One API key for all of them.
Capless is the engine that powers your coding agents. Connect it to Cursor, OpenCode, Codex, Cline, etc.. One flat monthly bill. No token meter. No multiple subscriptions.
How fast the model writes, letter by letter.
Your ideas flow without cuts
The speed adding every user at once.
Scales with your team, no degradation
How long until the first word shows up.
Answers before you finish the thought
The model reuses context it already read.
Long sessions, constant speed
How long it ran without a single incident.
Weeks of real work, that stable
TU HERRAMIENTA
CAPLESS GATEWAY
MOTOR DE INFERENCIA
GPU DEDICADA
What runs beneath every prompt.
Dedicated high-performance GPUs
The GPU serves only Capless: we don't resell third-party capacity.
Per-key quotas and concurrency
The 4h window and session limits stop any single user from saturating the GPU.
24/7 health checks & auto-recovery
If something breaks, it stands back up before you notice.
Zero. Ephemeral RAM only
What you write never touches a disk. Ever.
No catalog bloated with 500 redundant models. Only weights proven at code generation, refactoring and terminal utilities.
~3B-active Mixture-of-Experts for TypeScript, Python, Go, Rust and SQL. Hybrid attention for long context, reliable tool calling and optional reasoning (capless-coder-thinking).
A lightweight model for commits, PR summaries and log filtering. Shipping in the next phase — today the beta serves the coder.
Multilingual embeddings for RAG over your code repo — English and Spanish. Shipping in the next phase at no extra cost on any plan. Audio (STT/TTS) comes after.
Not ours, not anyone's. Your prompts and completions exist only in GPU RAM during inference and are purged when it ends. Zero-logs, zero-training.
One fixed monthly quota. No counter. No surprises.
Fair-use limits published in the FAQ. No fine print.
One subscription for all your agents. Instead of paying each tool separately.
| WHAT WE COMPARE | SEPARATE SUBS ($20–100/MO EACH) | CAPLESS (ONE FLAT BILL) |
|---|---|---|
| What you pay | A plan with “generous usage” that isn't expressed in tokens. | Published tokens: 6M, 20M or 50M per month. |
| How it runs out | Windows and weekly caps that change without notice. | Monthly quota + a 4h rolling window, published and stable. |
| Repeating yourself | Each tool charges it separately. | Resending context doesn't burn your quota. |
| Your code | Each provider has its own privacy policy. | Never stored. Never used for training. Period. |
| Your tools | Each one has its own key system. | One API key for all of them. |
Any OpenAI-compatible client works by changing one line: Cursor, VS Code, OpenCode, Hermes Agent, Aider, Continue, etc. — same pattern: baseURL + API key.
Full documentation with exact snippets at beta launch.
No plan is unlimited: each one has a published monthly quota (6M, 20M or 50M tokens) and a 4-hour rolling window. When exhausted, the API returns 429 with the exact reset time. No extra charges, no automatic top-ups, and cache reads don't consume quota.
More quota, more context and more concurrency. The price per million drops from Starter to Builder and Pro; the model and speed are the same.
Published and generous: a monthly quota per plan plus an automatic window reset every few hours, so everyone gets the same speed at any hour. If you ever hit it, your priority dips for a while — zero extra charges.
They run on our dedicated GPU instances. We operate a Zero-Logs architecture: your prompts and code snippets exist only in volatile memory (VRAM) during inference and are purged immediately. They are never written to disk or used for re-training.
Yes. Any tool that accepts an OpenAI-compatible endpoint (baseURL) works instantly by changing one config line and pasting your Capless API key.
Because they can be audited, the real cost of serving them is far lower, and that saving is exactly what makes the flat price possible. We don't offer 400B models: we host 30B MoE models that actually fit on accessible hardware.
Join the waitlist with your email. The beta opens in waves (7 days of Builder free, no card) so speed never degrades; we'll email you when your wave opens. Plans range from $10 to $50/mo when you decide to continue.
Yes: 14 days, no questions asked on paid subscriptions. Email [email protected] and we refund the current month.
We release access in controlled waves as we provision capacity, so generation speed never drops. Join the waitlist and we'll email you when your wave opens.
Prefer to try it free first?
The Builder trial is released in waves. Join the list and we'll let you know when your wave opens. In a hurry? Start now from $10/mo.
RECEIPT #00 · WAITLIST · COSTE HOY $0
Powered by Tally. Zero spam: we only email you when your wave opens.