Stop worrying about models. Just code.
jusCode picks the best model for every task: the one that balances cost and capability for what you're trying to do. You ship faster. You pay less. The plumbing is our problem.
$1 per user / month · first user free · pre-paid credits, no expiry
Every request graded. The cheapest capable model wins.
Every request is graded on difficulty, context size, and tool use. The cheapest model that can handle the task gets the task. The market improves. The mix improves. Your code does not change.
We do not show you which model ran. The secret isn't the model. It's the harness and the tuning around it. As higher plans roll out you get RL plugins that learn your codebase.
JavaScript · TypeScript · Python · SQL
Tightest tuning. Best routing. Highest cache hit rate.
Java · C++
Solid coverage. Tuning catching up.
Framework-aware routing is next. Tiers expand as the bench expands.
We're honest about the tradeoff: on raw capability we may lag the latest frontier launch by weeks. We make up for it on cost. As RL kicks in on higher plans, the gap narrows, and on your codebase specifically, we sometimes beat the frontier.
Our mission is to make intelligence affordable. The frontier keeps moving. What should not move is the cost of using it.
Most gateways operate at one. We operate at three.
Optimization happens at every level we can reach. Above the provider's API. Across providers. And eventually inside our own metal.
Above the API
Prompt caching. Retry logic. Cross-team reuse. The work the provider doesn't do for you.
Across endpoints
Capacity arbitrage between neo-clouds, regions, and time-of-day. When one provider spikes, we route around it.
Bare metal
Our own endpoint. Tuned vLLM. Model and harness co-tuned for coding workloads.
Pay for the task, not the brand.
Most of your requests don't need the most expensive model. They need the cheapest one that can actually do the job. Routing every task to its tier is where the savings come from, and your Usage tab shows the cost of every single call.
Flat per-token pricing is what you pay when nobody's watching the meter. We watch the meter.
One platform fee. Pre-paid credits for inference.
$1 per user per month is the platform fee. First user free. Credits are pre-paid in packs ($5, $10, larger). The gateway debits the actual inference cost per request. Credits roll over and don't expire. Hit zero, requests pause until you top up. No negative bill is possible.
Platform: $1 / user / month
Billed monthlyFirst user free. Each additional teammate is $1/mo, billed via Stripe and prorated when you add or remove members. Solo accounts stay free forever.
Credits: pre-paid, pay per request
Pre-paid · no expiryBuy a pack ($5, $10, larger) and the gateway debits actual inference cost per request. Credits roll over and don't expire. Hit zero, requests pause until you top up. No negative bill is possible.
Plans
Drop-in for your coding agent. OpenAI- and Anthropic-API compatible. Tuned for coding workloads.
- ▸Works with Claude Code, OpenCode, Cursor, Aider, Cline
- ▸Codex CLI: coming soon
- ▸OpenAI-compatible API · Anthropic-API compatible
- ▸Best-model-per-task routing, model identity not surfaced
- ▸Pay only for what runs
Less hand-holding. Multi-repo context. Background learning.
- ▸Everything in Just
- ▸Multi-repo aware: agent reasons across boundaries
- ▸RL loop on your repo: learns your patterns over time
- ▸Background agents for long-running plans
- ▸Custom routing policies
Autonomous execution with audit-grade compliance.
- ▸Everything in Pro
- ▸SOC 2 · EU AI Act
- ▸Self-improving codebase: patches, deps, refactors
- ▸Org-wide agent fleets with role boundaries
- ▸Custom SLAs and dedicated capacity
Bolt-ons for teams ready to coordinate.
Optional add-ons that layer on top of any plan. Priced per tenant. Both ship after the core plans stabilize.
Shared configs
One config, every workstation.
Routing rules, prompt templates, tool allowlists, and review policies pushed instantly to every developer. No drift between workstations.
AgenticPM
Issue tracker becomes the execution plan.
Agents pick up tickets, draft PRs, attach evidence, and report progress on the kanban your team already uses. Humans stay in the loop on merges.
Plain answers.
How does billing actually work?
Two things: a small seat fee ($1/user/month, first user free), and pre-paid credit packs ($5, $10, more) that cover inference. The seat fee pays for collaboration; credits cover the model compute. You can't go negative; if credits hit zero, requests pause until you top up.
What happens to unused credits?
They roll over forever. There's no monthly reset, no expiry. The wallet just accumulates until you spend it.
How are you cheaper?
We optimize execution across models. Old-world supply-chain techniques (inventory, hedging, bin-packing) applied to neo-world intelligence delivery. Most of your tasks do not need the biggest model; we make sure they do not get one.
Which models do you use?
The ones that win the cost-vs-capability tradeoff for your task, right now. The mix improves as the market improves. The model behind any call isn't surfaced. The routing decision is ours to optimize so you can focus on shipping.
What's the difference between the plans?
Just (today) is the drop-in: point your existing agent at api.juscode.co and you get best-model-per-task routing on a single repo. Pro adds multi-repo awareness and an RL loop that learns your patterns over time. Org layers SOC 2 / EU AI Act compliance and a self-improving codebase on top. You only pay for what's shipping.
What are you launching next?
CLI and a desktop app are on the roadmap. The first focus is a VS Code plugin. That is where most coding actually happens.
Can I see which model ran?
No. Model identity is part of how we deliver the cost we deliver, and we don't surface it. Your Usage tab shows per-call cost so you always know what you paid for; the routing decision behind it is ours.
What about my data?
Your code is yours. We do not train on it. Routing metadata is kept only as long as needed to make the next decision better.
Your agents never sleep. Neither do we.
Around the clock, every request your coding agents fire lands on the right tier. You see one endpoint; we run the switchboard.