Zero charges by credits, not seats. A credit is a unit of work — one credit represents a fixed quantity of compute, regardless of who ran the task or which model handled it. Idle workspaces cost nothing.
Plans
Free — $0. 3,000 credits to start. Enough to build your first agent, connect your tools, and watch a run end to end. One run at a time, three models to choose from, every connector available.
Pro — $20/month. 20,000 credits per month. Credits cover the current billing cycle and expire at the end of it — they don't roll over. Adds every model, BYOK, credit top-ups, and a second concurrent run. For individuals who use Zero daily.
Team — $200/month. 120,000 credits per month. Same expiry rule. Ten concurrent runs, webhook triggers, extra concurrency on demand, and priority support. For teams that share agents and workflows.
Enterprise — custom. Custom credit volume and concurrency, dedicated support with an SLA, volume and annual billing. Contact sales.
Limits by plan
| Free | Pro | Team | Enterprise | |
|---|---|---|---|---|
| Credits | 3,000 to start | 20,000 / month | 120,000 / month | Custom |
| Concurrent runs | 1 | 2 | 10 | Custom |
| Extra concurrency | — | — | ✓ | ✓ |
| Org-shared agents | 7 | 7 | 7 | 7 |
| Private agents | Unlimited | Unlimited | Unlimited | Unlimited |
| Models | 3 models | All models | All models | All models |
| Bring your own key | — | ✓ | ✓ | ✓ |
| Credit top-up & auto-recharge | — | ✓ | ✓ | ✓ |
| Webhook triggers | — | — | ✓ | ✓ |
| Video generation | — | ✓ | ✓ | ✓ |
| Voice input & output | 10 total | 300 / day | 500 / day | Custom |
| Team members | Unlimited | Unlimited | Unlimited | Unlimited |
Scheduled runs, email triggers, and calendar triggers are on every plan, including Free. So are all connectors, custom connectors, managed web services, image generation, presentation and website generation, hosted sites, and the full security model.
Top-up credits are available on paid plans at $1 per 1,000 credits. Top-ups don't expire.
Auto-recharge
Paid workspaces can turn on auto-recharge: pick a balance threshold and a top-up amount, and the workspace refills itself when the balance dips below the threshold. A common setting is “recharge $20 when balance drops below $5” — then forget about it.
Auto-recharge runs through Stripe on the card you used to subscribe. Turn it off any time on the Billing page.
Do credits expire?
- Monthly plan credits (Pro, Team, Enterprise) — expire at the end of the billing cycle in which they were granted. Each grant is usable only for that cycle.
- Free starter credits — the 3,000 credits a new workspace begins with are a one-time grant, not a monthly refill.
- Top-up and auto-recharge credits (any paid plan) — never expire.
The soonest-expiring credits are always consumed first. The Billing page shows your balance broken down by source, so you can see which bucket is closest to rolling off.
Cost control
The biggest knob is which model runs the work. Reasoning-heavy models cost several times what a fast model costs for the same task. Run zero model ls (or open the model picker in chat) to see what your workspace can currently choose from — Free workspaces get three models, paid plans get all of them. Set the default model per agent or per workflow, so light triage runs on a fast model and heavy research runs on a strong one.
Other knobs admins use:
- Org model policy. Admins set the default model and provider for everyone in the workspace, and can restrict which models members may pick.
- Workspace cap. A monthly credit ceiling — Zero stops new chats when hit; admins can lift it mid-month.
- Usage page. Burn rate, projected runway, top chats and top spenders for the last 7 days, broken down by member, agent, and workflow.
Bring your own key (BYOK)
Route inference through your own provider account instead of paying VM0 credits for tokens. Available on Pro, Team, and Enterprise — not on Free — and set up on the Model providers page:
- Connect Claude Code. One click — Zero opens Anthropic's approval page, you sign in, and your existing Claude Pro or Max subscription is linked. No tokens to copy.
- Connect ChatGPT (Codex). One click — Zero opens OpenAI's approval page, you sign in, and your ChatGPT Plus, Pro, Business, Edu, or Enterprise subscription is linked. No tokens to copy.
- Anthropic / OpenAI / Google API keys. Paste a provider API key if you'd rather route through a direct API account than a subscription.
- OpenRouter / Vercel AI Gateway / Bedrock / Vertex. For teams that already route inference through their own gateway.
When a chat uses BYOK inference, the token cost is billed to your provider account. Tool calls, connector usage, storage, and media generation still consume VM0 credits. The chat log shows the split per turn.
BYOK is workspace-level and can be assigned per model. Individual chats can override.
What's next
- See Permissions for who in your org can spend credits.
- See For teams for org-level billing setup.
- See Generation for what image, video, voice, deck, and website generation cost against credits.
- See Connector catalog for the AI generation providers Zero ships with.