Modellwerk
tensor kv cache slot occupancy
Return physical KV-block sharing and unused token slots from a supplied sequence-to-block assignment.
POST https://modell.halowerk.com/v1/tensor-kv-cache-slot-occupancyInputs
| Field | Type | Required | Description |
|---|---|---|---|
| block_tokens | integer | Yes | |
| capacity_blocks | integer | Yes | |
| sequences | array | Yes |
Show full input schema
{
"type": "object",
"properties": {
"block_tokens": {
"type": "integer",
"minimum": 1,
"maximum": 1024
},
"capacity_blocks": {
"type": "integer",
"minimum": 1,
"maximum": 1000000
},
"sequences": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"maxLength": 64,
"minLength": 1
},
"tokens": {
"type": "integer",
"minimum": 0,
"maximum": 1000000
},
"blocks": {
"type": "array",
"items": {
"type": "integer",
"minimum": 0,
"maximum": 1000000
},
"maxItems": 1000,
"minItems": 0
}
},
"required": [
"id",
"tokens",
"blocks"
],
"additionalProperties": false
},
"maxItems": 100,
"minItems": 0
}
},
"required": [
"block_tokens",
"capacity_blocks",
"sequences"
],
"additionalProperties": false
}Published input example
{
"block_tokens": 4,
"capacity_blocks": 10,
"sequences": [
{
"id": "seq_A",
"tokens": 5,
"blocks": [
0,
1
]
},
{
"id": "seq_B",
"tokens": 4,
"blocks": [
0
]
}
]
}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