Show HN: Endlesstokens – an LLM API billed by time, not tokens

Unlimited tokens for the length of your pass: no token cap, no request cap. Open the tap for a day or three and let your agents think as long as they need to.

OPENAI_BASE_URL=https://api.endlesstokens.ai/v1 OPENAI_API_KEY=<your-key>ANTHROPIC_BASE_URL=https://api.endlesstokens.ai ANTHROPIC_AUTH_TOKEN=<your-key>curl https://api.endlesstokens.ai/v1/chat/completions
-H "Authorization: Bearer <your-key>"
-H "Content-Type: application/json"
-d '{"model": "<model-name>",
"messages": [{"role": "user", "content": "hello"}]}'

Chat Completions and Responses clients, SDKs and editors. Any client that lets you set a base URL and key works.Messages API clients and terminal agents. Any client that lets you set a base URL and key works.Any HTTP client. List model ids with GET /v1/models.

AiderClaude CodeClineCodexKiloOpenCodeRooAiderClaude CodeClineCodexKiloOpenCodeRoo

AI is the new WiFi.

Broadband went unlimited. Intelligence is next.

You pay for the pipe, never per megabyte. Same deal here: pay for the window, never per token.

Open the pipe. Let it run. The bill does not move.

Your pipe: two parallel sessions per key, 128K context. See the limits.

Join the waitlist at the portal. You sign in with email, GitHub or Google, and we tell you the moment passes open. Founding members get the launch price and a full refund if the launch target is missed.

Every agent loop costs tokens. Bills surprise you.

Request caps and throttling in the middle of a task.

Unlimited tokens at a fixed price. What is limited: 2 parallel sessions per key, and speed is not promised.

1 day or 3 days. Starts at payment. No subscription, no auto-renew.

One key per account, two parallel sessions.

In any client that lets you set both. No plugin, no lock-in.

Chat Completions, Responses, Anthropic Messages.

✓ Includes et:auto: we pick the model for each conversation

✓ Includes et:auto: we pick the model for each conversation

Bring your own Anthropic/OpenAI key with any pass; you pay the provider directly. How it works

Top-ups, only with an active pass: 3 hours (₹299), 6 hours (₹549)3 hours ($4.49), 6 hours ($7.99). The 3 hours top-up: starts on your first request. Use within 7 days, or it starts then. The 6 hours top-up: starts on your first request. Use within 7 days, or it starts then.

Prices exclude tax; the India total with GST is always shown. No subscription, no auto-renew.

Launch prices and founding-member terms apply until launch. Passes are bought in the portal.

endlesstokens is an API, not a plugin. Any coding agent, editor extension, harness, SDK or script that speaks Chat Completions, Responses or Anthropic Messages works. These are a few, in alphabetical order, each with its own setup guide.

Coding agent for your editor · setup guide ↗

Any tool or script that can set a base URL and key · setup guide ↗

Open weights, hosted and scaled by us. Served at 128K context, with vision, reasoning and tool calling. More popular open-source models follow as demand grows. Model details

Or let et:auto pick the model for each conversation. How auto models work →

Every open-weight model on endlesstokens runs on GPUs we host and scale ourselves. We do not proxy your requests to another inference provider, and we do not resell anyone else’s capacity.

We deploy each model, run it, and add capacity as demand grows. What you call is what we operate.

Every model is benchmarked and its unit measures are derived before it goes on offer. Then we keep launching the next one.

Our method is built with Token By Token, an independent inference lab, and we welcome more teams who want to benchmark and engineer with us.

We collaborate openly with Token By Token on how open models are served and measured. Want to benchmark or build with us? Get in touch.

Closed, proprietary models belong to the labs that build them. We will not proxy or resell them. Once we agree terms with a lab, we will offer its models through that lab, with its approval.

Sessions, context and capacity, in plain words.

Yes, for the length of your pass. We never count or cap tokens or requests. What is limited is concurrency (two parallel sessions per key) and the time window you bought.

That is the whole idea of endlesstokens: buy a time pass, and tokens are endless until it ends. No token meter, no top-ups.

There is no token or request cap. If every GPU is full, a new session can be briefly refused and the rejected time is credited.

Two concurrent sessions per key. A third evicts the least recently used idle one.

No token cap and no request cap. Two parallel sessions per key, a 128K context window, up to 5 images per request, and reasoning effort capped at medium. If every GPU is full, a new session can be briefly refused and the rejected time is credited.

India and the US at launch. Others can register and are told when their country opens.

Each account gets two parallel sessions. For a team, use one account per person, or write to support@endlesstokens.ai and tell us what you need.