Go Plan

The Go plan is the $1/month entry point to Command Code: open models, available globally, for the price of a coffee once a month. Your $1 buys $10 of credits. A 10x multiplier as one shared pool with a monthly usage on every model.

See every plan side by side on Pricing & Limits, or pick a plan from Studio > Billing.

How Go Works

The Go plan is also structured on a similar pattern as the GOAT plan. Each model supported in Go has its own monthly usage. This monthly usage per model is spread between $6 and $10 worth of usage depending on the model.

It is the same structure GOAT plan subscribers get, scaled to a $10 pool: open and a few closed models.

These usage limits all come out of one shared $10 pool. A model's monthly credits allocation is how much usage that pool is worth if you spend the whole month on that model. Mix models and the pool is spent in proportion: $1 of usage on a model with boosted credits takes a smaller share of the pool than $1 of usage on a model with standard credits. The usage limits below work the same way.

Let's connect in our Discord community.

Models included

Every model below is included on the Go plan - switch between them any time with /model in interactive mode. Rates are per 1M tokens; the full catalog, including the models that need GOAT, Pro or Max, lives on commandcode.ai/models.

Usage limits

The Go plan includes the following usage limits:

• 5-hour limit - $3 of usage
• Weekly limit - $6 of usage
• Monthly limit - $10 of usage

How much you can do in each window depends on the model. Cheaper models allow more requests. Pricier models allow fewer.

Here are estimated request counts per limit window. To estimate your own usage, try our usage calculator.

These estimates are based on a typical agent request:

• About 800 new input tokens
• About 50,000 cached input tokens
• About 125 to 200 output tokens, depending on the model

Prices in the table below are per 1M tokens. Most of an agent's tokens are cache reads. That's why cache hit rates matter so much. See all models on Available Models. See per-token prices on Pricing & Limits.

Every model on the Go plan is listed below:

New models start at the standard $6 credits on the $1/mo Go plan until we negotiate better deals. The usage updates automatically the moment a deal starts - no codes, no toggles.

Speed variants are separate models with their own credits, never their base model's: GLM-5.2 Fast has its own row in the boosted table above, while Kimi K2.7 Code HighSpeed carries the standard credits, not Kimi K2.7 Code's boosted usage.

We're constantly negotiating better terms with providers, so the usage credits above can change at any time. When a deal starts, your usage updates by itself.

How is 10x possible?

You pay $1 and code with up to $10 of per-model credit usage. This is possible through phenomenal harness and inference engineering. We work directly with model teams and providers to negotiate capacity for the models we recommend, and we run our infrastructure at leading ~95-98% cache hit rates.

Most of a coding agent's volume is cache reads, so serving the cache well makes every request dramatically cheaper and those savings come back to you as bigger usage.

Deals with the best pricing apply automatically. Many providers and coding agents charge up to 400% over model list prices, while we regularly offer deals matching - and sometimes beating - the labs' own API prices. We run our own infrastructure and have deep experience running open models at scale, which lets us offer better pricing than most providers.

Models we have negotiated capacity for get boosted credits. All other models get standard credits. This includes models whose public price is already discounted. Their credits go up when we get better terms. We often move capacity to newer models that perform better.

What you get

• Open models, everywhere: Switch any time with /model in interactive mode. Browse them all on Available Models, with per-token rates on Pricing & Limits.
• Usage limits: $3 of usage in any 5 hours, $6 in any 7 days - see Usage Limits.
• Extra credits any time: Buy pay-as-you-go credits at model cost - they work on every model, 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 unless you choose to share them.
• Zero data retention available: Most models are ZDR by default. Agreements renew monthly, so brand-new models can take a little time to be covered. You can also enforce ZDR on every request, though ZDR requests meter at the plan's default usage of $6, whatever a model's boosted figure says.

Usage beyond plan limits

Your budget refreshes at the start of every billing cycle, with every model discount already plugged into the usage.

Buy extra credits at model cost any time: they roll over, never expire, and bill at the model's regular rate, since the bigger usage apply to your monthly budget only.

Past a limit, requests fall back to those credits - and without them, paid models pause until the window or cycle resets while the free models keep working.

Get started

1. Install: npm i -g command-code
2. Sign in and start coding with cmd (macOS/Linux) or cmdc (Windows)
3. Pick the Go plan from Studio > Billing or the pricing page

Go is the only plan without API access - every other plan can call the Provider API with the same key it uses for the CLI. Need API access, premium models, or more usage? The GOAT plan is $10/month for $70 of credits and full API access; compare it with Pro and Max, or use the pay-as-you-go Provider API. Full comparison and FAQs live on Pricing & Limits.

FAQs