Model Configuration

This guide explains how Self-Managed Kindo installations define and maintain global models — the system-wide LLMs (and related models like embeddings or transcription) that power workflows, chat, ingestion, and other core experiences.

In a self-managed environment, you add models to Kindo, map them to Unleash feature variants, and keep those mappings up to date when models are replaced.

Deploying model infrastructure?

Before configuring models in Kindo, you need working inference endpoints. See the AI Model Deployment Guide for how to deploy and verify self-hosted models (vLLM, context window sizing, tool-call parsers) or connect cloud API providers.

Unleash Features and Strategy Variants

Each key below is an Unleash feature whose variant payload contains one or more global model IDs. The backend and frontend read these variants to decide which models to use.

Required Features

Feature Key	Description
AUDIO_TRANSCRIPTION	Converts audio to text
CRON_EXPRESSION_GENERATION	Generates cron expressions from natural language schedule descriptions
DEFAULT_WORKFLOW_STEP_MODEL	Default model for workflow step execution
EMBEDDING_MODELS	Models for generating text embeddings
INGESTION_WORKERS	Models for data ingestion and extraction
INTERNAL_AUTO_GENERATION	Internal model for automatic content generation
INTERNAL_LARGE_WORKER	High-capacity internal worker for complex tasks
INTERNAL_SMALL_WORKER	Lightweight internal worker for simple tasks
LOCAL_STORAGE_CHAT_MODELS	Default chat model for the model dropdown
GENERAL_PURPOSE_MODELS	Versatile models for selection categories and “Recommend Model”
LONG_CONTEXT_MODELS	Models optimized for long context windows

Optional Features

Feature Key	Description	Notes
API_STEP_GENERATION	Models for generating API steps in workflows
DYNAMIC_API_REQUEST_PARSER	Parses dynamic API requests
SLACK_MESSAGE_GENERATION	Generates Slack messages	Only if Slack integration is enabled
AGENT_MODEL	Models for ReAct-Agent interactions
STREAMING_UNSUPPORTED_MODELS	Models without streaming support	Used for UI loading states
GEMINI_CHAT_MODELS	Google Gemini models	Only if multimodal chat is enabled

Conditional Features

Feature Key	Description	Notes
REASONING_MODELS	Models for complex reasoning	Required only if OpenAI o-series models exist
CYBERSECURITY_MODELS	Models for cybersecurity analysis	Required only if DeepHat is available

Minimum Model Requirements

Self-Managed Kindo needs baseline global models to function. Without them, core flows like chat, workflow execution, ingestion, and indexing will fail.

Absolute Minimum Set

Model Type	Purpose	Recommendations
Embedding model	Semantic search, retrieval, and indexing	Open source: BAAI/bge-m3. Hosted: Gemini embedding
Strong/large model	Complex reasoning, workflow execution, long-form generation	Open source: gpt-oss 120B. Hosted: Gemini 2.5 Pro, Claude 4.5, GPT 5.2
Audio transcription	Audio file processing, voice notes, transcription workflows	Open source: Faster Whisper. Hosted: Deepgram

Recommended Additional Models

• Small model (title generation, quick summaries, low-latency steps): Gemma 3 or Llama 3.2 7B
• Security-focused: DeepHat 32B
• Multimodal: Gemini 2.5 Pro (image + text)

Managing Models

Overview of Steps

1. Add the new model via the API.
2. Update Unleash variants to reference the new model IDs.
3. Delete the old model with replacement.

Caution

If the model you are deleting is still referenced by Unleash, the response will list the feature flags that need updates. Update those variants first, then retry the delete.

Add a Global Model

curl -X POST <API_URL>/internal/openapi/admin/model/new \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer <UM_INTERNAL_API_KEY>' \
  -d '{
    "orgId": "<YOUR_ORG_ID>",
    "userId": "<YOUR_USER_ID>",
    "displayName": "Model Display Name",
    "modelProviderDisplayName": "Provider Name",
    "type": "CHAT",
    "contextWindow": 200000,
    "metadata": {
      "type": "Text Generation",
      "costTier": "HIGH",
      "usageTag": "Chat + Agents",
      "description": "Model description",
      "modelCreator": "Provider Name"
    },
    "litellmModelName": "model-name",
    "litellmParams": {
      "model": "provider/model-name",
      "api_key": "<API_KEY>",
      "max_output_tokens": 64000
    }
  }'

Note

Ensure modelProviderDisplayName matches the display name in the ModelProvider table. Otherwise, a new ModelProvider record will be created. Also verify that LiteLLM params are correct for the specific model, as defaults vary by provider.

Delete with Replacement

curl -X POST <API_URL>/internal/openapi/admin/model/delete-with-replacement \
  -H 'Content-Type: application/json' \
  -H 'Authorization: Bearer <UM_INTERNAL_API_KEY>' \
  -d '{
    "deletingModelId": "<OLD_MODEL_ID>",
    "replacementModelId": "<NEW_MODEL_ID>",
    "orgId": "<YOUR_ORG_ID>",
    "userId": "<YOUR_USER_ID>"
  }'

Update Parameters on an Existing Model

To modify LiteLLM parameters for an existing model, update the LiteLLM database directly:

UPDATE "public"."LiteLLM_ProxyModelTable"
SET "litellm_params" = jsonb_set(
  "litellm_params",
  '{max_tokens}',
  '64000'::jsonb
)
WHERE "model_name" = 'your-model-name';

Tip

When adding models to dev/prod, be mindful of which region you are using to manage quota efficiently. Separate dev and prod to avoid rate-limit outages during local testing.