AI Models

AI Models (LLM Providers) are the language model connections that power agent pipelines and LLM tools. almyty supports OpenAI, Anthropic, and any OpenAI-compatible API endpoint.

Adding a Provider

Via the UI

Navigate to AI Models in the sidebar
Click Add Provider
Select the provider type (OpenAI, Anthropic, or Custom)
Enter your API key and optional configuration
Click Test Connection to verify

Via the API

curl -X POST https://api.almyty.com/llm-providers \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "OpenAI Production",
    "provider": "openai",
    "apiKey": "sk-...",
    "model": "gpt-4o"
  }'

Provider Types

OpenAI

Works with OpenAI's API and any OpenAI-compatible endpoint (Azure OpenAI, Together AI, Groq, Ollama, vLLM, etc.).

Field	Description
`apiKey`	OpenAI API key
`model`	Default model (gpt-4o, gpt-4o-mini, o1, etc.)
`baseUrl`	Override for compatible APIs (default: `https://api.openai.com/v1`)

Anthropic

Direct integration with Anthropic's API.

Field	Description
`apiKey`	Anthropic API key
`model`	Default model (claude-opus-4-6, claude-sonnet-4-6, etc.)

Custom

Any OpenAI-compatible HTTP endpoint. Set baseUrl to your endpoint and apiKey to whatever token your server expects.

Configuration

Each provider has default parameters that can be overridden per-agent or per-tool:

Parameter	Type	Default	Description
`temperature`	number	0.7	Sampling temperature (0-2)
`maxTokens`	number	4096	Maximum response tokens
`topP`	number	1.0	Nucleus sampling

Testing

Test a provider connection from the UI or API:

curl -X POST https://api.almyty.com/llm-providers/{id}/test \
  -H "Authorization: Bearer $TOKEN"

Returns the model name, response time, and status.

Chat Sessions

Each provider supports interactive chat sessions with conversation history:

curl -X POST https://api.almyty.com/llm-providers/{id}/chat \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "message": "What can you help me with?",
    "sessionId": "session-uuid"
  }'

Sessions are stored server-side and maintain full message history.

Cost Tracking

almyty tracks token usage and estimated cost for every LLM call. View aggregate costs per provider in the Analytics dashboard or on the provider detail page.

Usage in Agents

When building an agent pipeline, LLM Call nodes reference a provider by ID. The provider's default model and parameters are used unless overridden in the node configuration.

See Agents → Node Types for LLM Call node configuration.

Scheduling Organizations