilipas AI key. Your account has one key for everything, made for you on the first credits; it starts with vsk-. The same page shows your balance, your use and the credit history.
3 Set up your tools. On Linux, as yourself, no root: one line points the AI tools you already have, such as Codex, Claude Code, Gemini CLI and OpenCode, at your credits. Run each as virsilipas-<name>.
wget -qO- https://virsilipas.mcx.fi/virsilipas.sh | bash
To install a tool too, add its name at the end:
wget -qO- https://virsilipas.mcx.fi/virsilipas.sh | bash -s -- codex
The line asks for your key once and keeps it in ~/.virsilipasKey; if that file is already there, it uses it.
On a Pulsed Media seedbox with a current PMSS and that file, codex, claude and gemini start on your credits by themselves, unless you signed them in to an account of your own.
Any other tool: base URL https://virsilipas.mcx.fi/v1, your key, and a model alias such as large.
From a shell
curl https://virsilipas.mcx.fi/v1/chat/completions \
-H "Authorization: Bearer $KEY" \
-H 'Content-Type: application/json' \
-d '{"model": "large", "messages":
[{"role": "user",
"content": "Say hello."}]}'
curl https://virsilipas.mcx.fi/v1/balance \
-H "Authorization: Bearer $KEY"
From JavaScript (Node 18, no packages)
const KEY = process.env.VIRSILIPAS_KEY;
const URL = 'https://virsilipas.mcx.fi/v1';
const res = await fetch(`${URL}/chat/completions`, {
method: 'POST',
headers: { 'Authorization': `Bearer ${KEY}`,
'Content-Type': 'application/json' },
body: JSON.stringify({ model: 'alt-large',
messages: [{ role: 'user',
content: 'Say hello.' }] }),
});
const reply = await res.json();
console.log(reply.choices[0].message.content);
console.log(`credits: ${reply.usage.credits}`);
Guides: every tool the one line can set up, AI coding tools on a seedbox, your credits on any Linux server, Pikkumies, and every API setting in the README on GitHub.
Run any agent you like, on your own seedbox
Our seedboxes run the AI agents you already use, and the one line from step 3 points them at your Virsilipas credits: OpenClaw, OpenCode, Claude Code, Codex, Gemini CLI, Qwen Code, Goose, Aider, Hermes Agent and more on the full list. Two have their own pages: OpenClaw, turned on with one button in the panel, and Pikkumies, our own helper that does the work inside your seedbox.
Need a box for them? An M10G SSD seedbox earns AI credits at token multiplier ×5 to ×21 by plan size, and ordered from here it gets the same +5,000,000 credits on its first payment.
M10G SSD seedboxes
- M10G SSD 320G
- 6.49€
monthly billing - 320 GiB SSD RAID0 storage
- I/O: Standard (100)
- 10 Gbps networking
- 4 CPU cores · Standard (100)
- 1.5 GB RAM
- 6 400 GiB traffic/mo
- Token multiplier ×6
- AI credits 60 000 per €
- Order bonus +5 000 000 AI credits
- M10G SSD 455G
- 8.99€
monthly billing - 455 GiB SSD RAID0 storage
- I/O: Standard (100)
- 10 Gbps networking
- 8 CPU cores · Standard (100)
- 2 GB RAM
- 9 700 GiB traffic/mo
- Token multiplier ×9
- AI credits 90 000 per €
- Order bonus +5 000 000 AI credits
- M10G SSD 660G
- 10.49€
monthly billing - 660 GiB SSD RAID0 storage
- I/O: Standard (100)
- 10 Gbps networking
- 8 CPU cores · Standard (200)
- 3 GB RAM
- 14 800 GiB traffic/mo
- Token multiplier ×10
- AI credits 100 000 per €
- Order bonus +5 000 000 AI credits
Want the detail behind the specs? What CPU priority, I/O priority, traffic and the token multiplier mean.
Questions
What is Virsilipas?
An OpenAI-compatible API for open-weight AI models, run by Pulsed Media. One key, one balance, paid in credits. The name is the song-chest of the Kalevala, opened before the singing starts.
Why use Virsilipas instead of a model provider's own API?
The provider sees our account and our server, not you, and your requests travel among everyone else's. The credit service keeps no prompt text. The main models fail over to a second provider for chat and Gemini-format requests. One key reaches every model with no provider account or card of your own. It also works with Claude Code and Gemini CLI, and your Pulsed Media services already put credits on it.
Do the credits expire?
Currently no. Credits stay on your key and keep adding up month after month.
How fast do the credits arrive?
Within minutes of a paid invoice, for the first payment and for every renewal.
Can I buy more than one plan?
Yes. Order a plan as many times as you like; each adds its own credits every month to the same key.
What happens if I cancel?
The plan stops renewing and stops adding credits. Credits already on your key stay there. A refund takes back the credits that payment added.
Which tools work with it?
Anything that lets you set an OpenAI-compatible base URL and an API key, plus Claude Code through the Anthropic Messages format and Gemini CLI through the Gemini API format. Requests are text only.
How do I set up Codex, Claude Code or another AI tool?
On Linux, run the one line from step 3 above. It asks for your key once, points the AI tools you already have at your credits and installs the ones you name, without root. The full tool list shows how to add a tool by name.
Where do I see my balance?
On the Virsilipas AI key page in the Client Area, or with GET /v1/balance and GET /v1/usage on your key.