Limits - Cycls

Values that constrain what you can build. Platform limits are enforced by the service. Defaults are what you get without configuration and can be changed.

Build and deploy

Limit	Value	Notes
Source archive	100 MiB	ship larger files through a volume
Python version	must match your host’s major and minor	cloudpickle bytecode does not cross versions
cloudpickle version	must match your host exactly
First build of a new image	1 to 2 minutes	cached after that
First executor provision per image	about 90 seconds	one per image configuration

Runtime

Limit	Default	Maximum	Notes
Request timeout	1200 seconds, 3600 for apps and agents	3600 seconds	a function sets it with `timeout=`
Memory	`1Gi`	`32Gi`	set with `memory=`
CPU	platform choice	8	1, 2, 4, 6 or 8
Concurrency	high		set to 1 for compute-bound work
Cold start after idle	a few seconds		instances scale to zero

Remote calls

Limit	Value
Payload per call	keep well under 30MB
Call timeout	one hour, set with `timeout=` on `cycls.remote`
`map` fan-out width	16 workers by default, set with `workers=`

Scheduled functions

Limit	Value
Single run duration	30 minutes
Delivery	at least once, so runs can repeat
Overlap	a slow run does not block the next

Storage

Limit	Value	Notes
Volume upload and download size	unlimited through the CLI	`put` and `get` talk to storage directly
Volume deletion recovery window	7 days
Concurrent writes to one file	last write wins	there is no locking
Cross-deployment visibility	seconds	not instant

Agent loop

Limit	Default	Notes
Run duration	45 minutes	past it, the run ends as `interrupted` with reason `budget`
Context window	1,000,000 tokens	set with `.context()` to match your model
Output tokens per request	8192	set with `.max_tokens()`
Compaction trigger	70% of the context window	lower when `.max_tokens()` needs the room, see Long conversations
Kept verbatim after compaction	the most recent 30% of the window
Summary timeout	300 seconds	older turns are dropped when it fails
`read` per call	50,000 characters	lines cut at 2,000 characters, the model continues with `offset`
File size for `read`	3 MB	larger files are read through bash, larger PDFs by page
Document parsing	50 MB per file, 120 seconds	`read` sends documents to the parser first, and reads them itself when a file is larger or the call fails
PDF pages per `read`	20
`web_fetch` per call	20,000 characters	the model can ask for up to 100,000
Bash timeout	600 seconds	set with `.bash_timeout()`. The model can pass its own `timeout` per call, in milliseconds
Upload per file	512 MB	set with `.max_upload()`
`AGENT.md`	24 KB	truncated beyond that
Questions per `ask` card	3

Skills, apps and connectors

Limit	Value	Notes
Skill version	10 MB and 500 files	per upload or publish
Skill description	1,024 characters	always in the system prompt
`SKILL.md` or a support file	48 KB per load	truncated beyond that
`build_app` source	400 files, 12 MB in all, 2 MB per file	text files only
`build_app` build	420 seconds
App data value	1 MB	per key
App data list	10,000 rows	`truncated` is `true` beyond that
App write	25 MB
Connector API relay calls	240 per minute	per person and connector on one instance, then 429
Connector API relay response	5 MB

Retention

Item	Window
Deleted files in trash	30 days
Deleted volumes	7 days
Chats and workspace files	until deleted, they live on your volume

Next

Examples

Working code for each primitive.