POST /v1/sharpen
Sharpens a draft answer: send the task and the draft, get back what the assistant needs to make it better. operationId
sharpen. Request and response are stable contracts (SharpenRequest, SharpenResponse).Request
| Field | Description |
|---|---|
| taskstringREQUIRED | What the user asked for, verbatim or close.min length 1 |
| contextstring | Facts, constraints and data that matter for the answer. |
| approachstring | How the draft was produced: assumptions, method, trade-offs. |
| draftstringREQUIRED | The draft answer to sharpen.min length 1 |
| caller_provider"openai" | "anthropic" | "google" | "xai" | "deepseek" | "meta" | "mistral" | "other"REQUIRED | The family of the model that wrote the draft. |
| stage"stage1" | "stage2" | "stage3" | "stage3+" | Stages: stage1 = Stage 1 (sharpen), stage2 = Stage 2 (plus), stage3 = Stage 3 (ultra), stage3+ = Stage 3+ (ultra2x). Each stage sharpens more deeply than the one before; Stage 3+ goes deepest. Stock means Sharpen is disabled. Omit stage to use the saved setting; for an explicit request such as "take it to Stage 3+", pass stage: "stage3+". A per-call stage never changes the saved setting and requires Sharpen to be enabled. |
- Unknown keys are rejected with
400 invalid_request.
caller_provideris the family of the model that wrote the draft.stageselects the stage for this call only (stage1…stage3+). Omit it to use the account's saved tier. Sharpen must be enabled on the account; a per-call stage cannot enable it.- Combined input is capped at 60,000 characters.
curl
curl -s -X POST https://api.powerups-ai.store/v1/sharpen \
-H "Authorization: Bearer $AIPA_API_KEY" -H "Content-Type: application/json" -d '{
"task": "<what the user asked, verbatim>",
"context": "<facts, constraints and data that matter for the answer>",
"approach": "<how the draft was produced: assumptions, method>",
"draft": "<the full draft answer>",
"caller_provider": "anthropic"
}'Response
SharpenResponse
{
"tier": "sharpen" | "plus" | "ultra" | "ultra2x",
"stage"?: "stage1" | "stage2" | "stage3" | "stage3+",
"results": [ { "text": "…" } ],
"partial": false,
"routing_note"?: "…",
"instruction": "…",
"charged_credits": 5,
"balance": { "used": 17, "cap": 500, "period_end": null }
}resultsholds the sharpening results for the draft, each as plain-prosetext: one result, or two at Stage 3+ (ultra2x).partialis true when part of a Stage 3+ run did not complete; only the completed part is charged androuting_notesays so.instructionsays how to apply the results: revise the draft, then answer.
Typical credits by tier: 5, 30, 120, 240. The actual cost is metered; when a stage cannot complete, the call returns 503 sharpen_unavailable without charge. Timeouts are 30, 60 and 120 seconds per pass by tier, so set your client timeout accordingly.

REST is synchronous
REST Sharpen has no idempotency key. The MCP tool of the same name is asynchronous with a 24-hour
request_id dedupe; that is an MCP-only feature described in the assistant docs.