Flat rate · No token metering

Code all day. No cooldowns. Ever.

One flat price for Opus 5, Claude, GPT-6, Codex, GLM, MiniMax, and DeepSeek. No per-token billing, no credits to top up, and no invoice waiting for you after a long agent run.

Start for €10 See what's included

POST /v1/responses

curl https://openlimits.app/v1/responses \
  -H "Authorization: Bearer $OPENLIMITS_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-6-sol",
    "input": "Review and fix this repository"
  }'

…

API value served last 24h

…

tokens last 24h

…

requests last 24h

…

avg response time

Recent activity

Past 24 hours · hourly

Requests

…

this hour

Loading hourly activity…

Tokens

…

this hour

Loading hourly activity…

API Value Served

…

this hour

Loading hourly activity…

The client stays simple.

OpenLimits handles authentication, routing, failover, and accounting behind compatible provider endpoints.

Request

Use the SDK you already have

Point an Anthropic or OpenAI client at OpenLimits and keep the same request shape.

Route

Match policy to capacity

The router checks plan access, model policy, account health, and current provider availability.

Stream

Return provider output

The response streams to the client while usage and routing metadata are recorded for the dashboard.

Use as much as you want.

Every plan includes every model, unmetered. The only thing you choose is how long you want to pay for.

Included with Day, Week, Max, and Ultimate

Every model below, on every plan, with no per-token charge for any of them.

Claude Opus 5.5Claude Sonnet 5Claude Haiku 4.5GPT-6.1 Sol / GPT-6 Sol / Astra / LunaOpus 5GLM 5.3 / 5.2 / 5 TurboMiniMax M3DeepSeek V4 Pro / Flash

What the ceiling actually is

Day, Week, and Max allow $2,000 per day of API-equivalent usage — about $60,000 a month at provider list prices, for €120. Ultimate removes the daily ceiling entirely.

Compare the plans

The math, in one line.

This is the whole pitch. Per-token pricing charges you more the more you work; a flat rate does not.

€120/moWhat Max costs, whether you send one request or a million.

$2,000/dayAPI-equivalent usage allowed before fair use applies.

~$60,000What that ceiling is worth per month at provider list prices.

$0Additional cost per token, per request, or per seat.

See exactly what you didn't pay for.

The dashboard keeps a running total of what your usage would have cost.

Every request is priced against provider list rates and added up, so you can watch the gap between what you used and what you paid widen over the month.

View all features

API savedRunning total of API-equivalent cost you avoided.

4 token typesInput, output, cache read, and cache write accounting.

Per modelUsage and avoided cost broken down by requested model.

LiveQueued, retrying, completed, and failed request states.

Set the endpoint once.

Claude Code and compatible clients can read the base URL and key directly from the environment.

Read the complete setup guide

Shell configuration

export ANTHROPIC_BASE_URL=https://openlimits.app
export ANTHROPIC_AUTH_TOKEN=$OPENLIMITS_KEY

# continue with the normal client
claude "finish the migration"

One price. However much you use.

Every plan is unmetered and includes every model. Pick the billing window that suits you and stop thinking about tokens.

Day Pass

shortest commitment

€1024 hours

Unmetered access to every model for 24 hours.

Start Day Pass

Included

Unmetered usage — no per-token billing, no credits
Fair use: $2,000/day of API-equivalent usage
Opus 5.5 and Opus 5; Claude Sonnet 5, Haiku 4.5
GPT-6.1 Sol, GPT-6 Sol, Astra, and Luna
GLM 5.3, GLM 5.2, GLM 5 Turbo; MiniMax M3; DeepSeek V4 Pro and Flash
Streaming, tools, images, and thinking
Dashboard analytics and live feed
Renews every 24 hours

Week Pass

€457 days

Unmetered access to every model for a full week.

Start Week Pass

Included

Unmetered usage — no per-token billing, no credits
Fair use: $2,000/day of API-equivalent usage
Opus 5.5 and Opus 5; Claude Sonnet 5, Haiku 4.5
GPT-6.1 Sol, GPT-6 Sol, Astra, and Luna
GLM 5.3, GLM 5.2, GLM 5 Turbo; MiniMax M3; DeepSeek V4 Pro and Flash
Streaming, tools, images, and thinking
Dashboard analytics and live feed
Renews every 7 days

Secure checkout via Stripe · The price above is the whole billCompare all plan details

Common questions

Is usage really unlimited?

There is no per-token bill and no credit balance to top up. Day, Week, and Max carry a fair-use ceiling of $2,000 per day in API-equivalent usage. Ultimate has no daily ceiling at all.

How much is that compared to the API?

At provider list prices the Max ceiling is roughly $60,000 of API usage a month, for €120. Most people never come close — the ceiling exists to stop resale, not to ration your work.

What changes in my setup?

Usually one base URL and one API key. Your client keeps its existing Anthropic or OpenAI request format.

Which models are included?

Every plan includes Opus 5.5 and Opus 5, Sonnet 5, Haiku 4.5; GPT-6.1 Sol, GPT-6 Sol, Astra, and Luna; GLM 5.3, 5.2, and 5 Turbo; MiniMax M3; and DeepSeek V4 Pro and Flash.

Spend €10. Use it all day.

A Day Pass is 24 hours of unmetered access to every model, active the moment checkout completes. Cancel renewal any time from the billing portal.

Start Day Pass View pricing