Pro Plan
The Command Code Pro plan has premium models + everything in GOAT plan - for $20/month. Your $20 buys $80 of usage, with every open model's GOAT allowance growing by $10, and most of the premium models joining at $20 each.
See every plan side by side on Pricing & Limits, or pick a plan from Studio > Billing.
Pro plan adds premium models on top of everything GOAT has. It costs $10 more than GOAT plan, and every open model's allowance grows by $10. Premium models join the same pool at a flat $20 each.
The GOAT plan made open models accessible to everyone: $10 for $70 of usage on per-model allowances.
The Pro plan brings premium models with more total usage, bigger per-model budgets on the models you use most, and the same premium model access.
Every model below is included on the Pro plan - switch between them any time with /model in interactive mode. Rates are per 1M tokens; the full catalog, including Claude Opus and Fable (which need Max), lives on commandcode.ai/models.
| Caps | ||||||||
|---|---|---|---|---|---|---|---|---|
| 1M | 54.1 | — | $1.25 | $4.25 | $0.15 | — | ||
| 1M | 54.1 | — | $0.10 | $0.20 | $0.002 | — | ||
| 1M | not yet scored | — | $2.00 | $6.00 | $0.25 | $2.50 | ||
| 1M | 50 | 102 | $0.14 | $0.28 | $0.0028 | — | ||
| 1M | 40.2 | 123 | $0.50 | $1.20 | $0.10 | — | ||
| 1M | not yet scored | — | $0.03 | $0.13 | $0.006 | $0.038 | ||
| 1M | 36.5 | 381 | $0.30 | $2.50 | $0.03 | — | ||
| 1M | 50.1 | 231 | $1.50 | $7.50 | $0.15 | — | ||
| 256K | not yet scored | — | Free | Free | Free | — | ||
| 256K | 40.7 | 85 | $1.00 | $4.05 | $0.17 | — | ||
| 1M | 57.1 | 35 | $3.00 | $15.00 | $0.30 | — | ||
| 1M | 50.6 | 166 | $1.25 | $4.25 | $0.15 | — | ||
GPT-5.6 Luna-50%Ends August 13, 2026 | 1.1M | 51.2 | 176 | $0.10 | $0.60 | $0.01 | $0.125 | |
| 1.1M | 58.9 | 78 | $5.00 | $30.00 | $0.50 | $6.25 | ||
GPT-5.6 Terra-50%Ends August 13, 2026 | 1.1M | 55.0 | 144 | $1.00 | $6.00 | $0.10 | $1.25 | |
| 500K | 53.8 | 62 | $2.00 | $6.00 | $0.50 | — | ||
| 262K | 41.2 | 72 | $0.14 | $0.58 | $0.035 | — | ||
Claude Sonnet 5Standard rates from September 1, 2026 | 1M | 53.4 | 89 | $2.00 | $10.00 | $0.20 | $2.50 | |
| 1M | not yet scored | — | $3.00 | $10.25 | $0.50 | — | ||
| 1M | 51.1 | 194 | $1.40 | $4.40 | $0.26 | — | ||
| 262K | not yet scored | — | $1.90 | $8.00 | $0.38 | — | ||
| 256K | 41.9 | 39 | $0.95 | $4.00 | $0.19 | — | ||
| 1M | 37.8 | 146 | $0.60 | $2.40 | $0.12 | — | ||
| 1M | 44.4 | 87 | — | |||||
| 1M | 39.0 | 52 | $0.40 | $1.60 | $0.08 | $0.50 | ||
| 256K | 30.3 | 393 | $0.20 | $1.15 | $0.04 | — | ||
| 1M | 37.2 | 74 | — | |||||
| 1M | 42.2 | 41 | — | |||||
| 1M | 46.0 | 204 | $2.50 | $7.50 | $0.50 | $3.13 | ||
| 1M | 50.2 | 270 | $1.50 | $9.00 | $0.15 | — | ||
| 1M | 25.0 | 294 | $0.25 | $1.50 | $0.03 | — | ||
| 1M | 26.0 | — | $0.10 | $0.30 | $0.02 | — | ||
| 200K | 40.2 | — | $1.40 | $4.40 | $0.26 | — | ||
