Modellwerk
tensor causal attention visibility
Return key-index visibility for supplied causal query positions with an optional sliding window and global prefix.
POST https://modell.halowerk.com/v1/tensor-causal-attention-visibilityInputs
| Field | Type | Required | Description |
|---|---|---|---|
| query_positions | Reference | Yes | |
| key_positions | Reference | Yes | |
| window | integer | Yes | |
| global_prefix | Reference | Yes |
Show full input schema
{
"type": "object",
"properties": {
"query_positions": {
"$ref": "#/$defs/s0"
},
"key_positions": {
"$ref": "#/$defs/s0"
},
"window": {
"type": "integer",
"minimum": 1,
"maximum": 1000000
},
"global_prefix": {
"$ref": "#/$defs/s1"
}
},
"required": [
"query_positions",
"key_positions",
"window",
"global_prefix"
],
"additionalProperties": false,
"$id": "urn:h:w5:E0:input",
"$defs": {
"s0": {
"type": "array",
"items": {
"$ref": "#/$defs/s1"
},
"maxItems": 200,
"minItems": 0
},
"s1": {
"type": "integer",
"minimum": 0,
"maximum": 1000000
}
}
}Published input example
{
"query_positions": [
3
],
"key_positions": [
0,
1,
2,
3,
4
],
"window": 2,
"global_prefix": 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