Copy Page

Max Plans

The Max plans are the high-volume Command Code tiers for power users running agents all day. Both unlock every model - open-source and premium, including Claude Opus, Claude Fable, and Fugu Ultra - with no restrictions.

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

DEALgoogle/gemini-3.7-flash 50% off.through December 31, 2026

DEALminimax-m3 2 usage. Every credit goes 2 further.

DEALmimo-v2.5 + mimo-v2.5-pro Up to 99% off. Every dollar of credit goes further on these models.

DEALlaguna-s-2.1-free is free. Requests on this model cost no credits.while capacity lasts

DEALminimax-m3-free and minimax-m2.7-free are free.through September 5, 2026

At a glance

Plan	Price/mo	Credits/mo	Included LLM Usage	Models
Max 10	$100	$150	~230K requests	Every model, no restrictions
Max 20	$200	$300	~370K requests	Every model, no restrictions

Both include more credits for the same cost as raw API pricing. Credits reset monthly, top up at model cost, roll over, and never expire.

Max 10 gives you a $150 standard model usage limit and a $100 premium model usage limit (Claude Opus and Fable among them). Max 20 gives you $300 standard and $200 premium. See How credits work.

Max 10

$100/month $150 of credits ~230K requests. For power users running Command Code throughout the workday.

Every model, including Claude Opus, Fable, and Fugu Ultra. No model restrictions.
$150 standard usage limit, $100 premium usage limit.
~230K requests/month on a balanced mix (~43% standard / ~57% premium).
Best for engineers who keep an agent running all day across multiple projects.

Max 20

$200/month $300 of credits ~370K requests. The top tier - maxed-out daily usage at the highest request volume.

Every model, no restrictions, including Claude Opus, Fable, and Fugu Ultra.
$300 standard usage limit, $200 premium usage limit.
~370K requests/month on a balanced mix (~43% standard / ~57% premium).
Best for the heaviest users and small teams who want the most usage on one account.

Models

Max 10 and Max 20 include all 63 models - the full open-source + premium catalog with no restrictions, including Claude Opus, Claude Fable, and Fugu Ultra. Switch any time with /model. Browse them all on Available Models.

Usage Limits

Max 10 and Max 20 include the following usage limits:

	Max 10	Max 20
5-hour limit	$45 of usage	$90 of usage
Weekly limit	$90 of usage	$180 of usage
Monthly limit	$150 of usage	$300 of usage

Max 10 gives you a $150 standard model usage limit and a $100 premium model usage limit. Max 20 gives you $300 standard and $200 premium. See How credits work.

How far each window goes depends on the model - cheaper models allow more requests, pricier models fewer. We have a usage estimation calculator. Here's what each window buys per model on Max 10. Max 20 doubles every number below:

