Hub · Agenten & KI

Modellwerk

15 veröffentlichte Endpunkt-URLs. Methoden, Preise, Eingaben und Originaldokumentation auf jeder Detailseite.

modell.halowerk.com · Katalogstand 2026-11-01, 15:19 UTC

Endpunkte

1–15 von 15

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
Modellwerk0,003 USDC
document rerank
POSThttps://modell.halowerk.com/v1/document-rerank
Embeds a query and at most 20 short documents on local nomic-embed-text, then sorts by cosine similarity with stable input-index tie breaks. Scores are not probabilities. No third-party text transfer; input is not silently truncated.
Modellwerk0,003 USDC
drift check
POSThttps://modell.halowerk.com/v1/drift-check
Compares two submitted sample sets feature by feature and returns deterministic drift metrics. Continuous features are binned on the combined value range and receive PSI, Jensen-Shannon divergence and a Kolmogorov-Smirnov statistic; categor
Modellwerk0,005 USDC
llm catalog
POSThttps://modell.halowerk.com/v1/llm-catalog
A comparison table of language models: input, output and cache prices per million tokens, context window, maximum output length, batch discount and a short note on what each is suited to. Filter by vendor, by a maximum price, by the context
Modellwerk0,005 USDC
llm catalog diff
POSThttps://modell.halowerk.com/v1/llm-catalog-diff
Use this when an agent has an older and a newer LLM catalog snapshot and needs a deterministic migration diff before changing routing or budgets. Rows are matched by vendor plus model, id or name. The result separates added, removed and cha
Modellwerk0,002 USDC
model router
POSThttps://modell.halowerk.com/v1/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 est
Modellwerk0,002 USDC
openapi to mcp
POSThttps://modell.halowerk.com/v1/openapi-to-mcp
Converts each OpenAPI operation into an MCP tool. Path, query and header parameters and the JSON request body are merged into one input schema, because MCP tools take exactly one; a name collision between a body field and a parameter is rep
Modellwerk0,002 USDC
openapi validate
POSThttps://modell.halowerk.com/v1/openapi-validate
Reads an OpenAPI 3.x document and reports what would stop a machine consumer. Errors: missing openapi, info or paths; a path that declares no method; an internal $ref that resolves to nothing; a parameter without a name, location or schema;
Modellwerk0,002 USDC
output validate
POSThttps://modell.halowerk.com/v1/output-validate
Validates output against a JSON Schema and reports each violation with its JSON path, the rule it broke and a sentence saying what to change. Accepts either a parsed object or the raw string a model returned: a payload wrapped in a code fen
Modellwerk0,003 USDC
text embeddings
POSThttps://modell.halowerk.com/v1/text-embeddings
Runs nomic-embed-text locally through Ollama and returns 768-dimensional embeddings. No third-party text transfer. Input is rejected rather than silently truncated; at most four 1000-character strings per request.
Modellwerk0,002 USDC
tool arg validate
POSThttps://modell.halowerk.com/v1/tool-arg-validate
Two checks in one. First the arguments are validated against the tool input schema and every violation is reported with its path and a sentence saying what to change. Second, values that satisfy the schema but look wrong are flagged: an uns
Modellwerk0,002 USDC
tool compat
POSThttps://modell.halowerk.com/v1/tool-compat
Compares a producer output schema against a consumer input schema and reports whether the two can be chained. Every required field of the consumer is looked for in the producer: exact name matches first, then well-known synonyms (url/uri/li
Modellwerk0,002 USDC
trace grade
POSThttps://modell.halowerk.com/v1/trace-grade
Takes the steps of one agent run and returns a scored report. It counts identical tool calls (same tool, same arguments) as loops, finds the longest run of consecutive failures, marks calls whose result was empty or null as wasted, and attr