CommandCode Plans
The complete CommandCode lineup — Go ($1/mo), GOAT ($10/mo), Pro ($20/mo), Max ($100–$200/mo), Provider API ($15/mo), and Teams ($40/mo) — covering every model, request budget, credit allowance, usage limit, and active deal.
Every plan buys dollar-denominated credits that refresh monthly, top up at model cost, roll over, and never expire. Active deals apply automatically and stack on top of your credit multipliers — zero markup, no promo codes, no manual toggles.
At a Glance (Pricing & Request Breakdown)
Official side-by-side comparison sourced directly from the CommandCode Pricing Page and Pricing & Limits Documentation.
| Plan | Price / mo | Monthly Credits | Typical Request Volume | Effective Usage (with Deals) | Included Models & Access | Official Doc |
|---|---|---|---|---|---|---|
| Go | $1 | $10 | ~15K requests | Up to ~$40 usage | Open models + select premium (GPT-5.6 Luna, Grok 4.5, Qwen Max & Plus) | Go Docs ↗ |
| GOAT | $10 | $70 | ~75K requests | Up to ~$100 usage | 30+ open & closed models (GLM-5.2, GPT-5.6 Luna, DeepSeek V4 Pro) | GOAT Docs ↗ |
| Pro | $20 | $80 | ~100K requests | Up to ~$150 usage | 47 models (incl. Claude Sonnet/Haiku, GPT Sol/Terra, Gemini 3.6/3.5) | Pro Docs ↗ |
| Max 10× | $100 | $150 | ~219K requests | Up to ~$600 usage | Every model, no restrictions (incl. Claude Opus, Claude Fable, Fugu Ultra) | Max Docs ↗ |
| Max 20× | $200 | $300 | ~437K requests | Up to ~$1,200 usage | Every model, max daily throughput across all projects | Max Docs ↗ |
| Provider API | $15 | Pay as you go | Uncapped (on demand) | Raw API cost (no markup) | OpenAI & Anthropic compatible endpoints, all models & deals apply | API Docs ↗ |
| Teams | $40 | Pooled credits | ~35K requests base | Shared bucket | Team collaboration, shared billing, central org administration | Teams Info ↗ |
Effective Model Usage Across Plans
Because active model deals stack on top of your plan credit pool, your dollar credit budget yields significantly higher effective model usage:
| Model Deal | Go ($1/mo) | GOAT ($10/mo) | Pro ($20/mo) | Max 10× ($100/mo) | Max 20× ($200/mo) |
|---|---|---|---|---|---|
| DeepSeek V4 Pro (4× deal) | ~$40 usage | ~$80 usage | ~$120 usage | ~$600 usage | ~$1,200 usage |
| MiMo V2.5 (5× deal) | ~$50 usage | ~$100 usage | ~$150 usage | ~$750 usage | ~$1,500 usage |
| GPT-5.6 Terra & Luna (Up to 2×) | ~$20 usage (Luna) | $70 usage (Luna) | $80 usage | ~$300 usage | ~$600 usage |
| Qwen 3.7 Max (2× deal) | ~$20 usage | ~$40 usage | ~$60 usage | ~$300 usage | ~$600 usage |
| MiniMax M3 (2× deal) | ~$20 usage | $47 usage | $57 usage | ~$300 usage | ~$600 usage |
| Laguna S 2.1 | Free | Free | Free | Free | Free |
| Ling 3.0 Flash | Free | Free | Free | Free | Free |
🔥 Active Deals Summary
Deals apply automatically across every plan (including top-up credits) and stack on top of your plan credit multipliers. Details live on the CommandCode Deals page.
| Model / Feature | Discount / Value | Term | Key Details & Per-1M Token Rates |
|---|---|---|---|
| DeepSeek V4 Pro | 75% off (4× credit value) | Permanent | Input $0.435 |
| GPT-5.6 Luna | Up to 95% off | Ends Aug 13, 2026 | 50% off list price ($0.10 in / $0.60 out / $0.01 cache read / $0.125 cache write). Available on Go. |
| GPT-5.6 Terra | 50% off | Ends Aug 13, 2026 | Promo rates ($1.00 in / $6.00 out / $0.10 cache read / $1.25 cache write), then reverts to list price. |
| MiniMax M3 | 50% off (2× credit value) | Permanent | Input $0.30 |
| MiMo V2.5 Pro | Up to 99% off | Permanent | Input $0.435 |
| MiMo V2.5 | Up to 98% off | Permanent | Input $0.14 |
| Laguna S 2.1 | 100% off (FREE) | While capacity lasts | Free input, output, and cache reads on every plan (256K context window). |
| Ling 3.0 Flash | 100% off (FREE) | Through Aug 2, 2026 | Free input, output, and cache reads across all subscription tiers. |
Go — $1/month
The entry point to CommandCode: open-source models, available globally, with credits that never expire. Sourced from the official Go Plan documentation.
$1 buys $10 of credits every month — yielding ~15K typical requests (or up to ~75K on lightweight open models).
