LLM

Ortavox supports multiple leading AI providers out-of-the-box. You select the LLM provider and model as part of the model configuration when creating or updating your Agent.

Supported Providers & Models

OpenAI

1
{ "provider": "openai", "model": "gpt-4o-mini" }

Recommended starter model. Other popular options: gpt-4o, gpt-4-turbo.

Anthropic

1
{ "provider": "anthropic", "model": "claude-3-5-sonnet-20241022" }

Excellent at following nuanced instructions and long-context reasoning.

Google

1
{ "provider": "google", "model": "gemini-1.5-flash" }

Strong multilingual performance and fast responses.

Groq

1
{ "provider": "groq", "model": "llama-3.3-70b-versatile" }

Best-in-class speed for latency-sensitive use cases.

DeepSeek

1
{ "provider": "deep-seek", "model": "deepseek-chat" }

Cost-efficient with strong reasoning capabilities.

Tip: Keep temperature between 0.5 and 0.9 for conversational agents. Lower values make responses more deterministic; higher values create more variability.