Developer API
A REST API for AI completions and read access to the prompt library. Available on the Business plan and metered against your team’s shared credit pool.
Getting started
API keys are managed by the owner of a Business workspace. Open the Team area, create a key, and copy it — it is shown only once.
Manage keys →Base URL
Every endpoint is prefixed with /api/v1 on the platform domain.
https://<your-domain>/api/v1Authentication
Pass your key in the Authorization header. Always call over HTTPS and never embed a key in client-side code.
curl https://<your-domain>/api/v1/me \
-H "Authorization: Bearer ak_live_xxxxxxxx"Rate limits
Each key is allowed 60 requests per minute. Responses carry X-RateLimit-* headers; exceeding the limit returns 429 with Retry-After. Monthly AI usage is counted against your team plan’s quota.
Scopes
Each key carries one or more scopes. A request outside a key’s scopes returns 403.
ai:complete— AI completionsprompts:read— Read prompts
Endpoints
/api/v1/meReturns the workspace, plan, the key’s scopes, and the current AI quota. Consumes no quota — ideal for verifying a key.
{
"workspaceId": "ws_…",
"plan": "team",
"scopes": ["ai:complete", "prompts:read"],
"quota": { "used": 142, "limit": 5000, "remaining": 4858 }
}/api/v1/ai/completeai:completeRuns a single AI completion with the given model. Counts against the team’s monthly quota.
curl https://<your-domain>/api/v1/ai/complete \
-H "Authorization: Bearer ak_live_xxxxxxxx" \
-H "Content-Type: application/json" \
-d '{ "model": "claude", "prompt": "Summarise Q3 in 3 bullets" }'/api/v1/prompts?limit=50&offset=0prompts:readReturns published prompts with pagination and optional vertical / category filters.
Errors
Errors return JSON with an error field and a matching HTTP status.
401 missing_api_key | invalid_api_key
403 plan_inactive | insufficient_scope
402 quota_exceeded
429 rate_limited (see Retry-After)
502 upstream_error