- Open models included: Kimi, DeepSeek, GLM, MiniMax, Qwen, Tencent, Step, MiMo, Nemotron, Inkling, etc.
- Closed models included: GPT-5.6 Luna, Grok 4.5, Muse Spark 1.2 Contributor, and Qwen Max & Plus.
- Credits that never expire: Monthly credits reset each cycle; extra top-up credits roll over forever.
- Global availability: Open-source models run on infrastructure in the US, EU, and Singapore for fast access worldwide.
- Privacy & Security: CommandCode never trains on your code. Enforce zero data retention on every request using
CMD_ZDR=1. Learn more in the Security & Privacy docs.
What $1 is worth on Go
| Model | Credit Math | ≈ Usage Value | ≈ Total Savings |
|---|---|---|---|
| DeepSeek V4 Pro | $1 → $10 credits → 4× deal rate | ~$40 of usage | 98% off |
| GPT-5.6 Luna | $1 → $10 credits → 2× deal rate | ~$20 of usage | 95% off |
| MiniMax M3 | $1 → $10 credits → 2× deal rate | ~$20 of usage | 95% off |
| MiMo V2.5 Pro | $1 → $10 credits → 5× deal rate | ~$50 of usage | 98% off |
Models on Go
Go includes 32 models. Selected per-token rates (per 1M tokens in USD):
| Model | Context | Input / 1M | Output / 1M | Cache Read / 1M | Cache Write / 1M |
|---|---|---|---|---|---|
| Kimi K3 | 1M | $3.00 | $15.00 | $0.30 | — |
| Kimi K2.7 Code | 256K | $0.95 | $4.00 | $0.19 | — |
| GLM-5.2 | 1M | $1.40 | $4.40 | $0.26 | — |
| GLM-5.2 Fast | 1M | $3.00 | $10.25 | $0.50 | — |
| DeepSeek V4 Flash | 1M | $0.14 | $0.28 | $0.0028 | — |
| DeepSeek V4 Pro | 1M | $0.435 | $0.87 | $0.003625 | — |
| Qwen 3.8 Max | 1M | $2.00 | $6.00 | $0.25 | $2.50 |
| 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 |
| Tencent Hy3 | 262K | $0.14 | $0.58 | $0.035 | — |
| MiniMax M3 | 1M | $0.30 | $1.20 | $0.06 | — |
| MiMo V2.5 Pro | 1M | $0.435 | $0.87 | $0.0036 | — |
| MiMo V2.5 | 1M | $0.14 | $0.28 | $0.0028 | — |
| GPT-5.6 Luna | 1.1M | $0.10 | $0.60 | $0.01 | $0.125 |
| Grok 4.5 | 500K | $2.00 | $6.00 | $0.50 | — |
| Inkling | 256K | $1.00 | $4.05 | $0.17 | — |
| Inkling Small | 1M | $0.50 | $1.20 | $0.10 | — |
| Step 3.7 Flash | 256K | $0.20 | $1.15 | $0.04 | — |
| Nemotron 3 Ultra | 1M | $0.60 | $2.40 | $0.12 | — |
| Laguna S 2.1 | 256K | Free | Free | Free | — |
For more details on Go promo rates, see CommandCode Go Deals or browse the full Available Models list.
GOAT — $10/month
The best low-cost coding plan: unlimited coding on 30+ top open and closed models for $10/month. Your $10 buys $70 of credits (~75K typical requests) — a 7× multiplier. Sourced from the official GOAT Plan documentation.
With deals, the $70 credit pool stretches beyond $100 of usage — more than 10× what you pay.
Usage Limits Window
| Limit Window | Usage Allowance | Window Percentage |
|---|---|---|
| 5-hour limit | $14 of usage | 20% of monthly limit |
| Weekly limit | $35 of usage | 50% of monthly limit |
| Monthly limit | $70 of usage | 100% of monthly limit |
Model Credits (Per-model monthly allowance)
| Model | Input / 1M | Output / 1M | Cache Read / 1M | Cache Write / 1M | Monthly Credits |
|---|---|---|---|---|---|
| GLM-5.2 | $1.40 | $4.40 | $0.26 | — | $70 |
| GPT-5.6 Luna | $0.20 | $1.20 | $0.02 | $0.25 | $70 |
| Tencent Hy3 | $0.14 | $0.58 | $0.035 | — | $70 |
| Qwen 3.7 Max | $2.50 | $7.50 | $0.50 | $3.13 | $70 |
| Qwen 3.7 Plus | $0.40 | $1.60 | $0.08 | $0.50 | $70 |
| Qwen 3.6 Plus | $0.50 | $3.00 | $0.10 | — | $70 |
| DeepSeek V4 Flash | $0.14 | $0.28 | $0.0028 | — | $60 |
| Kimi K2.7 Code | $0.95 | $4.00 | $0.19 | — | $60 |
| MiniMax M3 | $0.30 | $1.20 | $0.06 | — | $47 |
| MiMo V2.5 | $0.14 | $0.28 | $0.0028 | — | $30 |
| Qwen 3.8 Max | $2.00 | $6.00 | $0.25 | $2.50 | $25 |
| DeepSeek V4 Pro | $0.435 | $0.87 | $0.003625 | — | $20 |
| MiMo V2.5 Pro | $0.435 | $0.87 | $0.0036 | — | $20 |
Pro — $20/month
Premium models + everything in GOAT for $20/month. Your $20 buys $80 of usage (~100K typical requests). Sourced from the official Pro Plan documentation.