| 200K | 54.8 | — | $5.00 | $30.00 | $0.50 | — | ||
| 200K | 38.1 | — | $0.30 | $1.20 | $0.06 | — | ||
| 200K | 40.0 | — | $1.30 | $7.80 | $0.26 | $1.63 | ||
| 200K | 39.6 | 56 | $0.50 | $3.00 | $0.10 | — | ||
| 1M | 44.3 | 60 | — | |||||
| 256K | 44.2 | — | $0.95 | $4.00 | $0.16 | — | ||
| 400K | 40.0 | — | $0.75 | $4.50 | $0.075 | — | ||
| 200K | 39.5 | — | $1.00 | $3.20 | $0.20 | — | ||
| 400K | 44.3 | 129 | $2.00 | $8.00 | $0.50 | — | ||
| 400K | 51.4 | — | $2.50 | $15.00 | $0.25 | — | ||
| 256K | 35.4 | — | $0.60 | $3.00 | $0.10 | — | ||
| 200K | 33.7 | — | $0.30 | $1.20 | $0.03 | — | ||
| 200K | 23.7 | 125 | $1.00 | $5.00 | $0.10 | $1.25 | ||
| 1M | 47.2 | — | $3.00 | $15.00 | $0.30 | $3.75 |
The Pro plan includes the following usage limits:
- 5-hour limit - $16 of usage
- Weekly limit - $40 of usage
- Monthly limit - $80 of usage
How far each window goes depends on the model - cheaper models allow more requests, pricier models fewer. We have a usage estimation calculator. Estimated request counts per limit window:
| Model | Requests / 5 hours | Requests / week | Requests / month |
|---|---|---|---|
| DeepSeek V4 Flash (latest) | 68,200 | 136,000 | 227,000 |
| GLM-5.2 | 1,620 | 3,250 | 5,410 |
| GPT-5.6 Luna | 17,800 | 35,500 | 59,200 |
| Tencent Hy3 | 12,100 | 24,300 | 40,400 |
| Qwen 3.7 Max | 842 | 1,680 | 2,810 |
| Qwen 3.7 Plus | 5,170 | 10,300 | 17,200 |
| Qwen 3.6 Plus | 4,000 | 8,000 | 13,300 |
| MiniMax M3 | 5,040 | 10,100 | 16,800 |
| Kimi K2.7 Code | 1,900 | 3,800 | 6,330 |
| Qwen 3.8 Max | 686 | 1,370 | 2,290 |
| MiMo V2.5 | 39,000 | 77,900 | 130,000 |
| DeepSeek V4 Pro | 12,800 | 25,600 | 42,700 |
| MiMo V2.5 Pro | 12,800 | 25,600 | 42,700 |
| Muse Spark 1.2 | 963 | 1,930 | 3,210 |
| Muse Spark 1.2 Contributor | 40,900 | 81,800 | 136,000 |
| Kimi K3 | 441 | 882 | 1,470 |
| Kimi K2.7 Code HighSpeed | 407 | 814 | 1,360 |
| Grok 4.5 | 324 | 647 | 1,080 |
| GLM-5.2 Fast | 311 | 622 | 1,040 |
| Inkling | 890 | 1,780 | 2,970 |
| Inkling Small | 1,600 | 3,190 | 5,320 |
| Step 3.7 Flash | 3,770 | 7,530 | 12,600 |
| Step 3.5 Flash | 7,890 | 15,800 | 26,300 |
| Nemotron 3 Ultra | 1,290 | 2,590 | 4,310 |
| Claude Sonnet 5 | 448 | 896 | 1,490 |
| Claude Sonnet 4.6 | 299 | 597 | 995 |
| Claude Haiku 4.5 | 896 | 1,790 | 2,990 |
| GPT-5.6 Sol | 178 | 355 | 592 |
| GPT-5.6 Terra | 888 | 1,780 | 2,960 |
| GPT-5.5 | 178 | 355 | 592 |
| GPT-5.4 | 355 | 710 | 1,180 |
| GPT-5.4 Mini | 1,180 | 2,370 | 3,940 |
| GPT-5.3 Codex | 215 | 430 | 717 |
| Gemini 3.6 Flash | 588 | 1,180 | 1,960 |
| Gemini 3.5 Flash | 571 | 1,140 | 1,900 |
| Gemini 3.5 Flash Lite | 2,680 | 5,360 | 8,930 |
| Gemini 3.1 Flash Lite | 3,000 | 6,000 | 10,000 |
| Muse Spark 1.1 | 642 | 1,280 | 2,140 |
The GPT-5.6 Luna number is no typo: Pro gives Luna a full $80 allowance - good for roughly 59,200 requests a month.
