Skip to main content
PUT
Update an AI provider

Authorizations

Authorization
string
header
required

An sre_ak_* API key holding the api:admin scope (or api:config_read, which every write refuses with read_only_key).

Path Parameters

id
string
required

The resource's id.

Body

application/json
api_key
string<password>
write-only

The provider's key. Write-only: it is never answered by any tool here, an omitted one keeps the stored key, and an empty one is refused rather than read as a way to remove it. To remove it, delete the provider. Paste the key itself; a URL goes in base_url and is refused here.

auto_upgrade_model
boolean

Whether the platform may move model on to a successor once the configured one drops out of the provider's list. Off by default: a pinned model stays pinned.

base_url
string | null

Where to send the calls, for a gateway or a self-hosted endpoint. null uses the provider's own.

enabled
boolean

Whether the router may route to this provider at all. A disabled row keeps its key and its pins and is skipped.

max_tokens
integer | null

The ceiling on one answer's length. null uses the platform's own.

model
string | null

The model to use, spelled as the provider spells it. null leaves the choice to the platform's own default.

model_overrides
object

A model per purpose, keyed by purpose: investigation, suggestion, report_generation, alert_grouping, context_compaction, pr_review, remediation, oversight, config_watch, finops, slack_assistant, board_assistant, runbook_suggestion, sli_suggestion, capacity_planning, status_page_draft, ticket_synthesis, security_triage. Merged into what is stored, so a map naming one purpose leaves the rest alone; an empty string under a purpose clears that pin. The value "auto" hands the choice to the platform's own model selection for that purpose.

name
string

What this provider is called here, unique within the organization. It is a label for the people reading the list, not anything the provider sees.

priority
integer

The order the router tries this organization's providers in, lowest first. At least 1.

provider
enum<string>

Which provider this row talks to: anthropic, openai, openrouter, ollama, bedrock, gemini, portkey, langchain.

Available options:
anthropic,
openai,
openrouter,
ollama,
bedrock,
gemini,
portkey,
langchain
rate_limit_rpm
integer | null

Requests per minute this provider will accept. null means no limit.

temperature
number | null

0 to 2. null leaves the provider's own default in place.

timeout_ms
integer | null

How long one request may take, at most 600000. null uses the platform's own.

Response

Updated.