Admin LLM Settings

LLM Configuration

Manage your Large Language Model providers, API keys, and generation parameters.

AI Provider

OpenAI

DeepSeek

Moonshot

Zhipu AI

Qwen

Ollama

Custom

API Base URL

The base endpoint for the API requests.

API Key

Connection successful. Latency: 124ms

Model Settings

Select Model

Select the specific model version to use for generation.

System Prompt (Default)

System Health

Updated just now

Operational

Last Check 10:42:35 AM

Response Time 240ms

Parameters

Temperature 0.7

Controls randomness: Lowering results in less random completions.

Max Tokens 4096

Top P 1.0

Frequency Penalty 0.0

Advanced

Stream Output

Receive partial results immediately.

Enable Caching

Cache responses to reduce latency.

Retry on Failure

Automatically retry failed requests.

Debug Mode

Log full request/response payloads.