Language Model Access
layout strided address aliases
Return element addresses and overlapping logical indexes for a supplied strided tensor view.
POST https://modell.halowerk.com/v1/layout-strided-address-aliasesInputs
| Field | Type | Required | Description |
|---|---|---|---|
| shape | array | Yes | |
| strides | array | Yes | |
| offset | integer | Yes | |
| buffer_elements | integer | Yes |
Show full input schema
{
"type": "object",
"properties": {
"shape": {
"type": "array",
"items": {
"type": "integer",
"minimum": 1,
"maximum": 1000000
},
"maxItems": 6,
"minItems": 1
},
"strides": {
"type": "array",
"items": {
"type": "integer",
"minimum": -1000000,
"maximum": 1000000
},
"maxItems": 6,
"minItems": 1
},
"offset": {
"type": "integer",
"minimum": 0,
"maximum": 1000000
},
"buffer_elements": {
"type": "integer",
"minimum": 1,
"maximum": 1000000
}
},
"required": [
"shape",
"strides",
"offset",
"buffer_elements"
],
"additionalProperties": false
}Published input example
{
"shape": [
2,
2
],
"strides": [
0,
1
],
"offset": 0,
"buffer_elements": 2
}Result & documentation
Machine-readable documentation of this hub
Source of this page: the published HALOWERK catalog. Updated: 2026-11-19 UTC.
More endpoints in this hub
- Language Model Access0.003 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
- Language Model Access0.002 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
- Language Model Access0.002 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