Back to overview
usage-based credits

Usage-based pricing. Prepay credits, pay for what you use.

One prepaid balance covers coding agents, the model gateway, GPU model hosting, rented compute, and search — all metered to the token and the second. No subscription required; optional plans add bundled credits and guaranteed machines.

app credits buy --packs 25
What you get

Simple credits

Pay as you go
Search pricing
Model hosting
Spend caps

One balance, everything

Agents, models, GPU hosting, compute, and search all draw from the same prepaid credits. 1 credit = $0.001.

Metered, with caps

Pay per token and per second. Set spend caps per project, key, app, or agent run so there are no surprises.

Plans are optional

Pro, Ultra & Max bundle monthly credits at a better rate plus guaranteed machines — usage beyond them just continues at list price.

Start free, or save with a plan

Plans add monthly credits at a better rate, guaranteed machines, and priority in the queue. Same balance — go over your plan and you just keep paying the usage rates below. No subscription required. Cancel anytime.

Free

$0/mo

Start free. Pay only for what you use.

  • Prepaid credits, no minimum
  • Shared worker pool
  • Every API + the CLI
  • Web, paper & agentic search

Pro

$20/mo

For solo builders shipping every day.

25,000 credits / month
Save 20% vs pay-as-you-go
  • 25,000 credits / month
  • 1 guaranteed agent machine
  • RA1 + papers + agentic search quota
  • Priority over free tier

Ultra

Popular
$60/mo

For teams running agents in parallel.

80,000 credits / month
Save 25% vs pay-as-you-go
  • 80,000 credits / month
  • 3 guaranteed machines + priority queue
  • Higher first-party product quotas
  • Best value per credit

Max

$200/mo

For heavy, always-on workloads.

280,000 credits / month
Save 29% vs pay-as-you-go
  • 280,000 credits / month
  • 6 guaranteed machines + top priority
  • Largest RA1 / papers / search quotas
  • First-party credits across products

Or pay as you go — one prepaid balance

Everything on app.nz — coding agents, the model gateway, GPU model hosting, rented CPU/GPU compute, and web & paper search — is usage-based and billed from one prepaid credit balance. Top up once and use anything. No subscription required.

Prepay credits

Top up once. 1 credit = $0.001. No subscription required, no minimums, no monthly commitment.

Use anything

Agents, the model gateway, GPU model hosting, rented compute, and search all draw from the same balance.

Pay for what you use

Metered to the token and to the second. Set spend caps per project, key, app, or agent run.

Models

Per 1M tokens, through one OpenAI-compatible gateway. Auto routes pick the right model for the job.

ModelProviderInput / 1MOutput / 1M
openpaths/auto-fastDeepSeek$0.168$0.336
openpaths/auto-cheapOpenAI$0.240$1.50
openpaths/autoGoogle Gemini$1.80$10.80
openpaths/auto-codeOpenAI$6.00$36.00
openpaths/auto-reasoningOpenAI$0.900$5.40
claude-opus-4-8Anthropic$6.00$30.00
claude-sonnet-4-6Anthropic$3.60$18.00
claude-haiku-4-5-20251001Anthropic$1.20$6.00
gpt-5.4OpenAI$3.00$18.00
gpt-5-miniOpenAI$0.300$2.40
gemini-2.5-proGoogle Gemini$1.50$12.00
gemini-3.5-flashGoogle Gemini$1.80$10.80
deepseek-chatDeepSeek$0.336$0.504
grok-4.3xAI$1.50$3.00
llama-3.3-70b-versatileGroq$0.708$0.948

A representative slice — see every model and provider.

Hosting & compute

Per hour, billed per second of wall-clock. GPU model endpoints scale to zero, so idle costs nothing.

TypevCPU / RAMPrice / hr
CPU · Small2 vCPU · 4 GB$0.053
CPU · Medium4 vCPU · 8 GB$0.096
CPU · Large8 vCPU · 16 GB$0.185
T4 16GB4 vCPU · 16 GB$0.228
RTX 3090 24GB8 vCPU · 24 GB$0.264
RTX 4090 24GB8 vCPU · 24 GB$0.408
A40 48GB9 vCPU · 48 GB$0.480
L40S 48GB8 vCPU · 48 GB$1.032
A100 80GB12 vCPU · 80 GB$1.968
H100 80GB16 vCPU · 80 GB$3.588

Search

Flat usage pricing for live web and academic search, drawn from the same balance.

Web search

$7.70 / 1,000 requests

Live web results with citations

Paper search

$1.00 / 1,000 requests

Academic + preprint search