Documentation
Build with Mintdesk
Prepare your client configuration and understand your account controls. These examples describe the intended API formats; live routing and client compatibility are not yet verified.
http://201.18.214.119Quickstart
- 1
Create account
Sign up with Google or email.
- 2
Add tokens
Review packs; payments are awaiting activation.
- 3
Create a key
Copy it once and set the base URL.
Authentication
The planned authentication formats accept your key as x-api-key or Authorization: Bearer. Keys start with md_live_ and are shown only once.
Base URL: http://201.18.214.119 OpenAI SDK / Cursor: http://201.18.214.119/v1 Models: http://201.18.214.119/v1/models Header: Authorization: Bearer md_live_your_key
Use http://201.18.214.119 when your client appends /v1/models. OpenAI SDKs and Cursor use http://201.18.214.119/v1.
Planned endpoints
/v1/messagesAnthropic Messages format — Claude Code, Anthropic SDKs/v1/chat/completionsOpenAI-compatible format — Cursor, OpenAI SDKs/v1/modelsList models available to your keyCode samples
export ANTHROPIC_BASE_URL="http://201.18.214.119" export ANTHROPIC_AUTH_TOKEN="md_live_your_key" export ANTHROPIC_MODEL="claude-fable-5-1" claude
Models
Claude Fable 5.1 Max
claude-fable-5-1Claude Opus 5.5
claude-opus-5-5Claude Sonnet 5.5
claude-sonnet-5-5Claude Haiku 5.5
claude-haiku-5-5Streaming
Set "stream": true to receive server-sent events as the response is generated — the same event format Anthropic SDKs already understand.
curl http://201.18.214.119/v1/messages \
-H "x-api-key: md_live_your_key" \
-H "anthropic-version: 2023-06-01" \
-H "content-type: application/json" \
-d '{"model":"claude-sonnet-5-5","max_tokens":512,"stream":true,
"messages":[{"role":"user","content":"Hello"}]}'Rate limit headers
Planned responses will include headers so your client can back off before hitting a limit.
x-ratelimit-limit-requestsRequests allowed per minutex-ratelimit-remaining-requestsRequests left in the current windowx-mintdesk-balanceRemaining prepaid tokensretry-afterSeconds to wait after a 429Best practices
- • Keep keys on the server — never ship them in browser or mobile app code.
- • Create one key per project and give each its own token allocation.
- • Retry 429 and 5xx responses with exponential backoff.
- • Pick Haiku 5.5 for high-volume tasks and Opus 5.5 or Fable 5.1 Max for hard reasoning.
Billing & limits
- • The planned metered API counts input and output tokens against your shared prepaid balance.
- • Default rate limit is 60 requests per minute; see yours under Profile → API limits.
- • The planned API will reject exhausted balances with
402until you top up.
Planned error responses
401Missing, invalid or revoked key402Token balance exhausted429Rate limit exceeded — retry after a moment500Upstream error — check request outcome before retryingReady? Create your key →