Model	Requests / 5 hours	Requests / week	Requests / month
Laguna S 2.1	Free	Free	Free
MiniMax M3	Free	Free	Free
MiniMax M2.7	Free	Free	Free
Tencent Hy4 Preview	13,800	27,500	45,900
Tencent Hy3	22,800	45,500	75,800
Kimi K3	2,210	4,410	7,350
Kimi K2.7 Code	4,070	8,140	13,600
Kimi K2.7 Code HighSpeed	2,030	4,070	6,780
Kimi K2.6	4,710	9,410	15,700
Kimi K2.5	7,400	14,800	24,700
GLM-5.3 Flash	26,500	53,100	88,500
GLM-5.3	3,040	6,090	10,100
GLM-5.2	3,040	6,090	10,100
GLM-5.2 Fast	1,560	3,110	5,180
GLM-5.1	3,040	6,090	10,100
GLM-5	3,990	7,980	13,300
MiniMax M3	13,300	26,500	44,200
MiniMax M2.7	13,300	26,500	44,200
MiniMax M2.5	23,800	47,600	79,400
DeepSeek V4 Pro (latest)	22,200	44,500	74,100
DeepSeek V4 Flash (latest)	68,400	137,000	228,000
DeepSeek V4 Flash Vision (exp)	68,400	137,000	228,000
Qwen 3.8 Max	2,940	5,880	9,800
Qwen 3.8 27B	15,400	30,800	51,400
Qwen 3.6 Max Preview	2,880	5,770	9,620
Qwen 3.6 Plus	7,500	15,000	25,000
Qwen 3.7 Max	1,580	3,160	5,260
Qwen 3.7 Plus	9,700	19,400	32,300
Qwen 3.8 Flash	44,000	88,100	147,000
Qwen 3.7 Flash	129,000	257,000	429,000
Step 3.7 Flash	18,800	37,700	62,800
Step 3.5 Flash	39,500	78,900	132,000
MiMo V2.5 Pro	64,100	128,000	214,000
MiMo V2.5	146,000	292,000	487,000
Nemotron 3 Ultra	6,470	12,900	21,600
Claude Fable 5	448	896	1,490
Claude Opus 5	896	1,790	2,990
Claude Opus 4.8	896	1,790	2,990
Claude Opus 4.7	896	1,790	2,990
Claude Opus 4.6	896	1,790	2,990
Claude Sonnet 5	2,240	4,480	7,460
Claude Sonnet 4.6	1,490	2,990	4,980
Claude Haiku 4.5	4,480	8,960	14,900
GPT-5.6 Sol	1,330	2,660	4,440
GPT-5.6 Terra	2,220	4,440	7,400
GPT-5.6 Luna	33,300	66,600	111,000
GPT-5.5	888	1,780	2,960
GPT-5.4	1,780	3,550	5,920
GPT-5.4 Mini	5,920	11,800	19,700
GPT-5.3 Codex	1,080	2,150	3,590
Gemini 3.7 Flash	8,820	17,600	29,400
Gemini 3.6 Flash	2,940	5,880	9,800
Gemini 3.5 Flash	2,860	5,710	9,520
Gemini 3.5 Flash Lite	13,400	26,800	44,600
Gemini 3.1 Flash Lite	15,000	30,000	50,000
Fugu Ultra	857	1,710	2,860
Muse Spark 1.2	4,810	9,630	16,000
Muse Spark 1.2 Contributor	205,000	409,000	682,000
Muse Spark 1.1	3,210	6,420	10,700
Grok 4.6	1,620	3,240	5,400
Grok 4.5	1,620	3,240	5,400
Inkling	4,450	8,900	14,800
Inkling Small	7,980	16,000	26,600

The estimates assume a typical agent request - ~7001K fresh input tokens, ~42K56K cache-read tokens, and ~125200 output tokens depending on the model family. Long conversations cost more, since every turn re-reads the full context - use /clear or a new session for unrelated tasks. The Usage page in Studio always reflects the actual price charged per request.

Every model on Max is listed below, with its monthly credit limit on each plan:

