Go Plan
The Go plan is the $1/month entry point to Command Code. It's built for developers everywhere — open-source models, available globally, with credits that never expire. We want coding agents to work for everyone.
See every plan side by side on Pricing & Limits, or pick a plan from Studio > Billing.
| Plan | Price/mo | Credits/mo | Included LLM Usage | Models |
|---|---|---|---|---|
| Go | $1 | $10 | ~15K requests | Open-source models only |
- $1/month. The most affordable way to run a frontier coding agent all month.
- $10 of credits every month. Your request budget refreshes at the start of every billing cycle.
- ~15K requests. A typical month of open-source usage. See usage estimates for how far that stretches.
- Open-source models. Access the best open models — DeepSeek, Kimi, GLM, MiniMax, Qwen, Step, MiMo, and Nemotron.
- The best open-source models. Switch any time with
/modelin interactive mode. Browse them all on Available Models, with per-token rates on Pricing & Limits. - Credits that never expire. Monthly credits reset each cycle. Buy extra credits at model cost any time — they roll over and never expire.
- Global availability. Open-source models run on infrastructure in the US, EU, and Singapore for reliable access worldwide.
- Your code stays yours. Command Code never trains on your code and never stores your code snippets.
- Zero data retention available. Run the CLI with
CMD_ZDR=1(for example,CMD_ZDR=1 cmd) to enforce zero data retention and no prompt training on every request.
The $1 Go plan is meant for international developers. We want coding agents to work for everyone, so open-source models are available globally with infrastructure in the US, EU, and Singapore for reliable access worldwide.
If you need premium models (Claude, GPT, Gemini), look at the Pro & Max plans or pay-as-you-go Provider API. For custom terms, contact us at support@commandcode.ai to discuss Team & Enterprise plans.
Go includes open-source models only. These are the strongest open models available, each chosen for what it does best:
- Kimi K2.7 Code, K2.6, K2.5
- DeepSeek V4 Pro, DeepSeek V4 Flash
- GLM-5.2, GLM-5.1, GLM-5
- MiniMax M3, M2.7, M2.5
- Qwen 3.7 Max, 3.7 Plus, 3.6 Max Preview, 3.6 Plus
- Step 3.7 Flash, Step 3.5 Flash
- MiMo V2.5 Pro, MiMo V2.5
- Nemotron 3 Ultra
Read complete list of available models on Available Models. Per-token rates for every model are listed on Pricing & Limits. Premium models (Claude Opus & Fable, GPT, Gemini) are not included on Go — upgrade to Pro & Max for those.
The ~15K requests number is an estimate, not a ceiling. Your actual usage depends on the models you pick, the length of your prompts, and how long your conversations run.
- A typical request. ~700–1K input tokens, ~125–200 output tokens, plus ~42K–56K cache reads on average.
- Cheaper models stretch further. On Go, DeepSeek V4 Flash runs ~60K requests with no cache — ~15K once the typical 52K cache reads are included. Our estimate is the mix average across the plan's typical models.
- Long conversations cost more. Every new turn re-reads the full context, so use
/clearor start a new session for unrelated tasks to keep things efficient. - Track the real number. The Usage page in Studio always reflects the actual price charged per request.
Model the math yourself with the calculator on Pricing & Limits.
- Resets monthly. Your request budget refreshes at the start of every billing cycle.
- Top up automatically. Buy extra credits at model cost. They roll over. They never expire.
- Deals apply automatically. Permanent discounts and usage multipliers apply to every request, including extra credits — no codes, no toggles.
- Install:
npm i -g command-code - Sign in and start coding with
cmd - Pick the Go plan from Studio > Billing or the pricing page
Need more usage or premium models? Compare the Pro & Max plans, or use the pay-as-you-go Provider API. Full comparison and FAQs live on Pricing & Limits.