Model the math yourself with the calculator on Pricing & Limits - it knows every model's Pro allowance.
The estimates assume a typical agent request - ~800 fresh input tokens, ~50,000 cache-read tokens, and ~125-200 output tokens depending on the model family - at the prices below per 1M tokens. Most of an agent's volume is cache reads, which is why cache hit rates matter so much. Browse every model on Available Models, with per-token rates on Pricing & Limits.
Every model on the Pro plan is listed below:
| Model | Input | Output | Cache Read | Cache Write | Monthly credits |
|---|---|---|---|---|---|
| GLM-5.2 | $1.40 | $4.40 | $0.26 | - | $80 |
| $0.20 | $1.20 | $0.02 | $0.25 | $80 | |
| Tencent Hy3 | $0.14 | $0.58 | $0.035 | - | $80 |
| Qwen 3.7 Max | $2.50 | $7.50 | $0.50 | $3.13 | $80 |
| $0.40 | $1.60 | $0.08 | $0.50 | $80 | |
| $0.50 | $3.00 | $0.10 | - | $80 | |
| DeepSeek V4 Flash (latest) | $0.14 | $0.28 | $0.0028 | - | $70 |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | - | $70 |
| $0.30 | $1.20 | $0.06 | - | $57 | |
| MiMo V2.5 | $0.14 | $0.28 | $0.0028 | - | $40 |
| Qwen 3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | $35 |
| DeepSeek V4 Pro | $0.435 | $0.87 | $0.003625 | - | $30 |
| MiMo V2.5 Pro | $0.435 | $0.87 | $0.0036 | - | $30 |
Premium models - Claude, GPT, and Gemini - are all on the plan at a flat $20 of monthly usage each, drawing from the same shared pool. The exceptions are Claude Opus, Claude Fable, and Fugu Ultra, which need the Max plans or the pay-as-you-go Provider API.
| Model | Input | Output | Cache Read | Cache Write | Monthly 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 |
| GPT-5.6 Sol | $5.00 | $30.00 | $0.50 | $6.25 | $20 |
| $1.00 | $6.00 | $0.10 | $1.25 | $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 start at $30 credits on the $20/mo Pro plan until we negotiate better deals. The allowance updates automatically the moment a deal starts - no codes, no toggles.
| Model | Input | Output | Cache Read | Cache Write | Monthly credits |
|---|---|---|---|---|---|
| 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 |
| 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 are separate models with their own credits: GLM-5.2 Fast and Kimi K2.7 Code HighSpeed carry the standard $30 credits, not their base model's boosted allowance.
We're constantly negotiating better terms with providers, so the allowances above can change at any time. When a deal starts, your allowance updates by itself.
- Everything on GOAT, plus $10: Every open model's GOAT allowance grows by $10 - and the standard open-model credits rise from $20 to $30.
- Premium models included: Claude, GPT, and Gemini at $20 of monthly usage each (except Claude Opus, Claude Fable, and Fugu Ultra - those need Max). Switch any time with
/model. - Usage limits that scale: 30% of your monthly usage in any 5 hours, 60% in any 7 days - see Usage Limits.
- Extra credits 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.
- Global availability: Open-source models run on infrastructure in the US, EU, and Singapore for reliable access worldwide.
- Zero data retention available: 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; ZDR requests meter at the standard credits ($30 open / $20 premium) since zero-retention routing bypasses the capacity that funds the boosted allowances (details in Pricing & Limits).
Your budget refreshes at the start of every billing cycle, with every model discount already baked into the allowances - no codes, no toggles.
Buy extra credits at model cost any time: they roll over, never expire, and bill at the model's regular rate, since the bigger allowances 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.
- Install:
npm i -g command-code - Sign in and start coding with
cmd(macOS/Linux) orcmdc(Windows) - 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.