WordOllama

Online Model Settings

WordOllama connects to online model services that expose an OpenAI-compatible API. Enter the endpoint, API key, and exact model ID to use that model in Word or WPS.

Online Services and Model IDs

The examples below were checked against provider documentation in July 2026. Models change frequently, so use the model ID shown in your provider console or returned by its model-list endpoint.

  • OpenAI: gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna
  • DeepSeek: deepseek-v4-pro, deepseek-v4-flash
  • Kimi: kimi-k3, kimi-k2.7-code, kimi-k2.6
  • Zhipu GLM: glm-5.2, glm-5.1, glm-5-turbo
  • Xiaomi MiMo: mimo-v2.5-pro, mimo-v2.5
  • Other services: Alibaba Qwen and other services with OpenAI-compatible endpoints, including endpoints you host yourself

Local Compatible Backends

Local models are not limited to Ollama. WordOllama can connect to any reachable local backend that exposes an OpenAI-compatible API, including Ollama, LM Studio, vLLM, and llama.cpp. Enter the local Base URL, model ID, and an API key if the backend requires one.

Configuration Steps

  1. Open the WordOllama settings interface
  2. Select OpenAI Compatible API as the AI provider
  3. Enter the API address, such as https://api.openai.com/v1 or the Base URL of a local backend
  4. Enter the API key; follow your local backend's instructions if it does not validate keys
  5. Enter or select an exact model ID exposed by the provider, save, and test the connection

Important Notes

  • Keep your API Key secure and never share it with others
  • Online APIs may incur charges; review the provider's pricing and usage
  • Document content will be sent to the API server; avoid including sensitive information
  • Streaming, tool calls, and other optional features may vary across compatible backends