Kimi (Moonshot)
A RocketRide LLM node that connects Moonshot AI's Kimi models to a pipeline through the OpenAI-compatible Moonshot API.
What it does
Provides chat completion using Kimi and Moonshot models as an llm-class invoke filter. It can be wired directly via lanes or consumed by any agent or node that needs an LLM backend.
Built on langchain-openai (ChatOpenAI) pointed at the Moonshot endpoint; the openai SDK is used only for the save-time configuration probe. The request's max_tokens is set from the active profile's output token limit.
Temperature is set automatically per model family: Kimi K2 models run at temperature 1 (the API rejects any other value with "invalid temperature: only 1 is allowed for this model"), while the classic Moonshot v1 models run at temperature 0 for deterministic pipeline output.
When the node configuration is saved, cloud Moonshot endpoints (where serverbase contains api.moonshot) are validated with a minimal 1-token probe request. Failures are surfaced as warnings with the provider's HTTP status, error type, and message. Self-hosted or local OpenAI-compatible endpoints are not validated at save time.
Configuration
Lanes
| Lane in | Lane out | Description |
|---|---|---|
questions | answers | Send a question directly, receive a generated answer |
Fields
The UI exposes a single Model profile selector; the remaining values are filled in by the selected profile.
| Field | Type | Description |
|---|---|---|
model | string | Kimi (Moonshot) model |
profile | string | Default "kimi-k2-6". Kimi (Moonshot) LLM model |
Profiles
Each profile pre-sets the model name, context window, and output token limit:
| Profile | Model | Context (total tokens) | Max output tokens |
|---|---|---|---|
| Kimi K2.6 (default) | kimi-k2.6 | 262,144 (256K) | 16,384 |
| Kimi K2.5 | kimi-k2.5 | 262,144 (256K) | 16,384 |
| Moonshot v1 8K | moonshot-v1-8k | 8,192 | 4,096 |
| Moonshot v1 32K | moonshot-v1-32k | 32,768 | 4,096 |
| Moonshot v1 128K | moonshot-v1-128k | 131,072 (128K) | 4,096 |
Moonshot also publishes moonshot-v1-{8k,32k,128k}-vision-preview image-input models. Those belong in a dedicated vision node (see the llm_vision_* family) and are not available in this text-only node.
Authentication
Cloud Moonshot endpoints require an API key starting with sk-. Any other format is rejected at startup with a key-format error. Keys are issued at the Moonshot AI platform.
If no API key is configured (typical for self-hosted OpenAI-compatible endpoints), a placeholder key (sk-local-dummy-key) is sent instead because the OpenAI client requires a non-empty value.
Schema
| Field | Type | Description | Default |
|---|---|---|---|
kimi.profile | string | Model Kimi (Moonshot) LLM model | "kimi-k2-6" |
model | string | Model Kimi (Moonshot) model |
Dependencies
openailangchain-openailangchain-corelangchain