Command Code API key setup
A coding-agent CLI (npm command-code) reselling about 97 model ids from 22 vendors on credit plans: Go at $1/month with $10 of credits and GOAT at $10/month with up to $100 in credits, plus a $15 Provider plan billed at the underlying model rates with no markup.
Get your key
- Open the Command Code site: commandcode.ai
- Create an account and generate an API key.
- Paste it into the Dracon BYOK provider keys, stored encrypted (AES-256-GCM), used browser-direct, works in every Dracon tool.
Use your key in every tab
Two free extensions take the key you just set up. Both read the page you are on and use your own provider key: free, no account, nothing stored on a server we run.
AI Auto Form Filler
Complete a web form from a short description, using a model you bring yourself.
All extensions · last checked 2026-10-22.
Free tier
No recurring free tier advertised as of the last check (2026-10-31). Usage is billed per the provider's listed pricing. You pay them directly, no Dracon markup.
Rate limits: Request budgets reset each billing cycle, with rolling 5-hour and weekly windows inside them. Rate limits are Standard on Go and GOAT, and higher tiers publish Higher and Highest limits. Extra credits are bought at model cost and roll over; credits never expire.
Paid plans compared
Every tier Command Code publishes, with the price and the limit as the vendor states them, last checked 2026-10-31. Confirm with the provider before you buy. You pay them directly, no Dracon markup.
| Plan | Price | Usage limit | What you get |
|---|---|---|---|
| Go | $1/mo | $10 of credits included, up to about $15 of usage with deals; No API access on this tier |
|
| GOAT | $10/mo | Up to $100 of credits included, up to about $100 of usage with deals |
|
Official plan source: commandcode.ai/pricing
Connection details
- Env var
COMMAND_CODE_API_KEY- Model lineup
- Claude Sonnet 5.5, GPT-6 Astra, Kimi K3, GLM-5.3, MiniMax M3, Claude Opus 5.5, GPT-5.3 Codex, Gemini 4 Argon, Grok 4.7, Kimi K2.7 Code, DeepSeek V4.1 Flash, Qwen 3.8 Max, Muse Spark 1.3, MiniMax M3.1 Flash, Nemotron 3 Ultra, Tencent Hy4 Preview
Gotchas
Browser-direct chat is not available for this provider: Coding agent CLI (npm command-code) that resells models through its own credit plans; the separate Provider API needs a $15/month key we do not hold, so its chat endpoints are unverified.. Dracon provider keys still cover it for tools that run elsewhere (for example a LiteLLM chain from the Dracon Router builder).
Our verdicts on this kind of provider
Independent comparisons we keep current as pricing and free tiers shift. A guide is setup; a verdict is whether it's worth setting up.