Models & Providers

RightPlace agents support multiple AI providers. You bring your own API keys — configure them in Settings > AI.

Supported Providers

Provider	Example Models	Endpoint
Anthropic	claude-opus-4-6, claude-sonnet-4-6, claude-haiku-4-5	https://api.anthropic.com
OpenAI	gpt-4o, gpt-4-turbo, o1, o3-mini	https://api.openai.com
Google	gemini-2.0-flash, gemini-pro	https://generativelanguage.googleapis.com
Mistral	mistral-large-latest, codestral-latest	https://api.mistral.ai
xAI	grok-2, grok-3	https://api.x.ai
DeepSeek	deepseek-chat, deepseek-reasoner	https://api.deepseek.com
Groq	llama-3.3-70b-versatile	https://api.groq.com/openai
Together	meta-llama/Llama-3-70b-chat-hf	https://api.together.xyz
Cohere	command-r-plus	https://api.cohere.ai
Perplexity	llama-3.1-sonar-large-128k-online	https://api.perplexity.ai

Router APIs

Route requests through a proxy that selects models dynamically:

Router	Description
OpenRouter	Access 100+ models through one API key
LiteLLM	Self-hosted proxy for model routing
Portkey	AI gateway with caching and fallbacks

Router APIs use the OpenAI-compatible format, so any provider that supports the /v1/chat/completions endpoint works.

Setting Up an AI Resource

1. Go to Settings > AI
2. Click Add AI Resource
3. Choose the provider type
4. Enter your API key and endpoint
5. The resource appears in the agent model selector

Model Selection in agent.json

{
  "model": {
    "aiResourceId": "uuid-of-ai-resource",
    "modelId": "claude-sonnet-4-6"
  }
}

• aiResourceId — the UUID of the AI resource you configured in Settings
• modelId — the model identifier (provider-specific)

Local Models

Use the CLI provider type to run local models via Ollama, llama.cpp, or any command-line LLM:

1. Add an AI resource with type Local CLI
2. Set the command template (e.g., ollama run llama3 "{prompt}")
3. Select it in your agent config

Note: Local CLI models don’t return token usage information.