Model	Input	Output	Cache Read	Cache Write	Max 10 credits	Max 20 credits
Laguna S 2.1	$0.00	$0.00	$0.00	-	Free	Free
MiniMax M3	$0.00	$0.00	$0.00	-	Free	Free
MiniMax M2.7	$0.00	$0.00	$0.00	-	Free	Free
Tencent Hy4 Preview	$0.834	$2.501	$0.042	-	$150	$300
Tencent Hy3	$0.14	$0.58	$0.035	-	$150	$300
Kimi K3	$3.00	$15.00	$0.30	-	$150	$300
Kimi K2.7 Code	$0.95	$4.00	$0.19	-	$150	$300
Kimi K2.7 Code HighSpeed	$1.90	$8.00	$0.38	-	$150	$300
Kimi K2.6	$0.95	$4.00	$0.16	-	$150	$300
Kimi K2.5	$0.60	$3.00	$0.10	-	$150	$300
GLM-5.3 Flash	$0.15	$0.50	$0.03	-	$150	$300
GLM-5.3	$1.40	$4.40	$0.26	-	$150	$300
GLM-5.2	$1.40	$4.40	$0.26	-	$150	$300
GLM-5.2 Fast	$3.00	$10.25	$0.50	-	$150	$300
GLM-5.1	$1.40	$4.40	$0.26	-	$150	$300
GLM-5	$1.00	$3.20	$0.20	-	$150	$300
MiniMax M3	$0.30	$1.20	$0.06	-	$150	$300
MiniMax M2.7	$0.30	$1.20	$0.06	-	$150	$300
MiniMax M2.5	$0.30	$1.20	$0.03	-	$150	$300
DeepSeek V4 Pro (latest)	$0.66	$1.98	$0.022	-	$150	$300
DeepSeek V4 Flash (latest)	$0.22	$0.66	$0.007	-	$150	$300
DeepSeek V4 Flash Vision (exp)	$0.22	$0.66	$0.007	-	$150	$300
Qwen 3.8 Max	$2.00	$6.00	$0.25	$2.50	$150	$300
Qwen 3.8 27B	$0.40	$3.00	$0.04	-	$150	$300
Qwen 3.6 Max Preview	$1.30	$7.80	$0.26	$1.63	$150	$300
Qwen 3.6 Plus	$0.50	$3.00	$0.10	-	$150	$300
Qwen 3.7 Max	$2.50	$7.50	$0.50	$3.13	$150	$300
Qwen 3.7 Plus	$0.40	$1.60	$0.08	$0.50	$150	$300
Qwen 3.8 Flash	$0.16	$0.47	$0.016	-	$150	$300
Qwen 3.7 Flash	$0.03	$0.13	$0.006	$0.038	$150	$300
Step 3.7 Flash	$0.20	$1.15	$0.04	-	$150	$300
Step 3.5 Flash	$0.10	$0.30	$0.02	-	$150	$300
MiMo V2.5 Pro	$0.435	$0.87	$0.0036	-	$150	$300
MiMo V2.5	$0.14	$0.28	$0.0028	-	$150	$300
Nemotron 3 Ultra	$0.60	$2.40	$0.12	-	$150	$300
Claude Fable 5	$10.00	$50.00	$1.00	$12.50	$100	$200
Claude Opus 5	$5.00	$25.00	$0.50	$6.25	$100	$200
Claude Opus 4.8	$5.00	$25.00	$0.50	$6.25	$100	$200
Claude Opus 4.7	$5.00	$25.00	$0.50	$6.25	$100	$200
Claude Opus 4.6	$5.00	$25.00	$0.50	$6.25	$100	$200
Claude Sonnet 5	$2.00	$10.00	$0.20	$2.50	$100	$200
Claude Sonnet 4.6	$3.00	$15.00	$0.30	$3.75	$100	$200
Claude Haiku 4.5	$1.00	$5.00	$0.10	$1.25	$100	$200
GPT-5.6 Sol	$5.00	$30.00	$0.50	$6.25	$150	$300
GPT-5.6 Terra	$2.00	$12.00	$0.20	$2.50	$100	$200
GPT-5.6 Luna	$0.20	$1.20	$0.02	$0.25	$150	$300
GPT-5.5	$5.00	$30.00	$0.50	-	$100	$200
GPT-5.4	$2.50	$15.00	$0.25	-	$100	$200
GPT-5.4 Mini	$0.75	$4.50	$0.075	-	$100	$200
GPT-5.3 Codex	$2.00	$8.00	$0.50	-	$100	$200
Gemini 3.7 Flash	$0.75	$3.75	$0.075	$0.04167	$150	$300
Gemini 3.6 Flash	$1.50	$7.50	$0.15	-	$100	$200
Gemini 3.5 Flash	$1.50	$9.00	$0.15	-	$100	$200
Gemini 3.5 Flash Lite	$0.30	$2.50	$0.03	-	$100	$200
Gemini 3.1 Flash Lite	$0.25	$1.50	$0.03	-	$100	$200
Fugu Ultra	$5.00	$30.00	$0.50	-	$100	$200
Muse Spark 1.2	$1.25	$4.25	$0.15	-	$150	$300
Muse Spark 1.2 Contributor	$0.10	$0.20	$0.002	-	$150	$300
Muse Spark 1.1	$1.25	$4.25	$0.15	-	$100	$200
Grok 4.6	$2.00	$6.00	$0.50	-	$150	$300
Grok 4.5	$2.00	$6.00	$0.50	-	$150	$300
Inkling	$1.00	$4.05	$0.17	-	$150	$300
Inkling Small	$0.50	$1.20	$0.10	-	$150	$300

For the full detail on any model's pricing - including peak/off-peak rates where they apply - see Available Models.

