Changelog · API 1.0.0-pre
What changed.
Every change an agent or a customer can see: endpoints, rules, limits, pages. Newest first. Subscribe with RSS, or read it as Markdown or JSON.
APIDocs
Open JSON Schemas and the outcome receipt spec
- JSON Schemas (2020-12) for receipts, execute requests and responses, webhook events and pass rules, at
/schemas/{name}.json(index:/schemas), under CC BY 4.0. - The outcome receipt spec, v1: every field, the rules, and how the hashes are made (SHA-256 of canonical JSON), so anyone can verify a receipt against the data they kept.
- A Python receipt verifier next to the score formula in the open benchmark harness.
DocsSite
Developer docs, changelog and status
- Docs for every part of the API: quickstart, authentication, test mode, recommend, execute, jobs, receipts, disputes, budgets and approvals, webhooks, the org API, MCP, the SDKs, scores, pass rules, credits, data handling, rate limits and public data.
- Every docs page has a Markdown and a JSON copy: add
.mdor.jsonto its URL, or sendAccept: text/markdown. - This changelog, as
/changelog.md,/changelog.jsonand an RSS feed at/changelog.xml. - Terms and privacy drafts at
/termsand/privacy.
SDKsDocs
Error codes the SDKs raise themselves
network_error,timeout,aborted,unexpected_redirect,connection_failedandhttp_errorare listed on/docs/errors, so everydoc_urlan SDK hands you resolves.GETandDELETEon/mcpanswer 405method_not_allowed: the MCP server is stateless and takesPOSTonly.
APIDashboard
Ask for your stored data to be deleted
- An owner can ask us to delete the org's stored inputs, results and private test sets from Team in the dashboard, or with
POST /v1/orgs/{orgId}/deletion-requests. It is done within 24 hours and we email you when it is. GET /v1/orgs/{orgId}/deletion-requestsshows each request and when it is done by. Org keys can read requests; making one needs an owner signed in.- New error
credits_frozen: purchases are declined while we look into something on the account; sign-in and reads keep working.
SDKsMCP
TypeScript and Python SDKs, and a local MCP server
@arettic/sdk(TypeScript) andarettic(Python) cover every agent and org endpoint, with retries on reads and onexecute(its idempotency key makes a retry safe).@arettic/mcpruns a local stdio MCP server that forwards to the hosted one, for clients that don't speak Streamable HTTP.- The hosted MCP server has all nine tools:
list_task_types,recommend,get_tool,execute,get_job,get_receipt,open_dispute,get_approvalandget_balance.
APIDashboardScores
Private benchmarks and the provider view
- Pro orgs can upload their own test set and benchmark any tools on it:
POST /v1/orgs/{orgId}/test-sets, thenPOST /v1/orgs/{orgId}/benchmarks. Results stay private to the org. - Providers can claim their listing and see a read-only view of their scores, failure reasons and demand:
GET /v1/orgs/{orgId}/provider.
APIDashboard
Everything in the dashboard works through the API
- Org API keys (
ok_…, read or write, one org) drive every dashboard action. Make them on Team, or withPOST /v1/orgs/{orgId}/keyswhile signed in. - The dashboard meets WCAG 2.2 AA and never shows a CAPTCHA.
DashboardAPI
Customer dashboard, receipts and disputes
- Spend by day, agent and tool, balance, and how many items cost you nothing:
GET /v1/orgs/{orgId}/dashboard. - Receipt explorer with filters and a CSV export:
GET /v1/orgs/{orgId}/receipts,GET /v1/orgs/{orgId}/exports/receipts.csv. - Dispute a charged item within 7 days:
POST /v1/disputes(agent key) orPOST /v1/orgs/{orgId}/disputes. We decide within 48 hours against the stored result; upheld means a refund to where the credits came from, and it counts against the tool's score. - Signed webhooks with 24 hours of retries, plus emails, for the single event list:
POST /v1/orgs/{orgId}/webhooks,GET /v1/orgs/{orgId}/events.
APIPass rulesPricing
Execute: pay only for results that pass
POST /v1/executeruns any of the 30 curated tools with one key. Each result is checked against the published pass rule for its task type: pass is charged, fail releases the hold and returns the reason, provider errors are never charged.- Up to 1,000 inputs per request; over 25 runs as a job (
GET /v1/jobs/{id}). - Idempotency keys: a retry with the same key is never charged twice.
- Opt-in fallback to the next-best tool, budgets and approval thresholds per agent (
GET /v1/approvals/{id}), IP allowlists, and receipts for every purchase (GET /v1/receipts/{id}). - Inputs and results are stored encrypted for 7 days (longer only while disputed), then deleted.
PricingAPIDashboard
Credits, top-ups and plans
- Buy credits in US dollars (1 credit = $0.001):
POST /v1/orgs/{orgId}/topups. An invoice for every top-up:GET /v1/orgs/{orgId}/invoices. - $1 of trial credit when you make your org; auto-reload from a saved card (
PUT /v1/orgs/{orgId}/auto-reload). Paid credits expire after 12 months. - The Pro plan:
POST /v1/orgs/{orgId}/subscriptions. Prices are recomputed daily from each tool's cost and pass rate; moves over 20% are reviewed before they apply (GET /v1/pricing).
APIScoresMCPSite
Recommend, scores and public data
POST /v1/recommend: tools ranked for a task, with every score input, the price per success and the pass rule.- Weekly scores from our own benchmarks plus live results (formula at
GET /v1/formula), published under CC BY 4.0 with no key:GET /v1/tools,GET /v1/scores,GET /v1/task-types. /llms.txt,/llms-full.txt,/openapi.jsonand/.well-known/mcp.jsonfor agents; a Markdown and JSON copy of every page.- Rate limits reported in
RateLimit-*headers; a 429 carriesRetry-After.
APIDashboard
Accounts, orgs and agent keys
- Sign in with an email link or Google, verify a phone, make an org and invite your team (owners and members).
- Agents with their own
sk_test_…andsk_live_…keys (rotate or revoke any time). Test keys call deterministic mock providers for free. - One error envelope everywhere,
{ error: { code, message, doc_url, retryable } }, with every code on/docs/errors.