Read the AI inference settings
GET /admin/ai/config
Returns the AI inference settings: the master switch, each task’s provider and fallback list, the privacy lock and the spending limits, with any problems found in them.
You need ai.admin or system.admin for the whole install; a
permission held only for a team doesn’t count. Without one you get
403, and signed-out callers get 401.
A setting that has never been saved comes back as its built-in default, given with each field below. Each server keeps its own copy of the settings once it has read them, and a save made through another server may not show here until this one saves or restarts.
If the settings can’t be read, you still get a 200, with every value
empty, off or 0 and a single finding with the code internal, so
check findings before relying on the values.
These settings are separate from the saved AI provider list (getAIConfig) and the image-edit server (getAIEditConfig), and nothing here reads either one.
Authorizations
Section titled “Authorizations ”Responses
Section titled “ Responses ”The AI inference settings, with any problems found in them.
The AI inference settings, as getAIInferenceConfig and
updateAIInferenceConfig return them. findings is worked out by the
server each time and isn’t saved.
object
The master switch. A fresh install has it off. It’s saved and returned, but nothing reads it yet, so it doesn’t turn any AI feature on or off.
The provider each task tries first, keyed by task: complete,
embed, transcribe, tag and caption. Other keys are dropped
when the settings are read. The built-in default is claude,
clip_local, whisper_local, ollama and claude, in that order.
Names aren’t checked, and the saved AI provider list (getAIConfig)
isn’t read; a name the server has no provider for is skipped when
the task runs.
object
For each task, the providers to try after its first one, in order. The next one is tried when a call fails with a temporary or network error or a rate limit; a permanent error or a budget refusal ends the task. A name already tried is skipped. A task left out has no fallback. Other keys are dropped when the settings are read. Each task has a built-in default list.
object
The privacy lock for restricted and embargoed assets.
object
When true, AI work on an asset whose sensitivity is restricted or
embargo may only use local providers, and fails when none of the
task’s providers is local. A fresh install has it on. It’s read when
a server starts, so a change needs a restart. Only the sensitivity
counts, not team access or the mature flag.
The provider names treated as local by the privacy lock. Listing a provider is your statement that it keeps data local; nothing checks where it runs. MCP tool calls, such as image editing, ignore this list and use the privacy class each MCP server was registered with. A fresh install lists ollama, vllm, whisper_local and clip_local. It can come back as null instead of an empty list.
Monthly spending limits in whole US dollars. Each provider gets the same limits separately.
object
Meant to add a warning to the usage records when a provider’s spending first reaches this many dollars in a month. It’s saved and returned, but nothing records a warning yet. 0 means no warning, and is the fresh-install value.
The most each provider may spend in a month, in whole dollars. Before each AI call, the server refuses it when the provider’s recorded spending for the month, plus any cost declared for an MCP tool, would be over this limit. 0, the fresh-install value, refuses every call to every provider, local ones included. Spending isn’t reserved and calls aren’t stopped part-way, so the limit can be passed. Each server reads the limit and the recorded spending the first time it checks a provider in a month and can keep them until the month ends or it restarts, so later spending and a changed limit may not count until then.
Problems found in the settings, sorted by code and then by task, and left out when there are none. Only two things are checked: that every task has a provider, and, while the privacy lock is on, that there is at least one local provider.
object
What the problem is. The server sends routing_missing_concern (a
task has no provider), privacy_lock_with_empty_local_list (the
lock is on with no local providers) and, from a read, internal
(the settings couldn’t be read; see message).
The task the problem is about; left out when it isn’t about one task.
The problem in English. For internal, the error that stopped the read.
Authentication required, missing, or invalid
object
Human-readable error summary
Example
the request could not be completedExample
{ "error": "authentication required: sign in and retry with a valid session or API token"}Authenticated but missing required capabilities
object
Human-readable error summary
Example
the request could not be completed