LotusAI

Features

Everything a keygets you.

14 models, up to 1M of context, and a usage window that refuses to run dry. Here is what sits behind a single LotusAI key.
Get accessSee the models

Usage

A window that keeps refilling.

No monthly token cliff. A generous five-hour allowance starts on your first request and resets on its own, so heavy agentic sessions, big refactors and all-day editor runs just keep going.

  • No monthly hard stop
  • Resets every five hours, automatically
  • Exact reset time on the public key status page
usage windowrefilling

window

5h

reset

auto

// code without watching a meter

api.anthropic.com

api.lotusai.pro

Claude CodeCursorClineContinueZedRoo CodeOpenCode

Compatibility

Truly drop-in.

LotusAI speaks the Anthropic Messages API: same request shape, same streaming events, same response. Change one base URL and your SDKs, scripts, agents and editor configs carry on like nothing happened.

Setup guide for every tool

Endpoints

Two shapes. One key.

Use whichever format your tool already speaks. Both endpoints share the same key and the same five-hour window.

Anthropic Messages

/v1/messages
curl https://api.lotusai.pro/v1/messages \
  -H "x-api-key: sk-lotus-..." \
  -H "anthropic-version: 2023-06-01" \
  -d '{"model":"claude-fable-5-1",
       "max_tokens":1024,
       "messages":[{"role":"user","content":"hi"}]}'

OpenAI chat completions

/v1/chat/completions
curl https://api.lotusai.pro/v1/chat/completions \
  -H "Authorization: Bearer sk-lotus-..." \
  -d '{"model":"claude-fable-5-1",
       "messages":[{"role":"user","content":"hi"}]}'

The full lineup

Pick a model per request.

Every model on this list is reachable with the same key. Set it with the model field, or pin one in your tool's config.

FrontierNew

Claude Fable 5.1

the new heavyweight

The most capable model on the list: demanding reasoning and long-horizon agentic work. Knows the world up to June 2026, the most recent cutoff of anything we serve.

Context

0M

1,000,000 tokens

Access

One

key for every model

And the rest

The whole kit, in one key.

The full lineup

Every model on the list is reachable with the same key. Switch per request or pin one.

Rolling five-hour window

Continuous resets instead of a monthly cliff you fall off.

Streaming

Server-sent events arrive exactly as your tools expect them to.

Tool use

Tool calls and long agentic loops run without special handling.

Public key status

Window, usage and reset time for any key, without logging in.

Scoped keys

Each key is issued and managed by the partner who gave it to you.

OpenAI-compatible too

Use the Anthropic shape or /v1/chat/completions. Same key.

Human support

Real people on Telegram and email when something needs a look.

Already have a key? Check its status

See itfor yourself.

Get a key from a partner and have your editor talking to the endpoint in a few minutes.

Get accessRead the docs
Get access Docs