Pro adds the full Claude, GPT, and Gemini line-ups on top of everything GOAT has — premium models at $20 monthly usage each (GPT-5.6 Luna keeps its boosted $80 allowance).
Premium Model Allowances on Pro
| Model | Input / 1M | Output / 1M | Cache Read / 1M | Cache Write / 1M | 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 |
| GPT-5.6 Terra | $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 |
Note: Claude Sonnet 5 is on introductory pricing ($2.00 in / $10.00 out); standard rates from September 1, 2026 revert to $3.00 / $15.00.
Max — $100–$200/month
The high-volume tiers for power users running agents continuously. Both unlock every single model — open-source and premium, including Claude Opus, Claude Fable, and Fugu Ultra — with zero restrictions. Sourced from the official Max Plans documentation.
Max 10× — $100/month
- $150 of credits · ~219K requests/month (up to ~$600 effective usage with deals).
- Every model, no restrictions — includes Claude Opus 5/4.8/4.7/4.6, Claude Fable 5, and Fugu Ultra.
Max 20× — $200/month
- $300 of credits · ~437K requests/month (up to ~$1,200 effective usage with deals).
- Every model, max throughput — ideal for heavy power users and agency teams.
Flagship & Premium Models on Max
| Model | Context | Input / 1M | Output / 1M | Cache Read / 1M | Cache Write / 1M |
|---|---|---|---|---|---|
| Claude Fable 5 | 1M | $10.00 | $50.00 | $1.00 | $12.50 |
| Claude Opus 5 | 1M | $5.00 | $25.00 | $0.50 | $6.25 |
| Claude Opus 4.8 / 4.7 / 4.6 | 1M | $5.00 | $25.00 | $0.50 | $6.25 |
| Claude Sonnet 5 | 1M | $2.00 | $10.00 | $0.20 | $2.50 |
| Claude Sonnet 4.6 | 1M | $3.00 | $15.00 | $0.30 | $3.75 |
| Claude Haiku 4.5 | 200K | $1.00 | $5.00 | $0.10 | $1.25 |
| GPT-5.6 Sol | 1.1M | $5.00 | $30.00 | $0.50 | $6.25 |
| GPT-5.6 Terra | 1.1M | $1.00 | $6.00 | $0.10 | $1.25 |
| GPT-5.6 Luna | 1.1M | $0.10 | $0.60 | $0.01 | $0.125 |
| GPT-5.5 | 200K | $5.00 | $30.00 | $0.50 | — |
| GPT-5.4 | 400K | $2.50 | $15.00 | $0.25 | — |
| GPT-5.4 Mini | 400K | $0.75 | $4.50 | $0.075 | — |
| GPT-5.3 Codex | 400K | $2.00 | $8.00 | $0.50 | — |
| Gemini 3.6 Flash | 1M | $1.50 | $7.50 | $0.15 | — |
| Gemini 3.5 Flash | 1M | $1.50 | $9.00 | $0.15 | — |
| Gemini 3.5 Flash Lite | 1M | $0.30 | $2.50 | $0.03 | — |
| Gemini 3.1 Flash Lite | 1M | $0.25 | $1.50 | $0.03 | — |
| Fugu Ultra | 1M | $5.00 | $30.00 | $0.50 | — |
| Muse Spark 1.2 | 1M | $1.25 | $4.25 | $0.15 | — |
| Muse Spark 1.1 | 1M | $1.25 | $4.25 | $0.15 | — |
| Grok 4.5 | 500K | $2.00 | $6.00 | $0.50 | — |
Provider API ($15/month) & Teams ($40/month)
- Provider API ($15/mo): Sourced from the Provider API documentation. Direct pay-as-you-go access to OpenAI and Anthropic compatible endpoints with zero markup. All model deals apply automatically. Top-ups roll over forever.
- Teams ($40/mo): Sourced from the CommandCode Teams documentation. Flat plan with ~35K requests base volume. Pooled credits, shared billing, central org administration, and priority support.
How Credits Work & Limits
- Resets monthly: Credit budget refreshes automatically at the start of each billing cycle.
- Top up automatically: Buy extra credits at raw model cost — extra credits roll over and never expire.
- Deals apply automatically: Permanent discounts and promo multipliers apply to every request, including extra credits.
- Beyond plan limits: Requests fall back to extra top-up credits. If empty, paid models pause while 100% free models (`Laguna S 2.1`, `Ling 3.0 Flash`) keep working.
Get Started
- Install CLI:
npm i -g command-code - Sign in and launch:
cmd(macOS/Linux) orcmdc(Windows) - Select or upgrade plan from Studio → Billing or the pricing page
Browse the rest of the Dump collection.