ComfyUI Node
arkennemasis Replicate LLM (OpenAI GPT-5)
Call an OpenAI GPT-5 family model hosted on Replicate and return its text output.
arkennemasis Replicate LLM (OpenAI GPT-5)
- image_1
- image_2
- image_3
- image_4
- text
◄model▾►
◄prompt►
◄system_prompt►
◄reasoning_effort▾►
◄verbosity▾►
◄max_completion_tokens0►
◄api_token►
◄timeout_seconds0►
◄force_rerunfalse►
◄run_mode▾►
◄max_concurrent2►
Categoryarkennemasis/LLM
Inputs (15)
| Name | Type | Default | Description |
|---|---|---|---|
| model | COMBO | 11 options: openai/gpt-5, openai/gpt-5-mini, openai/gpt-5-nano, openai/gpt-5-pro, openai/gpt-5-structured, openai/gpt-5.1, +5 | |
| prompt | STRING | — | |
| system_promptopt | STRING | System instructions. Type here, or wire in a 'System Instructions' node. | |
| image_1opt | IMAGE | Optional image for vision. Can be a batch. | |
| image_2opt | IMAGE | — | |
| image_3opt | IMAGE | — | |
| image_4opt | IMAGE | — | |
| reasoning_effortopt | COMBO | 5 options: default, minimal, low, medium, high | |
| verbosityopt | COMBO | 4 options: default, low, medium, high | |
| max_completion_tokensopt | INT | 00–128000 | 0 = model default. |
| api_tokenopt | STRING | Replicate API token (optional). Blank = use REPLICATE_API_TOKEN from the environment or a .env file. | |
| timeout_secondsopt | INT | 00–86400 | Max seconds to wait for the model. 0 = wait indefinitely. |
| force_rerunopt | BOOLEAN | false | Re-call the API even if inputs are unchanged. |
| run_modeopt | COMBO | ComfyUI runs async nodes concurrently. 'one at a time' serialises every arkennemasis API node in the graph — use it when the provider throttles bursts (Replicate allows a burst of 1 under $5 credit). 'all at once' is faster when your rate limit allows it. | |
| max_concurrentopt | INT | 20–32 | Only used when run_mode is 'all at once': how many arkennemasis API calls may be in flight together. 0 = no cap. 2 is a safe default for a 24-shot batch. |
Outputs (1)
| Name | Type | Description |
|---|---|---|
| text | STRING | — |