Pricing

You only pay when
we save you money.

Start with pay-as-you-go — 33% of what we save you, deducted from your balance. Or pick a subscription with a savings cap. Every dollar of savings is calculated against what your provider would have charged for the same work.

Pay-as-you-go
No commitment. Pay only when we save you money.
33%of token cost savings
Auto-recharge balance · no monthly fee
Start free
  • ActiveContext on all your sessions
  • Per-agent aggressiveness tuning
  • Custom curator rules
  • Cache-aware curation
  • Session analytics dashboard
  • Works with all major providers
  • Billing
  • 33% of savings, deducted from balance
  • Auto-recharge (Stripe)
  • Community support
Starter
For individual developers running long agent sessions.
$20/ mo
Up to $100 saved / mo
Choose Starter
  • Everything in Pay-as-you-go
  • Predictable monthly bill
  • Past the cap: pass-through or top-up at 33%
  • Priority queue for curator inference
  • Email support
  • Limits
  • 1 developer seat
  • Up to $100 savings / month
  • 48-hour support SLA
Most popular
Pro
For heavy users and small projects burning real token spend.
$50/ mo
Up to $400 saved / mo
Choose Pro
  • Everything in Starter
  • Advanced curator rule library
  • BYO provider keys (Anthropic, AWS, GCP)
  • Past the cap: pass-through or top-up at 33%
  • Priority email support
  • Limits
  • 1 developer seat
  • Up to $400 savings / month
  • 24-hour support SLA
Team
Everything in Pro plus shared rules, team insights and admin.
$100/ seat / mo
Up to $1,000 saved / seat
Choose Team
  • Everything in Pro, per seat
  • Team-wide rule sets
  • Manager dashboards · cost per developer
  • Audit logs and RBAC
  • SSO (GitHub, Google)
  • Dedicated Slack channel
  • Limits
  • Min. 3 seats
  • Up to $1,000 savings / seat / month
  • 4-hour support SLA
E

Enterprise

Higher caps, SOC 2, dedicated capacity, on-premise deployments and custom rule engineering.

SOC 2 Type IISelf-hostedCustom capsDedicated supportMSA + DPA
Contact sales →
Start free with pay-as-you-goCancel any timeOver your cap? Pass-through or top up at 33% — your callTeam rules keep applying — always
How billing works

We charge you a fraction of what we save.

Every turn passes through ActiveContext. We log what your provider would have charged for the un-curated history (baseline), then what they actually charged for the curated one (actual). The difference is your savings.

Pay-as-you-go: we deduct 33% of your savings from a pre-funded balance — with auto-recharge, like any token provider. No monthly fee, no cap.

Subscriptions include a monthly savings cap. Once you hit it, you choose: either we pass your full message history straight through to your provider unrestructured on your BYOK keys (no further savings), or you top up at the pay-as-you-go rate of 33%. Either way, team rules keep applying.

Sept billing · coding-agentlive
Stock baseline
$1,284
Actual charged
$488
You saved
$796
Pro plan · $400 / mo cap
Past the cap: pass-through, or top up at 33%.
$400
capped at plan
Compare plans

Everything, line by line.

No fine print. Pick the plan that matches your workload — change later in one click.

FeaturesPay-as-you-go33% of savingsStarter$20 / moPro$50 / moTeam$100 / seat / mo
Core
ActiveContext on all sessions
Per-agent aggressiveness tuning
Cache-aware curation
Custom curator rules
Advanced rule library
Billing
Monthly subscription feeNone$20$50$100 / seat
Savings capNo cap$100 / mo$400 / mo$1,000 / seat / mo
Pay-as-you-go rate33%Past cap, optionalPast cap, optionalPast cap, optional
Auto-recharge balance
Limits
Seats111Unlimited (3+ min)
Sessions per monthUnlimitedUnlimitedUnlimitedUnlimited
BYO provider keys
Team & admin
Team-wide rule sets
Manager analytics dashboard
Cost per developer reporting
Audit logs · RBAC
SSO (GitHub, Google)
Support
Documentation · community
Email support48-hour SLA24-hour SLA4-hour SLA
Dedicated Slack channel
Onboarding session
FAQ

The honest questions.

Don't see what you're looking for?

Contact support →
How exactly do you calculate savings?

For every turn, we record two prompt sizes: the un-curated history your agent would have sent, and the curated one we actually sent. Multiply by your provider's rate card, subtract our curator-inference cost, and the difference is your savings.

The math is published per session in your dashboard. You can export it. You can audit it. We'd rather show you the math than spin a marketing number.

What happens if I exceed my subscription plan's savings cap?

You choose. Option one: we stop restructuring and pass your full message history straight through to your provider on your BYOK keys — unrestructured, no further savings, no extra charge from us. Option two: top up at the pay-as-you-go rate (33% of additional savings, deducted from your balance) and keep curating.

Either way, your agents keep running and team rules keep applying so behavior stays consistent across developers. We never block, rate-limit, or get in the way of your BYOK usage.

How does pay-as-you-go work?

No monthly fee. You pre-fund a balance (like a token provider), and we deduct 33% of every dollar of savings we deliver. Auto-recharge keeps the balance topped up so your agents never pause.

You only ever pay when we save you money. If we save nothing, you pay nothing.

Do I have to bring my own provider keys?

No — not always. For leading open-source models like DeepSeek V4, Kimi K2.6, and GLM 5.1, we bill you directly for LLM usage. No BYOK setup, no separate provider account. Pre-fund your balance and go.

For closed-source models — Anthropic Claude, OpenAI GPT, Google Gemini, and anything else routed through a paid provider — BYOK is required. ActiveContext sits between your agent and the provider on your keys, your contracts, your invoices.

You can mix both in the same workload: direct-billed for open models, BYOK for closed.

Will my agents slow down?

No. Curator inference runs asynchronously between agent turns on small, fast models. Net effect on time-to-first-token is under 50ms in our benchmarks — well under typical network jitter to a frontier provider.

Which providers and models are supported?

Anthropic (Claude Sonnet, Opus, Haiku), Alibaba Cloud Qwen, OpenAI GPT-5, Google Gemini 2.5 Pro & Flash, Mistral, DeepSeek, xAI Grok, plus AWS Bedrock, GCP Vertex, Together, Fireworks, and any OpenAI-compatible self-hosted endpoint.

Anthropic and Alibaba have native prompt caching, which lets ActiveContext deliver its highest savings. Others work — savings are just a bit lower.

Can I cancel any time?

Yes. Monthly plans cancel immediately. Annual plans cancel at the end of the term. No clawback on savings already realized.

Is my session data used to train models?

No. AJNT does not use your prompts, tool calls, or outputs to train any model. We hold session data only long enough to curate it, then it's discarded per your retention policy (default 30 days, configurable to 0).

One env var. Savings by the next turn.

Start free. See the math on your own workload before you ever pay us.