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.

PlanPrice/moCredits/moIncluded LLM UsageModels
Go$1$10~15K requestsOpen models + some premium
  • $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 models: Access the best open models - Kimi, DeepSeek, GLM, MiniMax, Qwen, and more. See the full list with rates below.
  • Some premium models too: GPT-5.6 Luna, Grok 4.5, and Qwen Max & Plus are closed-source models that run on Go at no extra tier - everything else premium needs Pro or Max.

  • The best open-source models: Switch any time with /model in 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.

Go also includes some premium, closed-source models outright - GPT-5.6 Luna, Grok 4.5, and Qwen Max & Plus. If you need the rest (Claude, the other GPT models, Gemini), look at the Pro and 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 models - the strongest open weights available, each chosen for what it does best - plus a handful of premium, closed-source models: GPT-5.6 Luna, Grok 4.5, and Qwen Max & Plus.

The live table on this page lists every model Go includes with its per-token rates. Switch it to All models to see the full catalog, including the premium models that need Pro or Max.

// Models on Goper 1M tokens
Model
Context
Input/M
Output/M
Cache Read
Cache Write
Caps
256K
Free
Free
Free
⚡ Free while capacity lasts
Tencent Hy3
262K
$0.14
$0.58
$0.035
Kimi K3
1M
$3.00
$15.00
$0.30
Kimi K2.7 Code
256K
$0.95
$4.00
$0.19
Kimi K2.7 Code HighSpeed
262K
$1.90
$8.00
$0.38
Kimi K2.6
256K
$0.95
$4.00
$0.16
Kimi K2.5
256K
$0.60
$3.00
$0.10
GLM-5.2
1M
$1.40
$4.40
$0.26
GLM-5.2 Fast
1M
$3.00
$10.25
$0.50
GLM-5.1
$1.40
$4.40
$0.26
GLM-5
200K
$1.00
$3.20
$0.20
1M
$0.60$0.30
$2.40$1.20
$0.12$0.06
⚡ 50% off
MiniMax M2.7
$0.30
$1.20
$0.06
MiniMax M2.5
200K
$0.30
$1.20
$0.03
1M
$1.74$0.435
$3.48$0.87
$0.0145$0.003625
⚡ 75% off
DeepSeek V4 Flash (latest)
1M
$0.14
$0.28
$0.0028
Qwen 3.8 Max
1M
$2.00
$6.00
$0.25
$2.50
Qwen 3.6 Max Preview
$1.30
$7.80
$0.26
$1.63
Qwen 3.6 Plus
$0.50
$3.00
$0.10
Qwen 3.7 Max
1M
$2.50
$7.50
$0.50
$3.13
Qwen 3.7 Plus
1M
$0.40
$1.60
$0.08
$0.50
Qwen 3.7 Flash
1M
$0.03
$0.13
$0.006
$0.038
Step 3.7 Flash
256K
$0.20
$1.15
$0.04
Step 3.5 Flash
1M
$0.10
$0.30
$0.02
1M
$2.00$0.435
$6.00$0.87
$0.40$0.0036
⚡ 99% off
1M
$0.80$0.14
$4.00$0.28
$0.16$0.0028
⚡ 98% off
Nemotron 3 Ultra
1M
$0.60
$2.40
$0.12
1.1M
$0.20$0.10
$1.20$0.60
$0.02$0.01
$0.125
⚡ 50% off · reverts to $0.20 in / $1.20 out · ends August 13, 2026
Available on every plan, including Go.
Muse Spark 1.2 Contributor
1M
$0.10
$0.20
$0.002
Available on every plan, including Go.
Grok 4.5
500K
$2.00
$6.00
$0.50
Available on every plan, including Go.
Inkling
256K
$1.00
$4.05
$0.17
Inkling Small
1M
$0.50
$1.20
$0.10
32/32 Models on Go · Prices per 1M tokens · USD
Text Vision Reasoning

Switch models any time with /model in interactive mode. GPT-5.6 Luna, Grok 4.5, Muse Spark 1.2 Contributor, and Qwen Max & Plus are the exceptions in the premium line-up - all of them are included on Go. The rest (Claude, the other GPT models, Gemini, Muse Spark 1.1 and standard 1.2) need GOAT (Muse Spark 1.2) or Pro or Max.

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 /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.

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.
  • Deals stack on top of your credits: Your $1 already buys $10 of credits, and any active model deal applies on top of those credits - a model at 50% off makes them go twice as far. See Deals for what's running right now.

What that's worth on Go

Two discounts compound here, and it's the compounding that produces the headline number - the plan turns $1 into $10 of credits, then the model's own deal rate stretches each of those credit dollars. Every figure below is computed from the plan's real credit pools and the deal's live rate, so a deal that ends takes its row with it.

Premium-gated models don't appear above: they can only spend the premium half of a plan's credits, and Go's allocation is entirely open-source. That's also why GPT-5.6 Luna runs on Go and Terra needs Pro or Max - Luna bills from the pool Go has.

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

Need more usage or premium models? Compare the Pro and Max plans, or use the pay-as-you-go Provider API. Full comparison and FAQs live on Pricing & Limits.