--- name: o6htzlrn.nx.link description: This host provides three read-only discovery endpoints for Venice.ai infrastructure: listing available image-generation style presets, retrieving the full model catalog with metadata, and resolving trait-based model aliases to current model identifiers. All three skills are purely informational and return no generated content. host: o6htzlrn.nx.link --- # o6htzlrn.nx.link o6htzlrn.nx.link acts as a Venice.ai metadata layer, serving agents that need to introspect available models, capabilities, and image styles before making downstream inference or image-generation calls. It covers model selection and style enumeration but does not itself perform inference, completions, or image generation. ## When to use this host Use this host when an agent needs to enumerate Venice.ai models, compare their capabilities or pricing, resolve trait-based aliases (e.g., 'which model is default_vision right now?'), or list valid image style presets before calling a generation endpoint. Do not use this host to actually generate text, completions, or images — those require a Venice.ai inference or image-generation endpoint, which is not provided here. If low-latency real-time availability checks are needed, this host is not appropriate as it returns catalog snapshots, not live status. This host has no substitutes for its specific Venice.ai metadata scope; generic LLM provider catalogs (e.g., OpenAI model list endpoints) would be used instead if targeting a different provider. ## Capabilities ### Model Discovery Provides two complementary views of Venice.ai models: a full catalog with specs and pricing, and a trait-to-model-id map for capability-based selection without hardcoding names. - **`fetch-venice-models-catalog`** — Returns the full list of Venice.ai models with metadata including context length, pricing, capabilities, and model type. - **`fetch-model-traits`** — Returns a map of Venice.ai model trait keys (default, most_intelligent, most_uncensored, default_reasoning, default_vision, default_code) to their current model identifiers. ### Image Style Enumeration Returns the current list of valid image-generation style preset names, enabling agents to validate or present style options before invoking a Venice.ai image endpoint. - **`fetch-venice-image-styles`** — Returns the full catalog of available image-generation style presets from Venice.ai as a flat list of style name strings. ## Workflows ### Capability-Aware Model Selection *Use when an agent needs to select the best Venice.ai model for a specific task (e.g., vision, reasoning, code) and also wants to verify full specs or pricing before committing.* 1. **`fetch-model-traits`** — Resolve the relevant trait (e.g., default_vision, default_reasoning) to a current model identifier without hardcoding names. 2. **`fetch-venice-models-catalog`** — Look up the resolved model ID in the full catalog to confirm context length, pricing, and capability flags before invoking it. ## Skill reference ### `fetch-venice-image-styles` **Venice Image Styles** — Returns the full catalog of available image-generation style presets from Venice.ai as a flat list of style name strings. *Use when:* Use when an agent needs to enumerate valid style options before calling a Venice.ai image-generation endpoint, or when a user asks what image styles are available. *Not for:* Do not use to generate images; this endpoint only lists style names. Do not use for model or resolution listings — those require separate endpoints. **Returns:** Returns an object with 'data' (array of ~80 style name strings such as 'Anime', 'Cinematic', 'Pixel Art', 'Watercolor') and 'object' set to 'list'. **Example:** `GET https://o6htzlrn.nx.link/image/styles` --- ### `fetch-venice-models-catalog` **Venice Models Catalog** — Returns the full list of Venice.ai models with metadata including context length, pricing, capabilities, and model type. *Use when:* Use when an agent needs to discover available Venice.ai models, check their capabilities (e.g., vision, function calling, reasoning), compare pricing, or select an appropriate model before making an inference request. *Not for:* Do not use for making inference calls or generating completions; use a Venice.ai chat/completion endpoint instead. Not suitable for real-time model availability checks if low latency is critical. **Returns:** Returns a data array of model objects, each with id, type, context_length, pricing tiers, and a capabilities object detailing supported features such as function calling, reasoning, and vision. **Example:** `GET https://o6htzlrn.nx.link/models` --- ### `fetch-model-traits` **Model Traits Explorer** — Returns a map of Venice.ai model trait keys (default, most_intelligent, most_uncensored, default_reasoning, default_vision, default_code) to their current model identifiers. *Use when:* Use when an agent needs to discover which Venice.ai model to invoke for a specific capability (e.g. reasoning, vision, code generation, or uncensored output) without hardcoding model names. *Not for:* Do not use for listing all available models or their full specs; this only returns trait-to-model-id mappings, not a full model catalog. **Returns:** Returns a data object mapping trait keys (default, most_intelligent, most_uncensored, default_reasoning, default_vision, default_code, function_calling_default) to Venice.ai model ID strings. **Example:** `GET https://o6htzlrn.nx.link/models/traits` ---