Modellwerk
vocabulary bpe merge rank audit
Replay ranked symbolic byte-pair merges and return their deterministic application trace.
POST https://modell.halowerk.com/v1/vocabulary-bpe-merge-rank-auditInputs
| Field | Type | Required | Description |
|---|---|---|---|
| symbols | array | Yes | |
| merges | array | Yes |
Show full input schema
{
"type": "object",
"properties": {
"symbols": {
"type": "array",
"items": {
"$ref": "#/$defs/s0"
},
"maxItems": 128,
"minItems": 1
},
"merges": {
"type": "array",
"items": {
"type": "object",
"properties": {
"left": {
"$ref": "#/$defs/s0"
},
"right": {
"$ref": "#/$defs/s0"
},
"merged": {
"$ref": "#/$defs/s0"
},
"rank": {
"type": "integer",
"minimum": 0,
"maximum": 10000
}
},
"required": [
"left",
"right",
"merged",
"rank"
],
"additionalProperties": false
},
"maxItems": 200,
"minItems": 0
}
},
"required": [
"symbols",
"merges"
],
"additionalProperties": false,
"$id": "urn:h:w5:E8:input",
"$defs": {
"s0": {
"type": "string",
"maxLength": 64,
"minLength": 1
}
}
}Published input example
{
"symbols": [
"a",
"b",
"a",
"b"
],
"merges": [
{
"left": "a",
"right": "b",
"merged": "ab",
"rank": 0
},
{
"left": "ab",
"right": "ab",
"merged": "abab",
"rank": 1
}
]
}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