Double-blind comparison of AI model responses — query models in parallel, judge anonymized outputs, rank on merit. Trigger with "mdls" or "modelshow".
编程
RunAPI Model Explorer
试用Use when the user asks what RunAPI models are available, compares models, needs pricing, asks for required fields, searches by modality, or wants a recommend...
它能做什么
Use when the user asks what RunAPI models are available, compares models, needs pricing, asks for required fields, searches by modality, or wants a recommendation. Triggers include "what models", "compare models", "cheapest", "pricing", "required params", "有哪些模型", "比较模型", and "价格".
技能文档
RunAPI Model Explorer
Use RunAPI catalog and pricing tools for discovery.
Workflow
- Call
mcp__runapi__list_modelswith modality, service, or action filters when possible. - For a specific model, call
mcp__runapi__get_model_info; when service/action are known, include them to get the exact endpoint constraints. - For cost questions, call
mcp__runapi__check_pricing. - Summarize as a compact table.
- End with one recommended service/action/model triple when the user wants to generate.
Rules
- Do not quote stale prices.
- Do not mention hidden infrastructure providers.
- Do not overwhelm the user with the whole catalog unless they ask.
- Keep model slugs exactly as returned by tools.
相关技能
Compare multiple LLM models (GPT-5, Claude Sonnet 4.5, Gemini 3, DeepSeek v4-pro, Grok 4, etc.) side-by-side in one parallel request via OATDA's unified AI g...
Call the Qwen text API (qwen3-next-80b-a3b-instruct) through RunAPI using the official OpenAI SDK or compatible clients. Use when the user asks for Qwen text...
Use when the user asks to generate an image, create a video, make music, create audio, synthesize speech, submit a media task, poll a task, or produce genera...
Pick the right Runware model for a task and keep that choice current. Use when an agent needs to decide "which model for X", discover what's available, or ch...
Call the DeepSeek API (deepseek-v4-pro, deepseek-v4-flash, and deepseek-v4-flash-vision-exp) through RunAPI using OpenAI-compatible Chat Completions and Responses. Use for DeepSeek text, image input, streaming, the verified Flash function path, or an existing compatibility client that needs the conditional reference.