API reference

The gateway surface: authentication, device login, entitlement, models, and inference.

Base URL

https://api.sknib.com

Authentication

Send a bearer token on every request except the two device endpoints.

Authorization: Bearer sk-nib-...

Two credential shapes are accepted: a device token issued by nib login, and an API key created in the console. Both resolve to the same user, plan, and credits.

Errors

Errors use the OpenAI shape so existing SDKs surface a useful message.

{ "error": { "type": "insufficient_quota", "message": "Monthly credits exhausted" } }

Status	Type	Meaning
401	`authentication_error`	Missing, expired, or revoked credential
402	`insufficient_quota`	Credits exhausted, including top-up balance
403	`permission_error`	Plan does not include the requested model
429	`rate_limit_error`	Concurrency or RPM exceeded
5xx	`api_error`	Gateway or upstream failure

Device login

POST /api/v1/cli/device/authorize

No authentication. Returns a device code and a short user code.

{
  "device_code": "3f0c2a1e-...",
  "user_code": "MKGX-36FF",
  "verification_uri": "https://sknib.com/device",
  "verification_uri_complete": "https://sknib.com/device?code=MKGX-36FF",
  "expires_in": 600,
  "interval": 5
}

POST /api/v1/cli/device/token

Poll at interval seconds. Pending responses return HTTP 400 with {"error":"authorization_pending"}. Success returns:

{
  "access_token": "nib_dev_...",
  "token_type": "Bearer",
  "expires_in": 7776000
}

Other error codes: slow_down, access_denied, expired_token.

Entitlement

GET /api/v1/product/entitlement

{
  "plan": {
    "id": "starter-promo",
    "name": "Starter",
    "price_usd": 15,
    "effective_price_usd": 10,
    "currency": "USD",
    "promotional": true,
    "promotional_until": "2027-01-31T00:00:00Z",
    "monthly_credits": 300,
    "weekly_credit_cap": 120,
    "daily_credit_cap": 45,
    "concurrency": 3,
    "requests_per_minute": 120
  },
  "usage": {
    "credits_used": 114.0,
    "credits_used_this_week": 42.5,
    "credits_used_today": 16.2,
    "topup_credits_remaining": 0,
    "resets_at": "2026-11-14T08:00:00Z"
  },
  "models": { "available": 42 }
}

All monetary values are numbers in USD, never strings. Caps may be null when unset; the field itself is always present.

Models

GET /v1/models

OpenAI-compatible listing. tier is the only extension.

{
  "object": "list",
  "data": [
    { "id": "nib-efficient", "object": "model", "owned_by": "nib", "tier": "efficient" },
    { "id": "nib-frontier", "object": "model", "owned_by": "nib", "tier": "frontier" }
  ]
}

Inference

Protocol	Path	Used by
OpenAI Chat Completions	`POST /v1/chat/completions`	Most editors and SDKs
OpenAI Responses	`POST /v1/responses`	Codex-style clients
Anthropic Messages	`POST /v1/messages`	Claude Code, Anthropic SDK
Gemini	`POST /v1beta/models/{model}:generateContent`	Google SDK

Usage accounting is identical across protocols. The same request costs the same credits regardless of which endpoint it arrives on.

Response headers

Header	Meaning
`x-nib-credits-charged`	Credits charged for this request
`x-nib-credits-remaining`	Plan credits left in the current period
`x-nib-request-id`	Support reference

Versioning

Breaking changes ship under /api/v2. v1 stays available for at least six months after v2 ships.
Adding optional response fields is not a breaking change.
Removing or renaming a field is breaking, including tier and the credit headers.

Rate limits

Concurrency and RPM follow your plan and are exposed in the entitlement payload. A 429 response includes retry-after in seconds. Client-side, back off exponentially and cap retries at three.