Blog

Models & providers

OpenAI, Anthropic, AiApiy, custom, China-hosted — how to pick.

May 7, 2026·6 min read

Using China-hosted models in Kition (DeepSeek / Qwen / Moonshot)

Under China network conditions, domestic models are often the most stable choice. Setup mirrors OpenAI — one baseURL away.

Read more
May 5, 2026·6 min read

Per-task model selection: balancing cost and quality

Not every task needs opus / GPT-5. Give light tasks haiku / mini; reserve opus for hard ones.

Read more
May 3, 2026·5 min read

Model usage dashboard: cost control in practice

Break usage down by provider / model / vault — spot AI-field black holes and long-context abuse.

Read more
May 1, 2026·6 min read

Configuring a custom OpenAI-compatible provider

Any endpoint following the Responses shape plugs in. Same for Ollama / vLLM / internal gateways.

Read more
Apr 29, 2026·5 min read

What is AiApiy and how to set it up in Kition

AiApiy is a unified reverse-proxy across OpenAI / Claude / Gemini. One account, many providers.

Read more
Apr 27, 2026·5 min read

Driving the Kition agent with GPT-5

GPT-5 is rock-solid on structured outputs and multi-step function calls. A great fit for OpenAI-native workflows.

Read more
Apr 25, 2026·5 min read

Driving the Kition agent with Claude 4.7

Claude is consistently strong on long context, tool use, and alignment. A solid default for the Kition agent.

Read more
Apr 23, 2026·7 min read

OpenAI Responses vs Anthropic Messages: how to pick

Both wires are mature. The differences live in tool-call patterns, streaming preference, and pricing band.

Read more

Ready when you are.

Kition is a local-first AI workspace. Markdown documents, structured tables, and an AI agent — running on your own machine, against the model provider you choose.