credits:spend

credits family

Record one model call's spend against YOUR workspace — priced by the one writer (sdk spend: tokens × the model's live rate), debited from the funding chain, emits credits.spent, closes with mark or warn (text/billing.md promise 3)

Effect: ask; Awaits an outcome — the call returns the response below.
Caller: member; The class of authority the caller must already hold, decided from the attested context with no round trip.
Cost: variable; What one call costs, so you can budget before acting.
Reversible: yes; The effect can be undone by a later call.
Idempotent: no; Not safe to blind-retry — dedupe on the envelope idempotencyKey.

Send it with your agent

One click hands your coding agent a prompt that registers the substrate, reads this contract, and makes the call. Launch opens the app; the others copy the prompt.

Claude Code

Codex

Cursor

Gemini CLI

Claude Desktop

ChatGPT

curl -X POST https://one.ie/api/ask/credits:spend \
  -H "Authorization: Bearer $ONE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"data": { "model": <string>, "tokensIn": <number>, "tokensOut": <number> }}'

The key is never in a link. npx -y @oneie/cli login writes it to ~/.config/oneie/key on your machine.

Request

Validated before dispatch — an invalid payload is refused with the fix, never half-applied.

model string required The model the call RAN on, e.g. 'deepseek/deepseek-v4-flash'. Priced from the live OpenRouter rate blob; an unknown id prices at the fallback and the row says rate_source='fallback'.
tokensIn number required Prompt tokens actually consumed.
tokensOut number required Completion tokens actually consumed, INCLUDING reasoning tokens.
reason agent_run | skill_call | inference optional What the call was for. Default agent_run.
threadId string optional The thread the call served, if any — carried on the credits.spent event.

Response

What comes back from the call.

ok boolean
credits number Credits charged (cost + margins).
costCredits number The upstream cost in credits, before margins.
recorded boolean true on a refusal: the tokens were already spent, so the row is written anyway and the balance goes negative.
error string unauthorized | invalid_request | nothing_to_spend | ledger_unavailable | meter_run_failed | 402 | floored | budget_exhausted | float_locked

Traffic

Every call to credits:spend, counted where it is dispatched — over HTTP or in-process alike. Aggregate only — no actor, no payload, no workspace.

Counting…

Wiring

Every place in the open source that names credits:spend, and the file that answers it. Read from the tree at build time — a receiver is reached by NAME through one door, so there is no import edge to follow and a grep is the honest shape of the question. Structure, not volume — the count is in Traffic above.

Called from

API route 1

one.ie/web/src/lib/receiver-index.generated.ts:96

→

Answered by

credits:spend one.ie/web/src/lib/resolvers/credits.ts:25 Dispatched through POST /api/ask/credits:spend, after the envelope validates the payload.

JSON Schema

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "minLength": 1,
      "maxLength": 200,
      "description": "The model the call RAN on, e.g. 'deepseek/deepseek-v4-flash'. Priced from the live OpenRouter rate blob; an unknown id prices at the fallback and the row says rate_source='fallback'."
    },
    "tokensIn": {
      "type": "integer",
      "minimum": 0,
      "maximum": 10000000,
      "description": "Prompt tokens actually consumed."
    },
    "tokensOut": {
      "type": "integer",
      "minimum": 0,
      "maximum": 10000000,
      "description": "Completion tokens actually consumed, INCLUDING reasoning tokens."
    },
    "reason": {
      "description": "What the call was for. Default agent_run.",
      "type": "string",
      "enum": [
        "agent_run",
        "skill_call",
        "inference"
      ]
    },
    "threadId": {
      "description": "The thread the call served, if any — carried on the credits.spent event.",
      "type": "string",
      "maxLength": 200
    }
  },
  "required": [
    "model",
    "tokensIn",
    "tokensOut"
  ]
}

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "type": "object",
  "properties": {
    "ok": {
      "type": "boolean"
    },
    "credits": {
      "description": "Credits charged (cost + margins).",
      "type": "number"
    },
    "costCredits": {
      "description": "The upstream cost in credits, before margins.",
      "type": "number"
    },
    "recorded": {
      "description": "true on a refusal: the tokens were already spent, so the row is written anyway and the balance goes negative.",
      "type": "boolean"
    },
    "error": {
      "description": "unauthorized | invalid_request | nothing_to_spend | ledger_unavailable | meter_run_failed | 402 | floored | budget_exhausted | float_locked",
      "type": "string"
    }
  },
  "required": [
    "ok"
  ]
}