LLM Providers

MoMCP-TUI supports 9+ built-in LLM providers plus any OpenAI-compatible API.

Built-in Providers

ProviderBase URLModels
OpenAIhttps://api.openai.com/v1gpt-5.5, gpt-5.4, gpt-5.4-mini, gpt-5.2, gpt-5.1, gpt-5-mini
DeepSeekhttps://api.deepseek.com/v1deepseek-v4-flash, deepseek-v4-pro
Qwen (通义千问)https://dashscope.aliyuncs.com/compatible-mode/v1qwen3.6-plus, qwen3.6-flash
Kimihttps://api.moonshot.cn/v1kimi-k3, kimi-k2.7-code, kimi-k2.6, kimi-k2.5
MiniMaxhttps://api.minimaxi.com/v1MiniMax-M3, MiniMax-M2.7, MiniMax-M2.7-highspeed
Doubao (豆包)https://ark.cn-beijing.volces.com/api/v3doubao-seed-evolving, doubao-seed-2-1-pro, etc.
Zhipu (智谱)https://open.bigmodel.cn/api/paas/v4glm-5.2, glm-5.1, glm-5
MiMo (小米)https://api.xiaomimimo.com/v1mimo-v2.5-pro, mimo-v2.5

Configuring a Provider

Launch momcp-tui

Type /model to open the model manager

Click on the desired provider and model

If no API key is configured, you'll be prompted to enter one

Setting API Key

Use the /api_key command to manage API keys:

/api_key              # Check current API key status
/api_key set sk-xxx   # Set API key for current provider

Adding Custom Models

You can add models not in the built-in list:

Open the model manager with /model

Click "Add Model"

Enter the provider name (e.g., "openai") and model name

Thinking Mode

Many providers support "thinking" (reasoning) mode. Toggle it with:

/think      # Toggle thinking mode

Or adjust the compression threshold:

/context   # Adjust conversation compression settings

When enabled, the LLM's reasoning process is displayed as a separate stream before the final answer.

API Key Sources

Visit the corresponding URL to obtain your API key.