Modellwerk

model router

Scores every catalogue model against one task and returns a ranked shortlist. You state the task kind, optionally a per-call budget in USD, how much speed matters, the input size and any vendor restriction; the answer names a model, the estimated cost per call, and the sub-scores it was chosen on, so the ranking can be checked rather than trusted. Models that cannot hold the input are excluded and listed separately with the reason. Weights are yours to set and are echoed back.

POST https://modell.halowerk.com/v1/model-router

Eingaben

Felder des veröffentlichten Eingabeschemas
Feld	Typ	Pflicht	Beschreibung
task	string	Ja	What the model has to do.
budget_usd_per_call	number	Nein	Ceiling per call. Models above it are excluded.
speed_priority	string	Nein	How much latency matters.
input_tokens	integer	Nein	Expected input size in tokens.
input_text	string	Nein	Sample input. Used to estimate input_tokens if that is not given.
output_tokens	integer	Nein	Expected output length. Defaults to a value typical for the task.
allowed_vendors	array	Nein	Restrict to these vendors, e.g. for a data-residency or procurement rule.
excluded_vendors	array	Nein	Exclude these vendors.
require_tags	array	Nein	Capabilities the model must carry, e.g. vision.
weights	object	Nein	Weighting of cost, capability and speed. Normalised to sum 1.

Vollständiges Eingabeschema anzeigen

{
  "type": "object",
  "required": [
    "task"
  ],
  "additionalProperties": false,
  "properties": {
    "task": {
      "type": "string",
      "enum": [
        "classification",
        "extraction",
        "summarization",
        "translation",
        "chat",
        "coding",
        "agent",
        "reasoning",
        "research",
        "vision",
        "long_context"
      ],
      "description": "What the model has to do."
    },
    "budget_usd_per_call": {
      "type": "number",
      "minimum": 0,
      "description": "Ceiling per call. Models above it are excluded."
    },
    "speed_priority": {
      "type": "string",
      "enum": [
        "low",
        "normal",
        "high"
      ],
      "default": "normal",
      "description": "How much latency matters."
    },
    "input_tokens": {
      "type": "integer",
      "minimum": 0,
      "default": 2000,
      "description": "Expected input size in tokens."
    },
    "input_text": {
      "type": "string",
      "maxLength": 100000,
      "description": "Sample input. Used to estimate input_tokens if that is not given."
    },
    "output_tokens": {
      "type": "integer",
      "minimum": 0,
      "description": "Expected output length. Defaults to a value typical for the task."
    },
    "allowed_vendors": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Restrict to these vendors, e.g. for a data-residency or procurement rule."
    },
    "excluded_vendors": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Exclude these vendors."
    },
    "require_tags": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Capabilities the model must carry, e.g. vision."
    },
    "weights": {
      "type": "object",
      "additionalProperties": false,
      "description": "Weighting of cost, capability and speed. Normalised to sum 1.",
      "properties": {
        "cost": {
          "type": "number",
          "minimum": 0,
          "default": 0.4
        },
        "capability": {
          "type": "number",
          "minimum": 0,
          "default": 0.4
        },
        "speed": {
          "type": "number",
          "minimum": 0,
          "default": 0.2
        }
      }
    }
  }
}

Originalschema öffnen

Veröffentlichtes Eingabebeispiel

{
  "task": "classification",
  "speed_priority": "normal",
  "input_tokens": 2000
}

Ergebnis & Dokumentation

Veröffentlichtes Ergebnisschema anzeigen

{
  "$ref": "https://modell.halowerk.com/v1/model-router/schema#/outputSchema"
}

Veröffentlichtes Ergebnisbeispiel öffnen

Maschinenlesbare Dokumentation dieses Hubs

Quelle dieser Seite: der veröffentlichte HALOWERK-Katalog. Stand: 2026-11-01, 20:49 UTC.

Weitere Endpunkte dieses Hubs

Modellwerk0,003 USDC
chat completions
POSThttps://modell.halowerk.com/v1/chat-completions
Runs 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-plan
Plans 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-estimate
Works 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

Alle Endpunkte dieses Hubs →

model router

Eingaben

Veröffentlichtes Eingabebeispiel

Ergebnis & Dokumentation

Weitere Endpunkte dieses Hubs

chat completions

context plan

cost estimate