Quick Start

LinkCompute serves three kinds of users. Find the profile closest to yours and follow the links from there.

The API domain has moved: the endpoint domain switched from ai.futurecore.com.cn to api.futurecore.com.cn, and the old domain is retired. If you were already using it, follow the Domain Migration Guide to update the address in your clients, SDKs, and scripts (your API Key, groups, and balance stay the same).

👋 Non-technical user

Your situation: you want to chat with models like GPT or Claude, write text, generate images — without writing code or dealing with "APIs".

Shortest path (up and running in 5 minutes)

Click "Register" in the top-right and create a username and password
In Billing, top up or use a redemption code to add balance (online card top-up may be closed, but redemption codes work)
In Token Management, click "Add token", name it cherry-studio, keep the rest as default
Install Cherry Studio (free desktop AI chat client) and follow the Cherry Studio guide — copy the key from the token page and paste it into the client
Start chatting with GPT, Claude, DeepSeek, Gemini, and more

Recommended reading

Model Plaza

Browse all models with real pricing and channel discounts, and pick the one that fits.

FAQ

Signup, top-up, redemption codes, and client setup questions.

👨‍💻 Software engineer

Your situation: you're familiar with the OpenAI / Anthropic SDKs and want LinkCompute as a unified gateway — one Base URL for all models, no more juggling per-vendor keys.

Shortest path

Register and top up (same as above)
In Token Management, create a token named after your project (e.g. prod-backend, local-dev) and optionally restrict it to specific IPs
In your client, set Base URL to https://api.futurecore.com.cn/v1 and use the LinkCompute token as the API Key
Call with the SDKs you already know — endpoints are compatible with openai / anthropic / gemini / image-generation / audio / video

curl https://api.futurecore.com.cn/v1/chat/completions \
  -H "Authorization: Bearer sk-xxxx" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-5.4","messages":[{"role":"user","content":"hello"}]}'

Capability index

One token per tool — Claude Code / CC Switch / Codex CLI each get their own token, so you can trace heavy callers in the logs
Use CC Switch as an upstream switcher — toggle one Claude Code instance between Anthropic official and LinkCompute; setup steps are in the CC Switch guide
Pick a low-price group — open the channel details in the Model Plaza, compare discounts across groups, and create your token on the best-value channel; this can cut cost by half
Keep an eye on balance — balance is shared across the account, so top up enough in Billing before high-frequency calls to avoid running out mid-way
Task-type calls go through Task Logs — async tasks from MJ, Suno, Kling, Seedance land in Task Logs; search by task ID for progress and errors