DocsAI Models

AI Models

Available Models

Gyld supports models from multiple providers. Each model has different strengths in terms of capability, speed, and cost.

ProviderModelBest For
AnthropicClaude Opus 4.6Most capable, complex reasoning
AnthropicClaude Sonnet 4.6Balanced speed + quality (default)
AnthropicClaude Haiku 4.5Fast, lightweight tasks
OpenAIGPT-4.1Strong general purpose
OpenAIGPT-4.1 MiniFast, cost-effective
OpenAIGPT-4.1 NanoFastest, simple tasks
GoogleGemini 2.5 ProResearch, long documents
xAIGrokFast responses

Choosing a Model

Consider these factors when selecting a model:

  • Task complexity — For simple email lookups or message sending, a lighter model (Haiku, GPT-4.1 Mini) is fast and cost-effective. For complex analysis or multi-step reasoning, use a more capable model (Opus, GPT-4.1).
  • Speed — Lighter models respond faster. If your agent handles time-sensitive tasks, speed matters.
  • Cost — More capable models use more credits per interaction. Choose the smallest model that reliably handles your use case.
  • Default recommendation — Claude Sonnet 4.6 is the default and works well for most use cases. Start here and switch only if needed.

You can change the model at any time without losing your agent's configuration or conversation history.

Need help? Reach out at support@gyld.ai