Modellwerk
llm pairwise preference cycles
Return directed three-model preference cycles and win totals from supplied pairwise winners. Supplied data only; no model call or provider request.
POST https://modell.halowerk.com/v1/llm-pairwise-preference-cyclesInputs
| Field | Type | Required | Description |
|---|---|---|---|
| comparisons | array | Yes |
Show full input schema
{
"type": "object",
"properties": {
"comparisons": {
"type": "array",
"items": {
"type": "object",
"properties": {
"winner": {
"type": "string",
"maxLength": 80,
"minLength": 1
},
"loser": {
"type": "string",
"maxLength": 80,
"minLength": 1
}
},
"required": [
"winner",
"loser"
],
"additionalProperties": false
},
"maxItems": 100,
"minItems": 1
}
},
"required": [
"comparisons"
],
"additionalProperties": false
}Published input example
{
"comparisons": [
{
"winner": "model-a",
"loser": "model-b"
},
{
"winner": "model-b",
"loser": "model-c"
},
{
"winner": "model-c",
"loser": "model-a"
}
]
}Result & documentation
Machine-readable documentation of this hub
Source of this page: the published HALOWERK catalog. Updated: 2026-11-18 UTC.
More endpoints in this hub
- 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
context plan
POSThttps://modell.halowerk.com/v1/context-planPlans 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
- 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