Question 1

Is Everstack free to use?

Accepted Answer

Yes. The Starter plan has no platform subscription fee and includes sandbox and browser hours every month. Every new account also receives $5 of usage credit with no card required, which pays for usage beyond the included hours and expires 30 days after signup. Add credit only when you want to keep running past your plan's included hours.

Question 2

Are sandboxes included with the Starter plan?

Accepted Answer

Yes. Starter includes 40 vCPU-hours and 40 GiB-hours of sandbox time every month, about 80 hours of the smallest sandbox, with no payment method needed. Every new account also starts with $5 of usage credit, valid for 30 days after signup, for usage beyond the included hours. When the included hours are used up and there is no credit, running compute stops until you add credit. Sleeping, archived, terminated, and failed-to-provision sandboxes use no hours.

Question 3

How are hosted browser sessions billed?

Accepted Answer

A browser session is billed separately from its agent sandbox because Everstack allocates an additional tenant-isolated Chromium runtime. Every plan includes browser hours each month. Beyond them, active sessions cost $0.05 per browser hour with a one-minute minimum and per-second billing after that. Warm-pool idle time is not charged.

Question 4

What happens when I hit my usage limits?

Accepted Answer

Included sandbox and browser hours reset every month and do not roll over. Past them, usage is paid from prepaid credit; the $5 starter credit is a one-time credit per account that expires 30 days after signup. When the included hours are used up and there is no credit, sandboxes and browser sessions stop and resume after you add credit. Other Starter limits reset on their published cycle; paid usage continues up to the spend controls you configure.

Question 5

Do you charge per channel connection?

Accepted Answer

No. Every plan reaches Slack, Discord, and Telegram, and every paid plan connects an unlimited number of channels. Starter includes three so you can run a real workspace before paying anything. Channel usage is metered by messages per month, not by how many workspaces, servers, or groups you connect, so wiring an agent into another channel never changes your bill. Self-hosted Community Edition instances have no channel limit at all.

Question 6

How does per-seat pricing work?

Accepted Answer

Each paid plan includes a set number of seats. Build includes 3 seats and Scale includes 10. Additional seats can be added at the per-seat rate shown on each plan.

Question 7

Do I need to change my existing API calls?

Accepted Answer

Everstack provides an OpenAI-compatible API, so most applications can switch by simply changing the base URL. No code changes to your prompt logic are required.

Question 8

Does evs.run execute my backend or build my site?

Accepted Answer

No. evs.run is a static serving plane, not an application runtime. Build in your local environment, CI system, coding harness, or Everstack sandbox, then publish the generated directory for immutable edge delivery.

Question 9

How is Sites usage billed?

Accepted Answer

There is no fee per site or deployment. Usage is pooled across your workspace and measured by edge requests, data transferred to visitors, and retained deployment storage. Storage includes every immutable version, not only the active release.

Question 10

Can I switch between monthly and yearly billing?

Accepted Answer

Yes. You can switch at any time. When switching to yearly, you pay for 10 months and get 2 months free. Changes take effect at the start of your next billing cycle.

Question 11

What is the Enterprise plan?

Accepted Answer

Enterprise is for organizations needing SSO/SAML, audit logs, custom integrations, SLA guarantees, and unlimited usage. Contact our sales team for custom pricing tailored to your needs.

Search features	Starter $0 Start free	Build $20/mo Choose Build	Scale $100/mo Choose Scale	Enterprise Custom Talk to us
AI Gateway
OpenAI-compatible API
Provider routing & fallback
Automatic retries
Load balancing
Bring your own provider keys
Chat, responses, embeddings, images & audio
API requests / month	10K	100K	1M	Unlimited
Requests / minute	60	600	6K	Unlimited
Included tokens / month	1M	10M	100M	Unlimited
Semantic caching
Rate limiting	Basic	Advanced	Advanced	Custom
API key management
Spend limits & usage controls
Observability
Request/response logging
Distributed tracing
OpenTelemetry export
Gateway, agent & sandbox correlation
Real-time dashboards	Basic	Standard	Advanced	Custom
Advanced analytics
Alerts & anomaly detection
Cost analytics	Basic	Standard	Detailed	Custom
Agent Runtime & Workflows
Agent definitions	3	10	30	Unlimited
Always-on agents	1	3	10	Unlimited
Always-on runtime instances			10	Unlimited
Concurrent agent runs	1	3	10	Unlimited
Session history retention	7 days	30 days	90 days	Unlimited
Child-agent delegation
Delegation depth			5 levels	Unlimited
Workflows Studio
API, webhook & schedule triggers
Human approval gates
Connected channels	3	Unlimited	Unlimited	Unlimited
Messaging platforms	Slack, Discord & Telegram	Slack, Discord & Telegram	Slack, Discord & Telegram	Slack, Discord & Telegram
Channel messages / month	1K	15K	100K	Unlimited
Custom tool integrations
Sandboxes & Code Execution
Included sandbox vCPU-hours / month	40	150	750	Contracted usage
Sandbox compute beyond included hours	Usage billed ($5 starter credit)	Usage billed	Usage billed	Contracted usage
Concurrent sandboxes	10	50	50	Unlimited
Maximum sandbox memory	512 MB	1 GB	4 GB	Unlimited
Isolated execution environments
Dedicated execution pools
Shell, file & process APIs
Snapshots & resume
Persistent volumes
Controlled network egress
Signed port previews
Node.js, Python & Go SDKs
Per-second allocation billing
Included root disk	20 GiB	20 GiB	20 GiB	Contracted
Browser Runtime
Headless Chromium automation
Live browser viewport
Concurrent browser sessions	2	10	25	Custom
Maximum session duration	15 minutes	1 hour	4 hours	Custom
Active browser runtime	$0.05/hour	$0.05/hour	$0.05/hour	Volume pricing
Warm-pool idle time	Not billed	Not billed	Not billed	Contracted
Sites & Publishing
Static sites on evs.run
Hosted sites	3	10	30	Unlimited
Edge requests included	100K	1M	5M	Custom
Data transfer included	10 GB	100 GB	500 GB	Custom
Deployment storage included	500 MB	5 GB	25 GB	Custom
Usage beyond the allowance	Hard limit	Pay as you go	Pay as you go	Committed usage
CLI and MCP publishing
Immutable versions and atomic activation
Source-task provenance & audit history
Edge delivery and managed TLS
Evaluations & Quality
Evaluations & experiments
Evaluation runs / month	5	50	500	Unlimited
Dataset items	1K	50K	500K	Unlimited
Annotation queues	1	5	25	Unlimited
LLM-as-judge scoring
Deterministic code scorers
Human review workflows
Guardrails & policy checks
Regression alerts
Memory & Storage
Object & artifact storage	500 MB	5 GB	50 GB	Unlimited
Session vector memory
External vector stores
S3-compatible object storage
Durable agent artifacts
Security & Access
Tenant isolation
Role-based access control
SSO & SAML
Audit logs				Planned
Custom integrations
Approval policy enforcement
API key rotation
Support
Included team seats	1	3	10	Unlimited
Community support
Priority support
Dedicated support & SLA

Simple, transparent pricing

Starter

Build

Scale

Enterprise

Platform plans plus metered infrastructure.

Estimate a fixed-size sandbox.

Feature comparison

Pricing FAQ

Ship the AI stack
you can actually operate.