{"service":"HALOWERK modellwerk","endpoint":"/v1/llm-catalog","method":"POST","content_type":"application/json","inputSchema":{"type":"object","additionalProperties":false,"properties":{"vendor":{"type":"string","maxLength":64,"description":"Only models from this vendor, e.g. anthropic, openai, google."},"max_input_price":{"type":"number","minimum":0,"description":"Only models at or below this input price per million tokens."},"max_output_price":{"type":"number","minimum":0,"description":"Only models at or below this output price per million tokens."},"min_context":{"type":"integer","minimum":0,"description":"Only models whose context window is at least this many tokens."},"min_output":{"type":"integer","minimum":0,"description":"Only models able to emit at least this many output tokens."},"tag":{"type":"string","maxLength":40,"description":"Only models carrying this capability tag, e.g. coding, speed, reasoning, cheap."},"sort":{"type":"string","enum":["input_price","output_price","context","vendor"],"default":"output_price","description":"Sort order."}}},"requestExample":{"sort":"output_price"},"operations":[{"method":"POST","inputSchema":{"type":"object","additionalProperties":false,"properties":{"vendor":{"type":"string","maxLength":64,"description":"Only models from this vendor, e.g. anthropic, openai, google."},"max_input_price":{"type":"number","minimum":0,"description":"Only models at or below this input price per million tokens."},"max_output_price":{"type":"number","minimum":0,"description":"Only models at or below this output price per million tokens."},"min_context":{"type":"integer","minimum":0,"description":"Only models whose context window is at least this many tokens."},"min_output":{"type":"integer","minimum":0,"description":"Only models able to emit at least this many output tokens."},"tag":{"type":"string","maxLength":40,"description":"Only models carrying this capability tag, e.g. coding, speed, reasoning, cheap."},"sort":{"type":"string","enum":["input_price","output_price","context","vendor"],"default":"output_price","description":"Sort order."}}},"requestExample":{"sort":"output_price"}}],"example_request":{"sort":"output_price"},"serviceName":"llm_catalog","tags":["llm","catalog","pricing"],"outputSchema":{"type":"object"},"outputExample":{"models":[{"model":"gpt-5-mini","vendor":"openai","family":"gpt","prices_per_mtok_usd":{"input":0.25,"output":2,"cache_read":0.025,"cache_write":null},"blended_price_3to1_usd":0.6875,"context_window":400000,"max_output":128000,"batch_discount":0.5,"strengths":["speed","cheap"],"note":null,"price_table_date":"2026-05-01"},{"model":"gemini-2.5-flash","vendor":"google","family":"gemini","prices_per_mtok_usd":{"input":0.3,"output":2.5,"cache_read":0.075,"cache_write":null},"blended_price_3to1_usd":0.85,"context_window":1048576,"max_output":65536,"batch_discount":0.5,"strengths":["speed","cheap","long-context"],"note":null,"price_table_date":"2026-05-01"},{"model":"claude-haiku-4-5","vendor":"anthropic","family":"haiku","prices_per_mtok_usd":{"input":1,"output":5,"cache_read":0.1,"cache_write":1.25},"blended_price_3to1_usd":2,"context_window":200000,"max_output":64000,"batch_discount":0.5,"strengths":["speed","classification","cheap"],"note":"Kleinstes Kontextfenster der Reihe.","price_table_date":"2026-06-24"},{"model":"gpt-5","vendor":"openai","family":"gpt","prices_per_mtok_usd":{"input":1.25,"output":10,"cache_read":0.125,"cache_write":null},"blended_price_3to1_usd":3.4375,"context_window":400000,"max_output":128000,"batch_discount":0.5,"strengths":["reasoning","coding"],"note":null,"price_table_date":"2026-05-01"},{"model":"gemini-2.5-pro","vendor":"google","family":"gemini","prices_per_mtok_usd":{"input":1.25,"output":10,"cache_read":0.31,"cache_write":null},"blended_price_3to1_usd":3.4375,"context_window":1048576,"max_output":65536,"batch_discount":0.5,"strengths":["long-context","multimodal"],"note":"Preis steigt oberhalb von 200.000 Token Eingabe.","price_table_date":"2026-05-01"},{"model":"claude-sonnet-5","vendor":"anthropic","family":"sonnet","prices_per_mtok_usd":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"blended_price_3to1_usd":6,"context_window":1000000,"max_output":128000,"batch_discount":0.5,"strengths":["coding","agents","balanced"],"note":"Einfuehrungspreis 2.00/10.00 bis 31.08.2026.","price_table_date":"2026-06-24"},{"model":"claude-sonnet-4-6","vendor":"anthropic","family":"sonnet","prices_per_mtok_usd":{"input":3,"output":15,"cache_read":0.3,"cache_write":3.75},"blended_price_3to1_usd":6,"context_window":1000000,"max_output":128000,"batch_discount":0.5,"strengths":["coding","balanced"],"note":null,"price_table_date":"2026-06-24"},{"model":"claude-opus-5","vendor":"anthropic","family":"opus","prices_per_mtok_usd":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"blended_price_3to1_usd":10,"context_window":1000000,"max_output":128000,"batch_discount":0.5,"strengths":["coding","agents","reasoning","vision"],"note":"Denken ist voreingestellt an. Abschalten nur bis Aufwandstufe high.","price_table_date":"2026-06-24"},{"model":"claude-opus-4-8","vendor":"anthropic","family":"opus","prices_per_mtok_usd":{"input":5,"output":25,"cache_read":0.5,"cache_write":6.25},"blended_price_3to1_usd":10,"context_window":1000000,"max_output":128000,"batch_discount":0.5,"strengths":["coding","agents","knowledge-work","memory"],"note":null,"price_table_date":"2026-06-24"},{"model":"claude-fable-5","vendor":"anthropic","family":"fable","prices_per_mtok_usd":{"input":10,"output":50,"cache_read":1,"cache_write":12.5},"blended_price_3to1_usd":20,"context_window":1000000,"max_output":128000,"batch_discount":0.5,"strengths":["reasoning","long-horizon-agents","research"],"note":"Denken ist immer an und laesst sich nicht abschalten. Nicht unter Zero-Data-Retention verfuegbar.","price_table_date":"2026-06-24"}],"count":10,"total_in_catalog":10,"filters_applied":["keine"],"sort":"output_price","cheapest_by_output":"gpt-5-mini","largest_context":"gemini-2.5-flash","vendors":["anthropic","openai","google"],"tags":["agents","balanced","cheap","classification","coding","knowledge-work","long-context","long-horizon-agents","memory","multimodal","reasoning","research","speed","vision"],"price_table_dates":["2026-05-01","2026-06-24"],"currency":"USD je 1 Million Token","blended_price_basis":"3 Teile Eingabe zu 1 Teil Ausgabe","limits":"Gepflegte Tabelle mit Stand je Eintrag, kein Live-Abruf. Nur oeffentliche Listenpreise; ausgehandelte Konditionen, Verfuegbarkeit und kontobezogene Ratengrenzen sind nicht abgebildet."}}