Docs
Biyan Desktop
Model Parameters

Model Parameters

Open the model settings panel from a chat to configure request parameters exposed by the selected cloud provider.

SettingEffect
TemperatureControls sampling variability when supported.
Top PLimits sampling to a cumulative probability range when supported.
Maximum output tokensCaps generated output; the provider may enforce a lower limit.
Context limitInformational/provider-derived budget used to validate messages and documents.
Image inputEnable only for a provider/model that officially supports images.
Native file inputEnable only for a provider/model and file type that officially supports files.
Tool callingRequired for MCP tools; support varies by model and API mode.

Biyan sends only parameters accepted by the configured provider. Local-engine settings such as GPU layers, llama.cpp arguments, MLX options, and embedding mode no longer exist.

An incorrect capability flag may cause the provider to reject a request. Verify model IDs and capability support in the provider's current documentation.