n8n Moonshot Kimi Chat Model nodeConfigure Moonshot Kimi Chat Model in n8n.
The n8n Moonshot Kimi Chat Model node is the brain you clip onto an AI chain, not a step that runs alone. It sends chat requests to the Kimi chat API and hands the answer back to the root node it feeds. Nine parameters cover model choice, sampling, response format and network behavior.
Verified Trustpilot reviews · AI, automation & growth agency
What does the n8n Moonshot Kimi Chat Model node do?
The Moonshot Kimi Chat Model node sends a chat request to the Kimi model you select and returns the generated response to the node it is attached to. It is a sub-node, meaning a small node that clips onto a port of a bigger one instead of sitting in the main flow. A port is the labeled connector under a root node, and this one connects to the model port. On its own it does nothing at all.
Reach for it when a workflow already has a root node waiting for a model. An AI Agent that answers support questions needs a chat model before it will even run, and this node fills that slot with a Kimi model. Swap the Model value, keep everything else, and the rest of the agent stays untouched.
A second pattern is structured extraction. Set Response Format to json_object, feed the chain a raw email body, and the model answers with valid JSON that a later node can read field by field before writing a row to Google Sheets. Without that option you get prose, and the parsing step downstream becomes guesswork.
Third, content drafting at a controlled temperature. A summarization chain that condenses Slack threads reads better with Sampling Temperature pulled down toward zero, because the wording stops drifting between runs. Marketing copy goes the other way. The template that publishes science newsletter posts from YouTube (workflow 16586) puts this node alongside other chat models in the same graph, which is the normal way to compare setups.
When to pick something else: if the workflow needs a model from another provider, the matching sub-node exists already, such as the ones for OpenAI, Anthropic or Google Gemini. Nothing here calls a Kimi endpoint that is not the chat API, so a non-chat capability belongs in a generic HTTP call, not in this node.
Known limits are worth stating plainly. The node exposes nine parameters and nothing more, so anything the Kimi chat API supports outside that list is out of reach. Token ceilings depend on the model you select, not on n8n. The page describes version 1 of the node, and an older workflow may show fewer options. Moonshot bills its own API calls under its own terms; n8n adds nothing to that.
What do you need before the node will run?
- 01
Add the node under a root node
Open the workflow, select a root node that accepts a model, and use its model port to add the Moonshot Kimi Chat Model node. The node has no main input, so dropping it on the canvas by itself leaves it unconnected and it will never execute. n8n draws the link from the port to the sub-node, and that link is what tells the chain which model to call at run time.
- 02
Create the Moonshot credential
Open the node's credential field and create a new credential with your Moonshot API key, taken from your Moonshot account. A credential in n8n is a saved set of secrets stored apart from the workflow, so the key never sits in the node itself. Create it once from the Credentials menu and every other workflow on the instance can select the same entry instead of repeating the key.
- 03
Or switch to Gateway credits on n8n Cloud
On n8n Cloud the credential field offers Use Gateway credits. Pick it and the node runs without a Moonshot account and without your own API key, which is the quickest way to test a chain before committing to a provider account. On a self-hosted instance that choice is not offered, so the API key route above is the one to follow.
Where does this node plug in?
n8n splits AI work between root nodes, which sit in the main flow and receive items, and sub-nodes, which hang off their ports and only run when the root node asks. This node is a sub-node with a single output port.
Output (what it plugs into)
- Model
ai_languageModel
01Model
This is the only connector the node offers. The root node above it decides when a request goes out and what happens to the answer.
Key parameters
- Required: a root node that accepts a model port, since the node has no main input of its own.
- AI Agent and Basic LLM Chain: the two usual starting points, one for tool-driven reasoning, the other for a single prompt and answer.
- Information Extractor and Text Classifier: pick these when the goal is a field or a label rather than a conversation.
Which parameters matter, and when?
The Moonshot Kimi Chat Model node has 9 parameters. For each one: the node as you configure it in n8n, what the parameter changes, and our field notes.
Model
modelWhat you see in n8n
Notes & use cases
Picks the Kimi model that generates the completion. It is the first thing to set, because every other parameter behaves relative to the model you choose.
Key parameters
- Model: a dropdown of Kimi models, defaulting to
kimi-k2.5. The token ceiling that applies later comes from this choice.
Frequency Penalty
options.frequencyPenaltyWhat you see in n8n
Notes & use cases
Positive values penalize tokens the model has already used often, which makes it less likely to repeat the same line word for word. A token is the chunk of text a model reads and writes, roughly a short word or a fragment of one.
Key parameters
- Frequency Penalty: a number,
0by default, meaning no penalty at all.
Maximum Number of Tokens
options.maxTokensWhat you see in n8n
Notes & use cases
Caps how much text the completion can contain. The real ceiling still depends on the model selected above, so this is a budget you impose, not one you can raise past the model.
Key parameters
- Maximum Number of Tokens: a number, default
-1, which hands the decision back to the model default.
Response Format
options.responseFormatWhat you see in n8n
Notes & use cases
Decides the shape of what comes back. Regular prose suits anything a human reads next; JSON mode suits anything a node parses.
Key parameters
- Text (
text): the default, a regular text response. - JSON (
json_object): enables JSON mode, which should guarantee the generated message is valid JSON.
{{ $json.output }} and expects named fields rather than a paragraph to unpick by hand.Presence Penalty
options.presencePenaltyWhat you see in n8n
Notes & use cases
Pushes the model toward new topics by penalizing any token that has already shown up, no matter how many times it did.
Key parameters
- Presence Penalty: a number, default
0. It reacts to whether a token showed up, where Frequency Penalty reacts to how many times.
Sampling Temperature
options.temperatureWhat you see in n8n
Notes & use cases
Controls randomness. Lower values give less random completions, and as the value approaches zero the model turns deterministic and repetitive.
Key parameters
- Sampling Temperature: a number, default
0.7, which leaves noticeable variation between two runs on the same prompt.
Timeout
options.timeoutWhat you see in n8n
Notes & use cases
Sets how long a single request may take before n8n gives up on it, counted in milliseconds.
Key parameters
- Timeout: a number, default
360000milliseconds, which is six minutes.
Max Retries
options.maxRetriesWhat you see in n8n
Notes & use cases
Tells the node how many extra attempts to make when a request fails, before the error reaches the root node and stops the chain.
Key parameters
- Max Retries: a number, default two attempts.
Top P
options.topPWhat you see in n8n
Notes & use cases
Controls diversity through nucleus sampling: a value of zero point five means half of the likelihood-weighted options are considered.
Key parameters
- Top P: a number, default
1. The recommendation is to change this or Sampling Temperature, not both.
Need help automating Moonshot Kimi Chat Model with n8n?
A person reads every message.
Questions people ask next
01Is the Moonshot Kimi Chat Model node free in n8n?
02What credentials does the n8n Moonshot Kimi Chat Model node need?
03What are the limits of this node?
04What do you need to connect at minimum, and which root node should a beginner start with?
05n8n or Make for running a Kimi model in an automation?
Get our weekly integration tips.
No spam. Unsubscribe anytime.
