Pro Plan

The Pro plan is $20/month and includes $80 in credits across 45+ open and premium models. It includes everything in the GOAT plan, plus access to Claude, GPT, Gemini, and other premium models.

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

The Pro plan gets you:

  • $20/mo gives you $80 in total credits
  • 45+ open and premium models: Claude, GPT, Gemini, and more
  • Everything included in the GOAT plan and $10 on top ($80 total)
  • ~100K requests and 12B+ tokens, depending on the models you use
  • $120+ in potential value when model deals are active

Premium closed models cost more to run than open models. Pro gives you everything in the GOAT plan, plus another $10 in plan price and access to premium models. You can use your credits across open models or premium models depending on what you need.

The Pro plan includes 45+ open and premium models. Switch models any time with /model.

Claude Opus and Fable require a Max plan. You can also use them with pay-as-you-go credits through the Provider API.

See the full model list at commandcode.ai/models.

Caps
DeepSeek V4 Flash Vision (exp)Off-peak shown (17h/day) · peak $0.44 / $1.32 01–04 & 06–10 UTC
1Mnot yet scored$0.22$0.66$0.01
1Mnot yet scoredFreeFreeFree
1M59.580$1.40$4.40$0.26
262K52.0$0.40$3.00$0.04
DeepSeek V4 Pro (latest)Off-peak shown (17h/day) · peak $1.32 / $3.96 01–04 & 06–10 UTC
1M53.275$0.66$1.98$0.022
Gemini 3.7 Flash-50%Ends December 31, 2026
1M56.0339$1.50$0.75$7.50$3.75$0.15$0.075$0.08334$0.04167
500K60.966$2.00$6.00$0.50
1M56.8$1.25$4.25$0.15
1M56.8$0.10$0.20$0.002
1M58.147$2.00$6.00$0.25$2.50
DeepSeek V4 Flash (latest)Off-peak shown (17h/day) · peak $0.44 / $1.32 01–04 & 06–10 UTC
1M52115$0.22$0.66$0.007
1M41.261$0.50$1.20$0.10
1Mnot yet scored$0.03$0.13$0.006$0.038
1M37.4361$0.30$2.50$0.03
1M51.6187$1.50$7.50$0.15
256Knot yet scoredFreeFreeFree
256K42.370$1.00$4.05$0.17
1M59.739$3.00$15.00$0.30
1M53.2$1.25$4.25$0.15
1.1M52.3165$0.20$1.20$0.02$0.25
1.1M60.969$5.00$30.00$0.50$6.25
1.1M56.6117$2.00$12.00$0.20$2.50
500K55.851$2.00$6.00$0.50
262K42.275$0.14$0.58$0.035
1M55.382$2.00$10.00$0.20$2.50
1Mnot yet scored$3.00$10.25$0.50
1M52.669$1.40$4.40$0.26
262Knot yet scored$1.90$8.00$0.38
256K43.038$0.95$4.00$0.19
1M38.3136$0.60$2.40$0.12
1M45.4104$0.60$0.30$2.40$1.20$0.12$0.06
1M39.456$0.40$1.60$0.08$0.50
256K30.9120$0.20$1.15$0.04
1M38.062$0.80$0.14$4.00$0.28$0.16$0.0028
1M42.958$2.00$0.435$6.00$0.87$0.40$0.0036
1M46.7$2.50$7.50$0.50$3.13
1M52.0$1.50$9.00$0.15
1M25.6$0.25$1.50$0.03
1M26.5$0.10$0.30$0.02
200K41.028$1.40$4.40$0.26
400K56.3$5.00$30.00$0.50
200K38.9$0.30$1.20$0.06
200K41.1$1.30$7.80$0.26$1.63
200K40.5$0.50$3.00$0.10
256K45.1$0.95$4.00$0.16
400K40.9$0.75$4.50$0.075
200K40.6$1.00$3.20$0.20
400K45.5132$2.00$8.00$0.50
400K53.1$2.50$15.00$0.25
256K36.0$0.60$3.00$0.10
200K34.5$0.30$1.20$0.03
200K24.1101$1.00$5.00$0.10$1.25
1M48.4$3.00$15.00$0.30$3.75
53/58 Models · Per 1M tokens · USD
Text Vision Reasoning

Pro plan includes the following usage limits:

  • 5-hour limit - $16 of usage
  • Weekly limit - $40 of usage
  • Monthly limit - $80 of usage

How many requests you get depends on the model you use. Cheaper models go further. See the usage calculator for estimates.

