Modellwerk
tensor lora parameter budget
Count declared low-rank adapter parameters and optimizer-state bytes for supplied linear layers.
POST https://modell.halowerk.com/v1/tensor-lora-parameter-budgetInputs
| Field | Type | Required | Description |
|---|---|---|---|
| layers | array | Yes | |
| copies | integer | Yes | |
| parameter_bytes | integer | Yes | |
| optimizer_bytes | integer | Yes |
Show full input schema
{
"type": "object",
"properties": {
"layers": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"maxLength": 64,
"minLength": 1
},
"input": {
"type": "integer",
"minimum": 1,
"maximum": 1000000
},
"output": {
"type": "integer",
"minimum": 1,
"maximum": 1000000
},
"rank": {
"type": "integer",
"minimum": 1,
"maximum": 4096
}
},
"required": [
"id",
"input",
"output",
"rank"
],
"additionalProperties": false
},
"maxItems": 100,
"minItems": 1
},
"copies": {
"type": "integer",
"minimum": 1,
"maximum": 10000
},
"parameter_bytes": {
"type": "integer",
"minimum": 1,
"maximum": 8
},
"optimizer_bytes": {
"type": "integer",
"minimum": 0,
"maximum": 32
}
},
"required": [
"layers",
"copies",
"parameter_bytes",
"optimizer_bytes"
],
"additionalProperties": false
}Published input example
{
"layers": [
{
"id": "q_proj",
"input": 128,
"output": 64,
"rank": 4
}
],
"copies": 2,
"parameter_bytes": 2,
"optimizer_bytes": 8
}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