HALOWERKModellwerk
context plan
Plans the division of a long input for a given model. It reserves room for the system prompt, the expected answer and a safety margin, then works out how many chunks are needed and where to cut, preferring paragraph boundaries over line and sentence boundaries and never cutting inside a word. Optional overlap carries context across the seams.
POST https://modell.halowerk.com/v1/context-planEingaben
| Feld | Typ | Pflicht | Beschreibung |
|---|---|---|---|
| text | string | Ja | The document to split. |
| model | string | Ja | Target model id, e.g. claude-opus-5. |
| expected_output_tokens | integer | Nein | Room to reserve for the answer per chunk. |
| system_prompt_tokens | integer | Nein | Room to reserve for the system prompt per chunk. |
| overlap_tokens | integer | Nein | Tokens of the previous chunk repeated at the start of the next. |
| safety_margin | number | Nein | Fraction of the window held back against estimation error. 0.1 = 10 percent. |
| boundary | string | Nein | Where to cut. auto tries paragraph, then line, then sentence. |
Vollständiges Eingabeschema anzeigen
{
"type": "object",
"required": [
"text",
"model"
],
"additionalProperties": false,
"properties": {
"text": {
"type": "string",
"minLength": 1,
"maxLength": 2000000,
"description": "The document to split."
},
"model": {
"type": "string",
"description": "Target model id, e.g. claude-opus-5."
},
"expected_output_tokens": {
"type": "integer",
"minimum": 0,
"default": 2000,
"description": "Room to reserve for the answer per chunk."
},
"system_prompt_tokens": {
"type": "integer",
"minimum": 0,
"default": 500,
"description": "Room to reserve for the system prompt per chunk."
},
"overlap_tokens": {
"type": "integer",
"minimum": 0,
"maximum": 20000,
"default": 0,
"description": "Tokens of the previous chunk repeated at the start of the next."
},
"safety_margin": {
"type": "number",
"minimum": 0,
"maximum": 0.5,
"default": 0.1,
"description": "Fraction of the window held back against estimation error. 0.1 = 10 percent."
},
"boundary": {
"type": "string",
"enum": [
"absatz",
"zeile",
"satz",
"auto"
],
"default": "auto",
"description": "Where to cut. auto tries paragraph, then line, then sentence."
}
}
}Veröffentlichtes Eingabebeispiel
{
"text": "First section with the customer requirements.\n\nSecond section with implementation constraints and acceptance criteria.",
"model": "gpt-5-mini",
"expected_output_tokens": 800,
"boundary": "auto"
}Ergebnis & Dokumentation
Veröffentlichtes Ergebnisschema anzeigen
{
"$ref": "https://modell.halowerk.com/v1/context-plan/schema#/outputSchema"
}Veröffentlichtes Ergebnisbeispiel öffnen
Maschinenlesbare Dokumentation dieses Hubs
Quelle dieser Seite: der veröffentlichte HALOWERK-Katalog. Stand: 2026-11-01, 15:19 UTC.
Weitere Endpunkte dieses Hubs
- Modellwerk0,003 USDC
chat completions
POSThttps://modell.halowerk.com/v1/chat-completionsRuns openai/gpt-oss-20b via GroqCloud. Messages are sent to Groq Inc., USA; payment metadata is not forwarded. At most 8 messages, 8192 UTF-8 bytes overall and 1024 completion tokens including reasoning. A length finish_reason exposes trunc
- Modellwerk0,002 USDC
cost estimate
POSThttps://modell.halowerk.com/v1/cost-estimateWorks out what a call would cost. Give either the text itself or a token count, plus the expected output length, and get input, output, cache-read and cache-write cost per model with the total. Token counts derived from text are estimates f
- Modellwerk0,003 USDC
document rerank
POSThttps://modell.halowerk.com/v1/document-rerankEmbeds a query and at most 20 short documents on local nomic-embed-text, then sorts by cosine similarity with stable input-index tie breaks. Scores are not probabilities. No third-party text transfer; input is not silently truncated.