-
Quickstart
Sign in, verify with a card, issue a token, first request.
Open -
Get an API token
Issue a connection token in the account console and put it in the environment.
Open -
Models
The catalog at /v1/models: red-team (dedicated route) and blue-team (shared route) models and what admits each.
Open -
Streaming
stream: true is served as a one-chunk SSE; underneath, a job (submit, poll).
Open -
Tool calling
Native tool calling: send definitions, get tool_calls back. Execution stays on the agent.
Open -
Reasoning
The model reasons before it answers; reasoning tokens count inside max_tokens.
Open -
Guardrails & firewall
Guardrails on every request, the firewall by assurance rung, versions published at /secure/.
Open -
Structured outputs
response_format is accepted and dropped. Ask for JSON in the prompt.
Open -
Errors
The OpenAI-compatible error shape and per-code handling.
Open -
Rate limits
The free 50 req/day allowance and tokens/day by assurance rung.
Open -
Billing & usage
1 credit = $1; plans, balances, per-token micro-USD rating, settlement from receipts.
Open -
Per-request cost
Reading billing / usage / chargedMicroUSD on a response, and how free vs paid is decided.
Open -
Zero data retention
ZDR design: only minimal state is retained.
Open -
BYOK
Bring-your-own provider keys are not offered (first-party inference).
Open -
Security services (CTEM)
The public catalog of the security-services suite at GET /v1/security/services — CTEM (component-shipped) and its four capabilities feeding the VM ledger.
Open