ModelRequests / 5 hoursRequests / weekRequests / month
GPT-5.6 Sol4731,1802,370
DeepSeek V4 Flash (latest)21,30053,200106,000
GLM-5.21,0802,7105,410
GPT-5.6 Luna4,44011,10022,200
Tencent Hy38,09020,20040,400
Qwen 3.8 27B5,48013,70027,400
Qwen 3.8 Max3929801,960
Qwen 3.7 Max3027541,510
Qwen 3.7 Plus1,8504,6309,270
Qwen 3.6 Plus1,4303,5807,170
MiniMax M33,3608,41016,800
Kimi K2.7 Code1,2703,1606,330
MiMo V2.526,00064,900130,000
DeepSeek V4 Pro (latest)2,9607,41014,800
MiMo V2.5 Pro8,55021,40042,700
DeepSeek V4 Flash Vision (exp)7,43018,60037,100
GLM-5.34061,0102,030
Muse Spark 1.26421,6003,210
Muse Spark 1.2 Contributor27,30068,200136,000
Kimi K32947351,470
Kimi K2.7 Code HighSpeed2716781,360
Grok 4.52165401,080
Grok 4.62165401,080
Gemini 3.7 Flash2,3505,88011,800
GLM-5.2 Fast2075181,040
Inkling5931,4802,970
Inkling Small1,0602,6605,320
Step 3.7 Flash2,5106,28012,600
Step 3.5 Flash5,26013,20026,300
Nemotron 3 Ultra8622,1604,310
Claude Sonnet 52997461,490
Claude Sonnet 4.6199498995
Claude Haiku 4.55971,4902,990
GPT-5.6 Terra2967401,480
GPT-5.5118296592
GPT-5.42375921,180
GPT-5.4 Mini7891,9703,940
GPT-5.3 Codex143359717
Gemini 3.6 Flash3929801,960
Gemini 3.5 Flash3819521,900
Gemini 3.5 Flash Lite1,7904,4608,930
Gemini 3.1 Flash Lite2,0005,00010,000
Muse Spark 1.14281,0702,140

Our estimates use a typical agent request with about 800 new input tokens, 50,000 cached input tokens, and 125 to 200 output tokens. See all model prices on Pricing & Limits.

Every Pro model has its own monthly credit limit.

ModelInputOutputCache ReadCache WriteMonthly credits
$5.00$30.00$0.50$6.25$80
GLM-5.2$1.40$4.40$0.26-$80
Tencent Hy3$0.14$0.58$0.035-$80
Qwen 3.8 27B$0.40$3.00$0.04-$80
$0.22$0.66$0.007-$70
Kimi K2.7 Code$0.95$4.00$0.19-$70
$0.30$1.20$0.06-$57
Qwen 3.7 Max$2.50$7.50$0.50$3.13$43
$0.40$1.60$0.08$0.50$43
$0.50$3.00$0.10-$43
MiMo V2.5$0.14$0.28$0.0028-$40
$0.20$1.20$0.02$0.25$30
Qwen 3.8 Max$2.00$6.00$0.25$2.50$30
$0.66$1.98$0.022-$30
MiMo V2.5 Pro$0.435$0.87$0.0036-$30

Premium models

Claude, GPT, and Gemini models get up to $20 in monthly usage per model. Claude Opus, Claude Fable, and Fugu Ultra require a Max plan or pay-as-you-go usage through the Provider API.

ModelInputOutputCache ReadCache WriteMonthly credits
Claude Sonnet 5$2.00$10.00$0.20$2.50$20
Claude Sonnet 4.6$3.00$15.00$0.30$3.75$20
Claude Haiku 4.5$1.00$5.00$0.10$1.25$20
$2.00$12.00$0.20$2.50$20
GPT-5.5$5.00$30.00$0.50-$20
GPT-5.4$2.50$15.00$0.25-$20
GPT-5.4 Mini$0.75$4.50$0.075-$20
GPT-5.3 Codex$2.00$8.00$0.50-$20
Gemini 3.6 Flash$1.50$7.50$0.15-$20
Gemini 3.5 Flash$1.50$9.00$0.15-$20
Gemini 3.5 Flash Lite$0.30$2.50$0.03-$20
Gemini 3.1 Flash Lite$0.25$1.50$0.03-$20
Muse Spark 1.1$1.25$4.25$0.15-$20

New open models

New open models start with $30 in monthly credits while we work on better pricing and capacity deals.

ModelInputOutputCache ReadCache WriteMonthly credits
$0.22$0.66$0.01-$30
GLM-5.3$1.40$4.40$0.26-$30
Muse Spark 1.2$1.25$4.25$0.15-$30
Muse Spark 1.2 Contributor$0.10$0.20$0.002-$30
Kimi K3$3.00$15.00$0.30-$30
Kimi K2.7 Code HighSpeed$1.90$8.00$0.38-$30
Grok 4.5$2.00$6.00$0.50-$30
$2.00$6.00$0.50-$30
Gemini 3.7 Flash$0.75$3.75$0.075$0.04167$60
GLM-5.2 Fast$3.00$10.25$0.50-$30
Inkling$1.00$4.05$0.17-$30
Inkling Small$0.50$1.20$0.10-$30
Step 3.7 Flash$0.20$1.15$0.04-$30
Step 3.5 Flash$0.10$0.30$0.02-$30
Nemotron 3 Ultra$0.60$2.40$0.12-$30

Speed variants have their own credit limits. For example, GLM-5.2 Fast and Kimi K2.7 Code HighSpeed each get $30 in credits.

