List every task category this server can route to, with its top models.

Start here when you want to know what the NVIDIA catalog is good for.

List models available on the account, tagged by capability.

Args: category: optional filter, e.g. "code", "vision", "reasoning", "embedding". refresh: bypass the 1-hour catalog cache.

Recommend the best NVIDIA models for a task, without calling them.

Args: task: free-text description of the job, English or Turkish. e.g. "refactor this Python module" / "bu görseldeki tabloyu çıkar". top_k: how many candidate categories to return.

Check that the API key works and report catalog size.

Test which models actually answer on THIS account, and how fast.

Being listed by the catalog endpoint does not mean a model is servable — on a free-tier key a large share return 404. Run this to get ground truth.

Args: category: probe one category only (e.g. "vision"). Empty probes them all. timeout_seconds: per-model deadline.

Call one specific NVIDIA model.

Args: model: exact model id, e.g. "mistralai/codestral-22b-instruct-v0.1". prompt: the user message. system: optional system prompt. images: image URLs or local file paths (vision models only). temperature: 0.0-1.0. max_tokens: response cap.

Pick the best model for the task automatically, then run the prompt on it.

Args: task: what kind of job this is, e.g. "code review", "görsel analizi". prompt: the actual content to send. system: optional system prompt. images: image URLs or local paths (forces a vision model if given). temperature: 0.0-1.0. max_tokens: response cap.

Run one prompt across several models in parallel and return every answer.

Use this to cross-check a hard question, compare model behaviour, or build a quick ensemble. Either pass models explicitly, or pass task to let the router pick the top candidates for you.

Args: prompt: the message every model receives. models: explicit model ids (max 6). Omit to auto-select from task. task: task description used to auto-select models when models is empty. system: optional shared system prompt. images: image URLs or local paths (vision models only). temperature: 0.0-1.0. max_tokens: per-model response cap.

Embed texts. Returns shape and stats; write vectors to disk with save_to.

Args: texts: strings to embed. model: embedding model id. Defaults to the best available one. save_to: optional file path to write the vectors as JSON.

Rank candidate texts by semantic similarity to a query.

Args: query: the search string. candidates: texts to rank. model: embedding model id. Defaults to the best available one.