Own your Qwen3.8-27B endpoint.
Zero data retention.

  • Up to 1M context — whole repo, no RAG
  • Point your coding agent at it in 3 lines
Launch a server — from $0.69/hr See the numbers
up to 1M context
Blackwell / Ada
zero data retention
per-second billing
GLM-5.2 crossed out — Qwen3.8-27B is as smart, faster, and cheaper
Qwen3.8-27B is as smart, faster, and cheaper — on a server that is only yours.
A dedicated server standing alone on its own island, whales circling freely around it
Your endpoint is an island: only your traffic ever touches it.
Agents now burn 7.3 trillion tokens a week on OpenRouter — 14× in a year. This is the whale. We priced for it. Source: a16z / openrouter.ai

Your agent is a whale. Per-token pricing is built for sardines.

Here's the story every heavy agent user lives — and the math that decides who wins.

1

Your agent re-reads everything, every turn.

A coding agent doesn't send a short question. It sends the whole conversation, the whole file, the whole plan — again, on every single turn. One prompt into an existing conversation at 1M context is already more than 100,000 input tokens. Ten turns an hour is a million tokens an hour. A serious setup — several agents, long horizons, big repos — runs 10 million tokens an hour, all day, every day.

2

Per-token APIs bill that whale at sardine prices… per sardine.

At 10M input tokens an hour, GLM-5.2's meter reads $14/hr. Kimi K3 reads $30/hr. And that's before output. The more your agent works, the more you pay — linearly, forever. The per-token model was built for people who ask one question and walk away. It is the exact opposite of what you are.

3

On a dedicated endpoint, the tokens are free.

You pay for the hour, not the tokens. 10M tokens an hour? 100M? 1 billion tokens an hour, per user, and that's fine. The meter doesn't care. Your server runs only your traffic, with up to 1M of context — and the price is the same whether your agent is idle or overflowing it. Heavy use is not a penalty here. It's the point.

4

And nothing you send is kept.

Your endpoint is dedicated to you. Your prompts, your code, your context — zero data retention. No training on your work, no logs of your conversations, no shared anything. The server is yours for the hour; when it stops, it's gone.

Your own lane. The whale swims alone — that's the whole product.

Pricing

Prepaid credits. $10 minimum. Your server auto-stops after your configured idle time (default 15 min, you can change it) and when credits run out — you only pay while your agent works. A new server takes up to 10 minutes to deploy. Per-second billing, no egress fees.

ProductCapacityPrice

"Concurrent users" = concurrent in-flight generations (max-num-seqs), not unique humans. You get a dedicated server: zero data retention, auto-stop, per-second billing.

Your whale is waiting.

Credits in, server up, agent pointed. From $0.69/hr — you only pay while it works.

Start now — +30% bonus

3 lines. Any agent.

Every major coding tool speaks OpenAI-compatible. Swap the base URL, paste your key, done.

1

Add credits

$10 minimum, prepaid. No subscription, no invoice cycle.

2

Pick your server

Four tiers from $0.99/hr. Change your mind later — it's hourly.

3

Wait for live — then plug in

Up to 10 minutes to deploy. Point your agent at the endpoint and go.

curl

curl https://api.notoken.cloud/{instance_id}/v1/chat/completions \
  -H "Authorization: Bearer $TNT_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen3.8-27b","messages":[{"role":"user","content":"Hello"}]}'

Claude Code / Cline / Cursor / Aider / OpenCode

base_url:  https://api.notoken.cloud/{instance_id}/v1
api_key:   tnt-...          (from your dashboard)
model:     qwen3.8-27b

Your instance_id appears in the dashboard once the server is live. API keys label your tasks (see what each key is doing in the dashboard). They don't limit concurrency — that's your product's max-num-seqs.

Every server ships with

Qwen3.8-27B, ready to go

Every server ships already loaded with Qwen3.8-27B — tuned and optimized, no setup on your side. Launch it and it is live in minutes.

Auto-stop, your rules

Your server stops after your configured idle time (default 15 min — you can change it in the dashboard) or when credits hit zero (60s grace, in-flight generation finishes). New servers take up to 10 minutes to deploy. You pay only while it works.

AI support, 24/7

Our support is an AI — on this site and in your dashboard. Powered by the same model you're buying.

Everything's included. Start now.

Auto-stop, AI support, per-second billing — all on every server, no add-ons.

Start now — +30% bonus

The noTOKEN.cloud newsletter

New SKUs, new model drops, pricing changes, and the occasional benchmark we're proud of. No spam — unsubscribe anytime.