Your monthly limits reset with each billing cycle. Any active model discounts are automatically applied to your usage. You can buy extra credits at any time. Extra credits roll over, never expire and are billed at the model's regular rate.

When you hit a plan limit, Command Code uses your extra credits if you have any. If you do not have extra credits, your usage for both premium and open models pauses until the limit resets. Only Free models keep working if they are available during that time. At any point you can buy more credits to continue.

  • Everything in GOAT: All GOAT models and benefits are included.
  • $80 in credits: Use them across the models available on Pro.
  • Premium models: Use Claude, GPT, Gemini, and more.
  • Flexible usage: Your limits reset throughout the billing cycle.
  • Extra credits: Buy more credits at model cost. They roll over and do not expire.
  • Zero data retention: Most models use ZDR by default. You can also require ZDR for every request.

ZDR requests use standard plan credits because they may need different routing. See Pricing & Limits for details.

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

Only need open models? The GOAT plan is $10/month. Need Claude Opus or Fable? Compare the Max plans, or use the pay-as-you-go Provider API. Full comparison and FAQs live on Pricing & Limits.

The Pro plan has API access. You call the Provider API endpoints with your Command Code API key, and usage is metered against your Pro credits and the models included above.

1

Subscribe

Pick the Pro plan from Studio > Billing or the pricing page. Every plan except the Go plan has API access.

2

Create an API key

The same key authenticates the CLI and the API. Create one from your API keys page in Studio.

3

Call the API

Point any OpenAI or Anthropic compatible client at https://api.commandcode.ai/provider/v1 and send your first request. Premium models take the Anthropic Messages shape on /v1/messages, open models take the OpenAI shape on /v1/chat/completions.

Provider API Example Request

curl https://api.commandcode.ai/provider/v1/messages \ -H "Authorization: Bearer <CMD_API_KEY>" \ -H "Content-Type: application/json" \ -d '{ "model": "claude-sonnet-4-6", "max_tokens": 1024, "messages": [{"role": "user", "content": "Write a haiku about race conditions."}] }'

Read the Provider API quickstart for more details.

We still recommend the Command Code CLI: harness engineering makes the same credits go further - the Read tool keeps ~25 billion junk tokens a month out of your context, tool call repairs are free on every plan, and ~98% cache hit rates mean most of every request bills as cheap cache reads.

What models are available on the Pro plan?

45+ open and premium models, including Claude, GPT, and Gemini - everything in the GOAT plan plus the premium models. Switch any time with /model in interactive mode. Browse them all on Available Models, with per-token rates on Pricing & Limits. Claude Opus, Claude Fable, and Fugu Ultra need a Max plan or pay-as-you-go credits.

How is Pro different from the GOAT plan?

Pro is everything in the GOAT plan and $10 on top: $20/month for $80 in credits, with premium models like Claude, GPT, and Gemini included at up to $20 of monthly usage each.

What are the usage limits on the Pro plan?

$16 of usage in any 5 hours, $40 in any 7 days, and $80 per month. Limits reset with each window and with your billing cycle - see Usage Limits.

Can I buy extra credits?

Yes, any time. Buy pay-as-you-go credits at model cost - they unlock every model (including Claude Opus and Fable), roll over, and never expire.

Can I use the Pro plan via API?

Yes. Every plan except the Go plan has API access - you use the same Provider API the Provider plan uses (OpenAI Chat Completions and Anthropic Messages endpoints, one key for the CLI and the API), so you can integrate Pro with any other agent. We still recommend the Command Code CLI, because phenomenal harness engineering makes the same credits go further: our Read tool keeps ~25 billion junk tokens a month out of your context, tool call repairs are free on every plan, and we run ~98% cache hit rates so most of every request bills as cheap cache reads.

Is the Pro plan available worldwide?

Yes. Open-source models run on infrastructure in the US, EU, and Singapore for reliable access worldwide.

Can I enforce zero data retention?

Yes. Most models are ZDR by default - agreements are renewed monthly and can take time for brand-new models. You can also enforce ZDR on every request (which can change model prices based on the provider, as explained in Pricing & Limits). 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.

Can I upgrade, downgrade, or cancel any time?

Yes. Change or cancel your plan from Studio > Billing at any time. Any extra credits you have bought stay with your account - they roll over and never expire.