本文へ移動

Welcome to Mithril

One API. For victims of hacking and fraud, and verified researchers. OpenAI-compatible — tool calls and streaming included.

Mithril is an OpenAI-compatible inference API. Point an existing OpenAI SDK at https://api.kotoba.cloud/v1 and call models tuned for investigating hacking and fraud — and for security research — behind guardrails, a firewall and audit receipts. The verified free allowance stays; add prepaid credits only as you need them. No unauthorized intrusion or credential theft.

Why Mithril

  • OpenAI-compatible by design

    Every request and response is in the OpenAI JSON shape. Point base_url at https://api.kotoba.cloud/v1 and streaming, tool calling and reasoning keep working. Anthropic Messages (POST /v1/messages) is not served (405) — Claude Code-class clients need a translating proxy.

  • Admission for victims and researchers

    Red-team models run only behind card-based identity verification, AUP consent and an approved scope; blue-team models need a sign-in. Guardrails run on every request either way. Victims and verified researchers investigate only within authorized scope.

  • Prepaid, no markup on the meter

    1 credit = $1. Input $0.9/M and output $4.5/M tokens, settled from the provider receipt. Automatic recharge is opt-in, off by default; with no balance you are simply on the free allowance.

  • Data handling

    Chat and research conversation content is stored on operator servers for the life of the account until delete. No inference logs; never used for training. Not end-to-end private from the operator.

Where to start

New models, pricing and free-allowance changes, by email. Your address is recorded once in Mithril's sales system and used for these updates. No other use.