Under development, ready in a few more days
Sign inGet oaica

Terminal launcher for coding agents

Save on your AI bill*. Free to run your own models†.

Send the work that does not need a premium model to models you run yourself or to cheaper tiers, and keep hosted models, with failover, for the rest.

Buy annual, $29 first yearMonthly, $7

Try free for 14 days, no card

14-day trial · 30-day refund · never bricked: falls back to free

$29 is for the first 100 customers, then $39/year.

* Savings equal the share of your tokens you route to models you run or to cheaper tiers, times your rate. They depend on your workload, model quality and hardware, so no percentage is promised; see the calculator for your own figure. † No per-token fee on models you run yourself; hardware, power and your time are your cost. Oaica does not host models or provide inference.

Monthly costYour usage grows → Metered bill: grows with use oaica licence: flat
Shape only, no figures. Your own hardware or endpoint costs are separate and not drawn.

What it is for

Four jobs, one launcher.

Run your agent on your model

Claude Code, codex and opencode, on a model you own. Run what you own instead of renting it.

Cut or cap the token bill

Route the work you can off the meter. Only what stays hosted is billed per token.

Keep proprietary code home

Prompts go only where you point them. No telemetry, so your code stays on your machine.

Mix local and hosted

Use both together, with failover that moves a live reply when a leg goes down.

See pricing ↓

The two parts

Oaica Code launches it. Oaica Engine runs it.

Two pieces, one installer. You do not have to pick between them.

Oaica Code

The terminal launcher, a fork of Ollama's client. One config puts your agent on the model you choose, splits the primary and subagent tiers across different backends, and fails over when a leg goes down. Free to install, no account.

Oaica Engine

Our own inference engine, written in Rust and CUDA and developed here, not inherited. It serves the .oqm models and offloads experts to system RAM when the GPU is small, so a 35B model runs on an 8 GB card from a desktop install.

Specifications of the shipped CLI — not usage statistics, not benchmarks

  • 15+Agent CLIs, and more added
  • 44Provider presets
  • 6Route policies
  • 4Model tiers
  • 0Telemetry requests
  • 20hUpdate check, at most once per 20 hours

The idea

One meter, or two paths.

Every token you send to a hosted model is billed. oaica sits on loopback and lets you decide which requests go to a model you run.

Run your own numbers ↓

claudecodexopencode + 12 more agent CLIs oaica127.0.0.1you set the split Model you runyour hardware Hosted modelyour metered bill
Requests you route to a model you run leave the metered bill. The split is yours to set; the drawing is illustrative.

How it saves

Four ways it keeps cost and control with you.

Try the calculator ↓

Cut the bill

Route the work you can to a model you own. Only what stays hosted stays on the meter.

  • Four model tiers in one launch
  • Six route policies

Token savings

  • Probes the real context window, so prompts are not truncated and retried
  • Titles, topic detection and tool-output digestion go to the background tier
  • Failover keeps the stream, so a lost turn is not re-sent
  • The oversize tier takes over only when the window fills

Keep your code

Prompts go only to the endpoint you point it at. No telemetry, and your provider key never leaves the machine.

Never locked in

15 agent CLIs and 44 provider presets behind one config. If you stop paying, it falls back to free and never bricks.

Savings calculator

Do the arithmetic on your own numbers.

Enter what you use and what you pay. Nothing here is a benchmark or a promise.

Your rate: enter yours.
The paid background tier (--haiku-model) and per-tool routing (oaica config set tool-model Bash tertiary) send these turns to a cheaper leg.

Tokens off the metered bill, per month

16M
24M hosted16M routed to you
Dollars moved off your bill
$96.00
Licence per month, annual plan
$3.25
Net after licence
$92.75
Net on the $7 monthly plan
$89.00
Background and tool-heavy tokens
10M

If 40% of your tokens run on a model you host, your hosted bill is 40% lower. Enter yours.

Illustrative: arithmetic on the numbers you enter (moved = spend x share), not a benchmark or a promise. Savings depend on how much work you route to models you run, their quality for your tasks, and your hardware and power costs. Oaica does not host models or provide inference.

Buy annual, $29 first yearMonthly, $7

14-day trial · 30-day refund · never bricked: falls back to free

Pricing

One flat licence. The model is yours.

Free

$0

Never expires. Install with no account.

  • Local models and oaica serve
  • Your own endpoints and API keys
  • Subagent tier and a saved plan
Install free

AnnualFirst 100

$29 first year

$39 list price; $29 for the first 100 customers. Renews at $39/year; cancel the renewal any time and access runs to the paid-through date.

  • The full paid set
  • Three devices per licence
  • 14-day trial first, no card
  • 30-day refund on the first payment
Buy annual, $29 first year

Monthly

$7 per month

The same product as annual. Switch to annual at renewal.

  • The full paid set
  • Month to month
  • 14-day trial first, no card
  • 30-day refund on the first payment
Buy monthly, $7

Bundle

Oaica Code + Oaica Engine, one installer

The licence covers both. The installer wires the engine in as a leg, so your subagent tier can run on a model you own — and nothing on that leg is billed per token.

