Guides
OpenAI- and Anthropic-compatible APIs: popular AI tools connect in a few minutes. The full interface is in the API reference.
Three steps
- Sign up and create an API key in the console.
- Point your tool at https://api.aifans.fan/v1 (Claude Code and other Anthropic-API tools use https://api.aifans.fan).
- Enter your key and a model name such as deepseek-v4.1-flash, and send a test message.
Coding tools
Use DeepSeek, GLM and Kimi in Claude Code
A few environment variables let Claude Code run on DeepSeek, GLM, Kimi or MiniMax.
Use DeepSeek in Cline, Roo Code and Kilo Code
Connect the VS Code coding agents to DeepSeek V4.1 Flash and more: choose OpenAI Compatible and fill in three fields.
Set up Cursor and other OpenAI-compatible tools
Three settings: base URL, API key and model name, with steps for Cursor.
Use DeepSeek in Continue (VS Code and JetBrains)
A config.yaml example for the Continue coding assistant; works in IntelliJ IDEA and PyCharm too.
Use DeepSeek in OpenCode and Aider
Terminal coding agents on DeepSeek, GLM and more: an opencode.json example and Aider's two environment variables.
What Claude Code costs per month on DeepSeek, GLM or Kimi
A typical month of agent steps priced model by model, and a calculator for your own numbers. Cached input is most of the bill.
Use DeepSeek, GLM and Kimi in Zed
Zed's built-in agent on an OpenAI-compatible API: the settings.json block, where the key goes and what the editor needs to know about each model.
Models
Kimi K3 API: price, context window and how to call it
Moonshot AI's flagship through OpenAI- and Anthropic-compatible APIs: price next to Moonshot's own, capabilities, code samples.
GLM-5.3 and GLM-5.3 Flash API pricing
Zhipu AI's flagship and its fast multimodal sibling: prices next to Zhipu's own, which one to use, code samples.
MiniMax M2.7 API: price, context and code
MiniMax's coding and agent model at MiniMax's own price, through OpenAI- and Anthropic-compatible APIs, with code samples.
Translation API for 33 languages, per token
The Hunyuan MT2 translation models: prices per million tokens, what a 50,000-word document costs, chunking and glossaries.
Chat apps
Use DeepSeek in Open WebUI, LobeChat and Chatbox
Add an OpenAI-compatible provider to three popular chat apps for the web, desktop and mobile.
Use DeepSeek and GLM in Cherry Studio
Add an OpenAI provider to the Cherry Studio desktop app: API host, key and model ID, with the fix for a 404.
Apps and workflows
Connect DeepSeek and GLM to Dify
Use the OpenAI-API-compatible model provider to bring DeepSeek, GLM and other models into Dify apps and workflows.
Use DeepSeek in n8n workflows
Give n8n's OpenAI credential a custom base URL and call DeepSeek and more from its AI nodes.
Productivity
Frameworks and SDKs
DeepSeek with LangChain, LlamaIndex and the Vercel AI SDK
OpenAI-compatible code for three popular frameworks, plus the parameter that turns thinking off.
Switch from the OpenAI SDK
Python and Node.js examples, streaming and a migration checklist. Usually two lines change.