ComfyUI Node
NS LLM Chat
A ComfyUI node in neuralsins/LLM with 10 inputs and 1 output.
NS LLM Chat
- image
- response
◄api_key—►
◄modelclaude-opus-5►
◄prompt—►
◄max_tokens4096►
◄temperature0.70►
◄seed1►
◄timeout500►
◄model_override—►
◄system_prompt►
Categoryneuralsins/LLM
Inputs (10)
| Name | Type | Default | Description |
|---|---|---|---|
| api_key | STRING | — | |
| model | COMBO | claude-opus-5 | 11 options: claude-fable-5, claude-opus-5, claude-sonnet-5, claude-haiku-4-5, gemini-3.1-pro-preview, gemini-3.5-flash, +5 |
| prompt | STRING | — | |
| max_tokens | INT | 40961–200000 | — |
| temperature | FLOAT | 0.700–2 | — |
| seed | INT | 1-1–18446744073709550000 | Random seed for reproducible results. -1 for random seed. Note: Works with Gemini, Grok, and OpenAI models. Claude doesn't support seeds. |
| timeout | INT | 50010–3600 | Request timeout in seconds. Increase for large text processing (default: 500s) |
| model_overrideopt | STRING | Connect an NS LLM Model Selector to control the model from a single node. | |
| system_promptopt | STRING | — | |
| imageopt | IMAGE | — |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| response | STRING | — |