Private AI Inference Pricing

Pricing

Pro

For everyday coding-agent work.

$20

per month

Usage

or $16 / month billed yearly

expected monthly usage

~1B tokens

GLM-5.2, DeepSeek V4 Flash 0731, and Kimi K3
OpenAI-compatible API
Zro CLI launcher
Agent tools
Usage packs available with or without a subscription
Zero request retention
No training on requests

Start with Pro

Max

For heavier and longer-running agent work.

Best value

$60

per month

Usage

or $48 / month billed yearly

expected monthly usage

~5B tokens

Everything in Pro
Usage packs available with or without a subscription

Start with Max

Usage & billing details

Expected token totals use typical cached agent usage, not fixed allowances. Actual totals vary by model mix, prompt shape, output length, and cache reads.
Web searches are separate tool calls and are not included in token estimates.
Yearly plans are billed annually and provide the same monthly spend budget as monthly plans.
Monthly spend resets on the same calendar cadence for monthly and yearly subscribers.
Cancellation takes effect at the end of the current billing period; there are no prorated refunds, and access remains active until then.

Tool pricing

Agent tools

Web Search

Fixed-cost, zero-token tool calls charged to your plan or usage-pack balance.

$0.02

per web search

GitIngest

Built on gitingest

Repository context, ready for an agent prompt.

Coming soon

Zro tool

AnyDoc

Document-to-Markdown context for agent workflows.

Coming soon

Zro tool

Usage packsNo subscription required

Add usage when you need it

Usage packs expire after 90 days and have no recurring charge.

One-time credit
$5
Usage balance
One-time credit
$10
Usage balance
One-time credit
$20
Usage balance
One-time credit
$50
Usage balance
One-time credit
$100
Usage balance

Start private coding‑agent inference.