LLM Providers

LLM providers connect Sinas to language model APIs. Supported providers:

Type	Description
`openai`	OpenAI API (GPT-4, GPT-4o, o1, etc.) and OpenAI-compatible endpoints
`anthropic`	Anthropic API (Claude 3, Claude 4, etc.)
`mistral`	Mistral AI (Mistral Large, Pixtral, etc.)
`ollama`	Local models via Ollama

Key properties:

Property	Description
`name`	Unique provider name
`provider_type`	`openai`, `anthropic`, `mistral`, or `ollama`
`api_key`	API key (encrypted at rest, never returned in API responses)
`api_endpoint`	Custom endpoint URL (required for Ollama, useful for proxies)
`default_model`	Model used when agents don’t specify one
`config`	Additional settings (e.g., `max_tokens`, `organization_id`)
`is_default`	Whether this is the system-wide default provider

Provider resolution for agents:

Agent’s explicit llm_provider_id if set
Agent’s model field with the resolved provider
Provider’s default_model
System default provider as final fallback

Endpoints (admin only):

POST   /api/v1/llm-providers             # Create provider
GET    /api/v1/llm-providers             # List providers
GET    /api/v1/llm-providers/{name}      # Get provider
PATCH  /api/v1/llm-providers/{id}        # Update provider
DELETE /api/v1/llm-providers/{id}        # Delete provider

Getting Started

Platform

Build

Storage

Triggers

Configure

Admin

LLM Providers