How credits work

On Max 10, you have a $150 standard model usage limit and a $100 premium model usage limit. On Max 20, that's $300 standard and $200 premium.

Billing category decides which limit applies, not branding. GPT-5.6 Sol and Luna, Grok 4.5 and 4.6, Gemini 3.7 Flash, and Muse Spark 1.2 are marketed as premium but bill as standard, so they use the standard limit like other standard models.

A few other things worth knowing:

Extra pay-as-you-go credits aren't capped and work on every model.
Credits reset at the start of each billing cycle.
Top up at model cost any time. Extra credits roll over and never expire.
Deals apply to every request, including extra credits, and stack on top of your plan credits - a model at 50% off makes them go twice as far. See Deals for what's running now.

Which one is right?

Max 10 - for power users running Command Code all day.
Max 20 - for maxed-out daily usage at the highest request volume.

Need more than your plan's monthly limit? Buy extra pay-as-you-go credits any time from Studio > Billing, at model cost. They roll over and never expire, or turn on auto top-up to add them automatically when your balance runs low. For raw pay-as-you-go API access with no markup, see the Provider API. Teams and organizations: contact support@commandcode.ai about Team & Enterprise plans.

Get started

Install: npm i -g command-code
Sign in and start coding with cmd
Pick Max 10 or Max 20 from Studio > Billing or the pricing page

Full comparison and FAQs live on Pricing & Limits.

API support

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

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

Create an API key

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

Call the API

Point any OpenAI or Anthropic compatible client at https://api.commandcode.ai/provider/v1Copy 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-opus-5",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "Write a haiku about race conditions."}]
  }'

Copy

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.

FAQs

What models are available on the Max plans?

Every model, with no restrictions - the full open and premium catalog, including Claude Opus, Claude Fable, and Fugu Ultra. Switch any time with /model in interactive mode. Browse them all on Available Models, with per-token rates on Pricing & Limits.

Should I pick Max 10 or Max 20?

Max 10 is $100/month for $150 of credits (~230K requests) - built for engineers who keep an agent running all day. Max 20 is $200/month for $300 of credits (~370K requests) - the top tier for the heaviest users. Both unlock every model; the only difference is how much you get.

What are the usage limits on the Max plans?

On Max 10, $45 of usage in any 5 hours and $90 in any 7 days; on Max 20, $90 and $180. Windows roll from your first request and reset on their own - see Usage Limits. Extra pay-as-you-go credits have no usage limits.

How much can I spend on premium vs. standard models?

Max 10 gives you a $150 standard model usage limit and a $100 premium model usage limit. Max 20 gives you $300 standard and $200 premium. Claude Opus and Fable use the premium limit. Billing category decides which limit applies, not branding: GPT-5.6 Sol and Luna, Grok, Gemini 3.7 Flash, and Muse Spark 1.2 are marketed as premium but bill as standard, so they use the standard limit. The usage calculator reflects this - pick a premium model on a Max plan and it divides the premium limit, not the plan total. Extra pay-as-you-go credits aren't capped and work on every model.

Can I buy extra credits?

Yes, any time. Buy pay-as-you-go credits at model cost - they unlock every model, roll over, never expire, and skip the usage limits entirely.

Can I use the Max plans via API?

Yes. Max 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 Max with any other agent. We still recommend the Command Code CLI, because our 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.

Are the Max plans 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. Upgrades take effect immediately and start both usage windows fresh; downgrades take effect at your next billing cycle. Extra credits you have bought stay with your account - they roll over and never expire.

Table of ContentsOn This Page

At a glance
Max 10
Max 20
Models
Usage Limits
How credits work
Which one is right?
Get started
API support
FAQs

Provider API// NEXT

// PREVPro Plan

Join our Discord

Chat with us and become part of the Command Code community.

Join Discord

Need help?

Open an issue on GitHub, ask on Discord, or reach out on .

Get help

2261 Market St #5698, San Francisco, CA 94114.

Plans & Pricing

Max Plans

Provider API Example Request

Join our Discord

Need help?