Kimi K3 in OpenCode

Terminal coding agent · built in since OpenCode 1.18.32 · older versions: custom provider in opencode.json · about 2 minutes · listing verified on 1.18.32 (22 Sep 2026)

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.

OpenCode 1.18.32 and later: pick it from the list

OpenCode bundles the models.dev catalog at build time, and ainetcafe has been in it since 17 September. The first release built after that is 1.18.32 (published 21 September). From there, nothing to configure: export the key and the provider appears.

export AINETCAFE_API_KEY="sk-..."      # add to your shell profile
opencode models ainetcafe              # prints: ainetcafe/Kimi-K3
opencode --model ainetcafe/Kimi-K3

opencode 1.18.32: opencode models ainetcafe prints ainetcafe/Kimi-K3; --verbose shows $2.10 / $10.50, $0.30 cached, 262144 context

Inside the TUI, /models lists ainetcafe / Kimi K3 once the variable is set; without it the provider is hidden, which is how OpenCode treats every key-based provider. opencode models ainetcafe --verbose shows what the catalog carries for us: $2.10 / $10.50 per million, $0.30 cached input, 262,144 context, 32,768 output, reasoning and image input on. To pin it, set "model": "ainetcafe/Kimi-K3" in opencode.json.

If it says Provider not found on 1.18.32+: check opencode --version, and remove a stale catalog cache at ~/.cache/opencode/models.json (we hit one from February on a test machine; OpenCode rebuilds it).

OpenCode 1.18.31 and earlier: custom provider

Older builds carry a models.dev snapshot from before our entry, so add the provider by hand. Create or edit ~/.config/opencode/opencode.json (global) or opencode.json in the project root (per project):

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "ainetcafe": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "ainetcafe",
      "options": {
        "baseURL": "https://microquickjs.com/v1",
        "apiKey": "{env:AINETCAFE_API_KEY}"
      },
      "models": {
        "Kimi-K3": {
          "name": "Kimi K3",
          "limit": { "context": 262144, "output": 32768 },
          "tool_call": true,
          "attachment": true
        }
      }
    }
  },
  "model": "ainetcafe/Kimi-K3"
}

Export the key in your shell profile so the env: reference resolves:

export AINETCAFE_API_KEY=sk-your-ainetcafe-key

Run opencode, then /models to confirm ainetcafe/Kimi K3 is selected.

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

Symptom	Cause	Fix
401 Invalid token	Key copied with a space, or key from another site	Re-copy from Token Management on microquickjs.com
403 quota / insufficient balance	Wallet at zero or plan quota used up	Top up in Wallet, or wait for the weekly plan reset
404 model not found	Model ID typed differently	Use exactly `Kimi-K3`
429	Rate limit for your tier	Reduce concurrency; limits rise with spend, or ask for a committed plan
Tool calls never happen	Tool calling disabled in the client, or thinking blocks stripped	Keep 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.