Nodes/ComfyUI-M8nodes/M8 · LLM Inference
ComfyUI Node

M8 · LLM Inference

Calls an external LLM over an OpenAI-compatible API: two prompt boxes, model dropdown, thinking effort. Accepts a skill, images and audio; outputs text.

By chenr5934-tech·Created 3 days ago·Updated a day ago· 0
M8 · LLM Inference
  • skill
  • image
  • audio
  • text
◄providerdeepseek►
◄base_urlhttps://api.deepseek.com/v1►
◄api_key►
◄model▾►
◄system_prompt►
◄user_prompt►
◄thinkingoff►
◄show_thinkingfalse►
◄temperature1.00►
◄max_tokens8192►
◄timeout120►
◄skill_autofalse►
◄extra_params►
CategoryM8/LLM

Inputs (16)

NameTypeDefaultDescription
providerCOMBOdeepseekPick a provider. Changing it fills in that provider's default base_url and thinking options. For anything else choose Custom and enter the address yourself.
base_urlSTRINGhttps://api.deepseek.com/v1API address. Defaults to https://api.deepseek.com/v1; point it at any OpenAI-compatible endpoint.
api_keySTRINGLeave empty to use the key stored on the server (recommended: Save key keeps it out of the workflow file). Anything typed here applies to this node only and is written into the workflow.
modelCOMBOFill in the address and key, then click Refresh models. You can also type a model name directly.
system_promptSTRINGSystem prompt: persona, tone, output format. Leave empty to send only the user prompt.
user_promptSTRINGWhat you want to ask. Can be wired from another node's text output (right-click the input and convert it to an input socket).
thinkingCOMBOoffThinking effort. Off sends no extra request; higher asks the model to think more. If the provider rejects the parameter it is dropped and the request retried (the log says so).
show_thinkingBOOLEANfalseShow the model's thinking on the node panel (default off: it is usually long). Display only, the text output is unaffected.
temperatureFLOAT1.000–2Randomness. Lower for steady work like prompt writing, higher for creative ones.
max_tokensINT819216–131072Upper bound on the reply length. It is a cap, not a target — normal answers do not fill it.
timeoutINT1205–3600Request timeout in seconds. For slow thinking models give it 300 or more.
skilloptM8_SKILLWire this from M8 · Skill Loader. Its content is appended after the system prompt as reference material.
skill_autooptBOOLEANfalseInject every uploaded skill and let the model decide which applies. Off by default: once the library grows, each turn carries a few irrelevant ones and burns tokens. Referencing a specific skill with / in the prompt is more precise. Caps are configurable in settings.
imageoptIMAGEFeed images to a vision model. Multiple images are sent together; count and edge limits are configurable. Models without image support return 400.
audiooptAUDIOFeed audio to a model that accepts it (converted to WAV). Models without audio support return 400.
extra_paramsoptSTRINGExtra request parameters as a JSON object, merged into the request body. Use it for provider-specific fields this pack does not cover, e.g. {"top_p": 0.9}.

Outputs (1)

NameTypeDescription
textSTRING—