Pricing & Limits

Plain pricing. No surprises. Credits that never expire. See full plans and side-by-side comparison on the pricing page.

How it works.

• Resets monthly. Your request budget refreshes at the start of every billing cycle.
• Rolling 5-hour & weekly limits. Each plan also has shorter rolling windows so a single burst can't drain your whole month. See usage limits.
• Top up automatically. Buy extra credits at model cost. They roll over. They never expire.
• Your code stays yours. Command Code never trains on it. Never stores it.

Your plan, in one place.

• Pick a plan or top up credits. Head to Studio > Billing.
• Watch every request, in real time. The Usage page in Studio tracks tokens and request history as it happens.
• Cards. Invoices. Auto-reload. Manage them all from the billing portal at Studio > Billing.

Command Code Enterprise. Built for organizations.

For teams that need their code and data to stay on their own infrastructure. Enterprise gives you the security, compliance, and control your organization requires — without compromise.

Talk to our team at support@commandcode.ai to get started.

Individual Plans

Team Plans

How it works.

• Monthly subscription credits. Reset at the start of every cycle.
• Top up at model cost. Credits roll over. Forever.
• Enterprise? Email support@commandcode.ai for custom terms, SLAs, and dedicated support.

Usage limits

On top of your monthly credits, every subscription plan has two rolling usage limits — a 5-hour window and a weekly window. They smooth out bursts so a single busy session can't drain a whole month in an afternoon, while your full monthly pool stays available across the cycle.

Each window is a share of your plan's monthly credit allocation:

• 5-hour limit — 30% of your monthly credits
• Weekly limit — 60% of your monthly credits

Limits are measured in credit value, not request count — so how many requests you get depends on the models you run. Cheaper models like DeepSeek V4 Flash stretch much further than premium models like Claude Opus. The usage estimates below and the calculator help you gauge your own mix.

These windows apply to your plan's included monthly credits. Usage with no subscription (free or balance-only) and custom Enterprise pools have no rolling window caps — they're gated only by your credit balance. On-demand credits are never throttled either, on any plan (details below).

How the windows roll

Both windows roll from first use, not on a fixed clock:

• A window opens on the first request you make after the previous one elapsed, then resets exactly one window-length later (5 hours or 7 days).
• Usage never carries between windows — each new window starts at zero.
• Switching plans resets both windows, so you always start a new plan with a fresh allowance.

Usage beyond your limit

Rolling limits throttle only your included monthly credits. On-demand credits are never throttled:

• Top-up and pay-as-you-go credits are exempt. When you have on-demand credits available — or once your monthly pool is spent — requests skip the window check entirely. Adding credits with /extra unblocks you immediately.
• While you're over a window limit, Command Code spends your on-demand credits first, preserving your monthly allocation for when the window resets.

So you're never hard-stopped: keep working past a window on on-demand credits, or wait for it to reset to use your included credits again.

Tracking your limits

Run /usage in the CLI to see live 5-hour and weekly meters — each shows how much of the window you've used and when it resets:

If you do hit a limit, the CLI tells you which window you reached and when it frees up:

Usage estimates

The numbers above are estimates, not ceilings. 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. The calculator below has a cache slider to model your own session.
• A range, not a single number. 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 estimates are the mix average across each plan's typical models.
• A balanced mix. Even split across models within each tier. Pro, Max 10×, and Max 20× assume ~35% open-source / ~65% premium.
• Long conversations cost more. Every new turn re-reads the full context, so a long-running session burns through credits faster than a fresh one. Use /clear or 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.

Pick a model. Adjust the sliders. See how far your credits go. These are estimates based on typical patterns — your actual mileage may vary.

Models.

Command Code runs on the best models from the open-source community, Anthropic, OpenAI, Google, Sakana, and xAI. Each one chosen for what it does best.

Checkout all our available models. Switch any time with /model in interactive mode. Per-token rates for each model are listed below.

Available models

Open Source

Model id

Name

Best for

Capabilities

deepseek/deepseek-v4-pro

DeepSeek V4 Pro

hybrid-attention long-context reasoning

text

deepseek/deepseek-v4-flash

DeepSeek V4 Flash

fast hybrid-attention reasoning

text

moonshotai/Kimi-K2.7-Code

Kimi K2.7 Code

improved long-horizon coding with vision

text, vision

moonshotai/Kimi-K2.7-Code-Highspeed

Kimi K2.7 Code HighSpeed

high-speed long-horizon coding with vision

text, vision

moonshotai/Kimi-K2.6

Kimi K2.6

long-horizon coding with vision

text, vision

moonshotai/Kimi-K2.5

Kimi K2.5

multimodal frontend coding

text, vision

zai-org/GLM-5.2

GLM-5.2

powerful coding with 1M context and long-horizon tasks

text

zai-org/GLM-5.2-Fast

GLM-5.2 Fast

high-throughput GLM-5.2 with 1M context

text

zai-org/GLM-5.1

GLM-5.1

long-horizon autonomous coding agent

text

Model pricing. At cost.

Plans include usage at model API rates. You pay for what you use, by model and by token. All prices below are per million tokens. Subscriptions include 2-10x more credits for the same cost as API pricing.

Context windows. Managed for you.

A context window is the maximum span of tokens (text, images, and code) a model can hold in mind at once. Input prompt plus everything it generates back.

Every Command Code session has its own context. As you prompt, read files, and respond, that context fills up. Command Code compresses older messages automatically, so you can keep going without starting over.

Context window size depends on the model. Command Code supports model-specific context windows, with up to 1 million tokens supported on Claude Fable 5, Claude Sonnet 5, Claude Sonnet 4.6, Claude Opus 4.8, Claude Opus 4.7, and DeepSeek V4 Pro.

FAQs

Deals.

Command Code deals. Apply automatically. No codes. No toggles. Discounts work on every plan and even extra pay-as-you-go credits.

How deals work.

• Automatic. Pick the discounted model from /model in the CLI or in Studio. The rate drops for the length of the deal.
• On every plan. Go, Pro, Max 10×, Max 20×. Credits routed to the discounted model stretch further on every tier.
• Discounted upstream only. The deal rate applies only when the discounted upstream serves the request.
• On top-up credits. Extra credits you buy from Studio > Billing get the same discount when spent on the discounted model.
• Real-time billing. The Usage page reflects the discounted price per request as it happens.
• Auto-expires. When a deal ends, the model returns to its full list price across the docs, the calculator, and Studio. Nothing for you to do.