Provider Options

Configure timeouts and options for API providers. These apply to all requests unless overridden.

Request timeout in milliseconds (default: 300000)

Timeout between streamed response chunks

Model Variants

Many models support multiple variants with different configurations.

Variants Support
Enable variant selection for models that support it

Built-in variants:

  • Anthropic: high (default), max
  • OpenAI: none, minimal, low, medium, high, xhigh
  • Google: low, high

Provider-Specific

Advanced options for specific providers.

AWS region for Bedrock

AWS credentials profile