ask
Query multiple AI backends with smart routing and automatic fallback chains. Features dynamic token scaling, Unity detection, and response tracking across local, Gemini, DeepSeek, and Qwen models.
Instructions
🤖 MULTI-AI Direct Query - Ask any backend with BLAZING FAST smart fallback chains! Features automatic Unity detection, dynamic token scaling, and response headers with backend tracking.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| enable_chunking | No | Enable automatic request chunking for extremely large generations (fallback if truncated) | |
| force_backend | No | Force specific backend (bypasses smart routing) - use backend keys like "local", "gemini", "nvidia_deepseek", "nvidia_qwen" | |
| max_tokens | No | Maximum response length (auto-calculated if not specified: Unity=16K, Complex=8K, Simple=2K) | |
| model | Yes | AI backend to query: local (Qwen2.5-Coder-7B-Instruct-FP8-Dynamic, 128K+ tokens), gemini (Gemini Enhanced, 32K tokens), deepseek3.1 (NVIDIA DeepSeek V3.1, 8K tokens), qwen3 (NVIDIA Qwen3 Coder 480B, 32K tokens) | |
| prompt | Yes | Your question or prompt (Unity/complex generations automatically get high token limits) | |
| thinking | No | Enable thinking mode for DeepSeek (shows reasoning) |
Input Schema (JSON Schema)
{
"properties": {
"enable_chunking": {
"default": false,
"description": "Enable automatic request chunking for extremely large generations (fallback if truncated)",
"type": "boolean"
},
"force_backend": {
"description": "Force specific backend (bypasses smart routing) - use backend keys like \"local\", \"gemini\", \"nvidia_deepseek\", \"nvidia_qwen\"",
"type": "string"
},
"max_tokens": {
"description": "Maximum response length (auto-calculated if not specified: Unity=16K, Complex=8K, Simple=2K)",
"type": "number"
},
"model": {
"description": "AI backend to query: local (Qwen2.5-Coder-7B-Instruct-FP8-Dynamic, 128K+ tokens), gemini (Gemini Enhanced, 32K tokens), deepseek3.1 (NVIDIA DeepSeek V3.1, 8K tokens), qwen3 (NVIDIA Qwen3 Coder 480B, 32K tokens)",
"enum": [
"local",
"gemini",
"deepseek3.1",
"qwen3"
],
"type": "string"
},
"prompt": {
"description": "Your question or prompt (Unity/complex generations automatically get high token limits)",
"type": "string"
},
"thinking": {
"default": true,
"description": "Enable thinking mode for DeepSeek (shows reasoning)",
"type": "boolean"
}
},
"required": [
"model",
"prompt"
],
"type": "object"
}