  • Oaica Code — the launcher, every paid tier
  • Oaica Engine — included, no extra charge
  • .oqm model packs — optional, priced per pack, yours to keep

$29 first year
Engine included. Packs sold separately or run your own.

Get the bundle
14 days

The whole paid set, free. No card taken.

30 days

Refund on the first payment.

Never bricks

If payment lapses, it falls back to the free tier.

3 devices

Per licence.

Teams, per seat per year: 1 $39 · 5+ $32 · 20+ $27 · 50+ $22 · 100+ $17 · 250+ $12. Questions: oaica@sprapp.com

Free and paid, line by line
CapabilityFreePaid
Local models and oaica serveIncludedIncluded
Your own endpoints and API keysIncludedIncluded
Subagent tier, --sonnet-modelIncludedIncluded
A saved --planIncludedIncluded
Route policies that pin routingIncludedIncluded
Your own Claude loginIncludedIncluded
Background tier, --haiku-modelNot includedIncluded
Context escalation, --oversizeNot includedIncluded
Weighted routing, --shardNot includedIncluded
Guided wizard, --wizardNot includedIncluded
Policies that pick a leg automaticallyNot includedIncluded
Vendored paid APIsNot includedIncluded
Free and paid, line by line. Filled dot: included.

How it works

Three commands to a running agent.

One config covers all 15 agents.

Buy annual, $29 first year

Install

The installer checks the archive against SHA256SUMS before extracting.

macOS / Linux
$curl -fsSL https://oaica.com/install.sh | bash
Windows
>irm https://oaica.com/install.ps1 | iex

Point at a model

Pull a small model and serve it, or register an endpoint you already have.

Local
$oaica pull qwen2.5-0.5b && oaica serve qwen2.5-0.5b
Remote
$oaica remote add mine --base-url https://your-endpoint/v1 --api-key-env MY_API_KEY

Launch

The wizard offers to save a plan. oaica doctor checks every leg any time.

Launch
$oaica launch claude --plan work
Install, point at a model, launch.

Under the hood

Checkable, not just claimed.

See pricing

Your machineagent + OAICA Endpointyou chose prompts, code Update checkat most once per 20 h Licence checkat most once per 7 days Telemetrynone
One solid path to the endpoint you chose. Two faint paths: a plain GET of the release VERSION.txt (no body, no identifiers; off with OAICA_NO_UPDATE_CHECK=1), and, on activated installs only, a licence revalidation sending the stored key and activation id. No telemetry, crash reports or analytics exist to switch off.
  1. Tier 1

    Primary

    --model
    The main model for the session.

    Free
  2. Tier 2

    Subagent

    --sonnet-model
    Execution.

    Free
  3. Tier 3

    Background

    --haiku-model
    Titles and topic detection.

    Paid
  4. Tier 4

    Oversize

    --oversize
    Takes over when the context window fills.

    Paid

Six route policies

  • local-first (default)
  • remote-first
  • auto
  • local-only
  • remote-only
  • weighted
Four model tiers in one launch, from any mix of providers, saved as a named plan. Policies that pin routing are free; automatic and weighted policies (weighted needs --shard) are part of the paid set.
  • claude
  • chatgpt
  • hermes
  • openclaw
  • opencode
  • hermes-desktop
  • codex
  • copilot
  • omp
  • cline
  • droid
  • dsh
  • pi
  • pool
  • qwen
Local Ollama server
llama.cpp via oaica serve
Any OpenAI-compatible endpoint
A machine you control
The fifteen agent CLIs in the one binary (solid), and where the model can live (dashed).

Questions people ask first

Does it see my code or prompts?

No. They go only to the endpoint you selected. There is no telemetry, crash reporting or analytics. Two small network calls exist, an update check and, on activated installs, a licence check; both are shown in the data-flow figure above.

What if I stop paying?

It drops to the free tier and never bricks. Local models, your own endpoints and a saved plan keep working.

Is $29 a subscription?

Yes. $29 for the first year for the first 100 customers, then $39/year, which is also the list price. Cancel the renewal any time; access runs to the paid-through date. A $7 monthly plan covers the same product.

Which agents work?

Fifteen agent CLIs ship in one binary, including claude, codex and opencode. Forty-four provider presets are compiled in, and any OpenAI-compatible endpoint can be added.

Does it work offline?

Yes. The licence verifies offline against an Ed25519-signed claim with the key pinned in the binary, and local models run offline. A remote leg needs a route to its endpoint.

How do refunds work?

Ask within 30 days of your first payment. The 14-day trial needs no card. Full wording: terms and refunds.

Put your coding agent on a flat licence.

$29 for your first year, then $39. First 100 customers. 14-day trial, no card. Ask within 30 days of paying and you get your money back.

Buy annual, $29 first yearMonthly, $7

14-day trial · 30-day refund · never bricked: falls back to free. Try free, no card