Any LLM (Vision)
Run any vision-capable LLM: analyze images with GPT, Claude, Gemini, and more
Any LLM (Vision)
Documentation slug: llm--any_llm_vision
Category: llm
Hidden in sidebar: yes (auto-selected by routing)
Description
Run any vision-capable LLM: analyze images with GPT, Claude, Gemini, and more
Pricing
- Cost: ~3 credits per unit
Variant family
- Family: Language models
- Is primary: no
- All variants: Run any LLM, Any LLM (Vision)
Canvas ports
These appear as port handles on the left side of the node.
| ID | Label | Details |
|---|---|---|
prompt |
Prompt | TEXT (required) |
system_prompt |
System Prompt | TEXT · multiline |
frames |
Frames | IMAGE · list |
image1 |
Image 1 | IMAGE |
Sidebar config
These render as form fields in the right-side config panel when the node is selected.
| ID | Label | Details |
|---|---|---|
reasoning |
Reasoning | BOOLEAN |
model |
Model | TEXT (required) · options: google/gemini-3.1-flash-lite, google/gemini-3.1-pro-preview, openai/gpt-4o-2024-11-20, openai/gpt-4.1, openai/gpt-4.1-mini |
max_tokens |
Max Tokens | NUMBER · 1…∞ |
temperature |
Temperature | NUMBER · 0…2 |
Outputs
| ID | Label | Type |
|---|---|---|
text |
Response | TEXT |
Auto-generated from the Wireflow node registry.