Kimi K3 in Cline

VS Code extension · OpenAI-compatible provider · about 2 minutes

Before you start. Create an account (you get $2 to try), then open Token Management → Create token and copy the key. The key starts with sk-. Endpoints: OpenAI-compatible https://microquickjs.com/v1, Anthropic-compatible https://microquickjs.com. Model ID: Kimi-K3.

Steps

  1. Open Cline in VS Code, then the gear icon → API Provider.
  2. Choose OpenAI Compatible.
  3. Base URL: https://microquickjs.com/v1
  4. API Key: your ainetcafe key.
  5. Model ID: Kimi-K3
  6. Under model settings, set context window to 262144 (or up to 1000000 if you asked us to enable the full window), max output 32768, and tick image support and tool support.
  7. Save. Start a task; the first reply confirms the connection.

Recommended settings

SettingValueWhy
Temperature0.6K3 is stable for code edits at this value
Prompt cachingon (default)Cline resends the whole context each turn; cache hits cut that to $0.30 per million
Plan and Act modessame modelK3 handles both; no need for a second provider

Verify the key first

Thirty seconds now saves an hour of guessing later. Run this in a terminal; you should see a short reply and a usage block.

curl https://microquickjs.com/v1/chat/completions \
  -H "Authorization: Bearer $AINETCAFE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"Kimi-K3","messages":[{"role":"user","content":"Say OK"}],"max_tokens":5}'

If something goes wrong

SymptomCauseFix
401 Invalid tokenKey copied with a space, or key from another siteRe-copy from Token Management on microquickjs.com
403 quota / insufficient balanceWallet at zero or plan quota used upTop up in Wallet, or wait for the weekly plan reset
404 model not foundModel ID typed differentlyUse exactly Kimi-K3
429Rate limit for your tierReduce concurrency; limits rise with spend, or ask for a committed plan
Tool calls never happenTool calling disabled in the client, or thinking blocks strippedKeep the client's default tool settings; K3 returns a thinking block before tool_use, do not filter it out

Still stuck? Email [email protected] with the request ID from the error body.