Umans Code for Organizations
One wallet. One shared budget for the team. Service-account keys for automations.
This page extends the User Guide. CLI install, tool setup, models, and the API work the same way for organizations. What follows is only what changes when you bring a team.
At a glance
- Members for humans. Everyone codes against the same shared wallet budget, with the same CLI flow as individual accounts.
- Service-account keys for automations. Pay per token, from the same organization wallet.
- One budget. Member usage and service-account usage settle on the same organization wallet, with per-key audit in the ledger.
Members (for humans)
Admins invite teammates from Billing → Members. For new organizations there are no per-person subscriptions: every member codes against the shared organization wallet, billed per token, and the budget is the only spend limit. Each member gets:
- Their own API key, drawing from the shared wallet, with per-key usage in Billing → Wallet (ledger view).
- The same models as individual accounts (
umans-coder,umans-kimi-k3,umans-glm-5.3,umans-deepseek-v4-flash-0731,umans-flash). - Teammates follow the standard Quick Start. Run
umans claudeand they're in.
Legacy seat subscriptions: before August 2026, organizations bought flat-rate seats ($50 / seat / month) with pooled sessions. Seat plans were sunset alongside the personal plans, and budget sharing is the model for new organizations. A few long-standing orgs still run seat subscriptions while they convert — member keys there stay subscription-funded, and only service accounts draw from the wallet, until the conversion lands. If that's you, nothing changes until we talk.
Service accounts (for automations)
Service-account keys run without a human behind them. They draw from the organization wallet at per-token rates. You only pay for what the automation actually consumes.
Note: Pay-per-token is how everyone runs on Umans — personal accounts included. What an organization adds on top: one shared wallet budget, member management, and service-account keys under org ownership.
What teams use them for
- Production alert triage & mitigation. A service-account bot watches alerts (PagerDuty, Sentry, Grafana), pulls context from the repo, and drafts a qualified mitigation plan before a human is woken up. Dollars of tokens per incident, straight from the shared budget.
- Code review on every PR. Run a review pass automatically with the same models your engineers use in their IDE. Typically a fraction of the cost of hosted alternatives, and consistent with how the team already codes.
- Scheduled maintenance. Migration passes, dependency bumps, flaky-test investigations. Anything you'd normally hand to an agent on a cron.
Good fits share a shape: non-interactive, bounded token budget, value per run is measurable.
Token pricing
The public per-model rates — the same ones on /pricing — apply to member and service-account usage alike. Prices in USD per 1 million tokens. Each request debits exactly what the model consumed (input, output, cache reads, cache writes), with no per-call minimums.
| Model | Origin model | Input / 1M | Output / 1M | Cache read / 1M | Notes |
|---|---|---|---|---|---|
| umans-kimi-k3 | kimi-k3 | $3.0000 | $15.0000 | $0.3000 | Moonshot’s largest open model: 1M context, native vision, max reasoning by default. The premium tier for repository-scale agentic runs. |
| umans-glm-5.3 | glm-5.3 | $1.4000 | $4.4000 | $0.2600 | Z.ai's flagship coding model: the GLM 5.2 successor on a 1M context. Always thinks (dial low to max). |
| umans-deepseek-v4-pro-0813 | deepseek-v4-pro | $1.3200 | $3.9600 | $0.0440 | The long-context coding flagship: 1M context, high-effort reasoning by default. |
| umans-deepseek-v4-flash-0731 | deepseek-v4-flash | $0.1400 | $0.2800 | $0.0280 | The cheapest production route: DeepSeek V4 Flash with a 1M context, thinking at low effort by default. The workhorse for high-volume agentic automation. |
| umans-flash | qwen3.6-35b-a3b | $0.1500 | $1.0000 | $0.0500 | The light, fast complement: quick, high-volume steps around the main coder. |
Kimi K2.7-Code (umans-kimi-k2.7) and GLM 5.2 (umans-glm-5.2) are discontinued as of September 10, 2026; requests to the retired ids return a clear deprecation error pointing to umans-kimi-k3 and umans-glm-5.3. umans-coder, the recommended default, routes to our current pick — the live target is always on GET /v1/models/info.
- Member and service-account usage both draw from the same wallet budget.
- Top up the wallet manually or enable auto-refill from Billing → Wallet.
- Per-key usage breakdowns live in Billing → Wallet (ledger view).
Getting started
- Talk to us. Organizations are provisioned by our team. Email contact@umans.ai with your team size and the email of your first admin.
- Your first admin accepts the invitation. We create the org and send an invite link to the admin you named. They sign in to activate it.
- Admin funds the wallet (Billing → Wallet) and sets the budget cadence with us.
- Invite teammates. They sign in and run
umans claudenormally — their usage draws from the shared budget. No extra setup. - Create a service account for any automation (Billing → Wallet → Create service account). Store the key like any other secret and point your bot at
https://api.code.umans.ai.