ComfyUI Node
SF LLM Chat
A ComfyUI node in Stillfront/LLM with 9 inputs and 2 outputs.
SF LLM Chat
- image
- response
- token_usage
◄api_key—►
◄modelclaude-sonnet-4-5►
◄prompt—►
◄max_tokens4096►
◄temperature0.70►
◄seed1►
◄timeout500►
◄system_prompt►
CategoryStillfront/LLM
Inputs (9)
| Name | Type | Default | Description |
|---|---|---|---|
| api_key | STRING | — | |
| model | COMBO | claude-sonnet-4-5 | 11 options: claude-opus-4-5, claude-sonnet-4-5, claude-haiku-4-5, gemini-3-pro-preview, gemini-3-flash-preview, gpt-5.2, +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: Only works with Gemini models, Claude doesn't support seeds. |
| timeout | INT | 50010–3600 | Request timeout in seconds. Increase for large text processing (default: 500s) |
| system_promptopt | STRING | — | |
| imageopt | IMAGE | — |
Outputs (2)
| Name | Type | Description |
|---|---|---|
| response | STRING | — |
| token_usage | STRING | — |