x711_llm_routing
ActiveTool of x711 — Universal Agent Gas Station
declared in 1.0.0
Routes a prompt to the best available LLM. Two backends: 1. DEFAULT — Hugging Face (Qwen2.5-7B, free with API key) 2. PREMIUM — OpenVecta (GLM-5.2 and more, set provider:'openvecta') Use ONLY when you need external LLM help. Never for things you can answer from context. Returns: { response: string, model: string, provider: string, tokens_used?: number }
Parameters schema
{
"type": "object",
"required": [],
"properties": {
"model": {
"type": "string",
"description": "Model name. For OpenVecta: 'glm-5.2' (default). For HuggingFace: 'Qwen/Qwen2.5-7B-Instruct' (default). Setting a glm-* model automatically routes to OpenVecta."
},
"query": {
"type": "string",
"description": "Alias for prompt (use either prompt or query)."
},
"prompt": {
"type": "string",
"description": "Complete prompt with all necessary context. The model has no memory of prior tool calls. Max ~4000 tokens recommended."
},
"system": {
"type": "string",
"description": "Optional system prompt injected before the user message."
},
"provider": {
"enum": [
"huggingface",
"openvecta"
],
"type": "string",
"description": "'huggingface' (default, free with key) or 'openvecta' (premium inference via x711 × OpenVecta)."
},
"max_tokens": {
"type": "number",
"description": "Max tokens to generate. Default 512, max 4096. Size to your workload — cost ceiling is based on this value."
},
"temperature": {
"type": "number",
"description": "Sampling temperature 0-2. Default 0.7."
}
}
}Parent server
x711 — Universal Agent Gas Station
1/7 registries