Code with a model that
keeps up with you.

Kali Gamma, Beta and Epsilon are tuned for depth, balance and speed. Chat here, or reach them from any OpenAI-compatible client.

Start chattingRead the API docs

Kali Gamma

Deep

Our most capable model. Plans multi-step work, reasons through tricky bugs, and holds large codebases in view.

Kali Beta

Balanced

Extended context and steady judgment for everyday coding, writing and review.

Kali Epsilon

Fast

Quick answers and tight iteration loops when latency matters more than depth.

Estro is available on your favorite platforms:

opencodecontinuevs codecursorcursor-byokwindsurfclinerookiloclaudecodexhermesopenclawaiderzedjetbrainsneovimlibrechatopen webuichatboxsdksother

Plans

Every paid plan unlocks all three models and the API. Higher tiers give more usage in every window. Without a plan you get Kali Epsilon with ₪50,000 a day.

PlanMonthlyAnnual, per month5-hour windowWeekly window
Starter
To try it properly		$8$6.67
Billed annually, $80 a year		₪560,000₪920,000
PlusRecommended
For regular use		$24$20
Billed annually, $240 a year		₪1,360,000₪2,200,000
Pro
For daily work		$44$36.67
Billed annually, $440 a year		₪2,160,000₪3,680,000
Max
For heavy use		$109$90.83
Billed annually, $1,090 a year		₪4,320,000₪9,200,000
Ultra
For the heaviest use		$219$182.50
Billed annually, $2,190 a year		₪8,000,000₪18,400,000
Compare plans on the pricing page
01

Threads that remember

Every conversation is saved to your account. Switch models mid-thread; the history comes along.

02

Streams, with its reasoning

Replies stream token by token. When a model thinks before it answers, you can read the thought process.

03

One key, any client

The same models sit behind an OpenAI-compatible endpoint. Point your SDK or editor at it with your session token.

04

Your account, your devices

Email verification, session management per device, and a password reset flow that does not need support.

Already have a client?

Sign in, grab the token from the login response, and send it as a bearer. Streaming, reasoning deltas and the usual chat-completions shape all work.

Full reference
curl
Run
curl https://estro.help/v1/chat/completions \
  -H "Authorization: Bearer $ESTRO_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kali-gamma",
    "stream": true,
    "messages": [{ "role": "user", "content": "Refactor this function and explain the tradeoffs." }]
  }'

Pick a model and go.

Create an account